You are on page 1of 54

Geotech Geol Eng

https://doi.org/10.1007/s10706-020-01536-7 (0123456789().,-volV)
( 01234567
89().,-volV)

STATE-OF-THE-ART REVIEW

35 Years of (AI) in Geotechnical Engineering: State


of the Art
Ahmed M. Ebid

Received: 21 September 2019 / Accepted: 26 August 2020


 Springer Nature Switzerland AG 2020

Abstract It was 35 years ago since the first usage of Keywords (AI) techniques  Geotechnical
Artificial Intelligence (AI) technique in geotechnical engineering  Expert system  Fuzzy system  ANN 
engineering, during those years many (AI) techniques SVM  GA  GP  EPR  PSO
were developed based in mathematical, statistical and
logical concepts, but the breakthrough occurs by
mimicking the natural searching and optimization
algorithms. This huge development in (AI) techniques 1 Introduction
reflected on the geotechnical engineering problems. In
this research, 626 paper and thesis published in the Artificial Intelligence (AI) became one of the fastest
period from 1984 to 2019 concerned in applying (AI) growing industries in the 21st century because of its
techniques in geotechnical engineering were col- ability to deal with fuzzy, incomplete, distorted and
lected, filtered, arranged and classified with respect even incorrect data. This ability to handle the uncer-
to subject, (AI) technique, publisher and publishing tainty in inputs made it the perfect tool to deal with
date and stored in a database. The extracted informa- geotechnical problems. Each (AI) technique has its
tion from the database were tabulated, presented own characteristics, advantages and disadvantages;
graphically and commented. The main conclusions is this variation allows the researchers to address the
that the number of researches in this field increases same problem using different techniques to figure out
almost exponentially, the most used (AI) technique is the best technique for such problem.
the Artificial Neural Networks and its enhancements The earliest found research concerned in applying
where it is presents about half the researches and (AI) techniques in geotechnical engineering was a
finally correlating soil and rock properties is the most ‘‘Bibliography on Knowledge-Based Expert Systems
addressed subject with about 30% of the researches. in Engineering’’ by Sriram (1984). 626 researches
were collected from 1984 and up to May-2019
regardless the unpublished work on the web. During
those 35 years, many researchers tried to summarize
the previous researches, 42 state of the art and review
research were collected, most of them summarized
A. M. Ebid (&) some applications for certain techniques. The most
Department of Structural Engineering, Faculty of
Engineering and Technology, Future University, Cairo,
recent one was ‘‘Applications Of Artificial Intelli-
Egypt gence In Geotechnical Engineering’’ by Juwaied
e-mail: ahmed.abdelkhaleq@fue.edu.eg

123
Geotech Geol Eng

(2018), he summarized 24 researches in the period system about the problem and that is why (AI)
from 1996 to 2016 and addressed three subjects using techniques may be called ‘‘Learning-Machine-
five different techniques, those subjects are pile Techniques’’
capacity, settlement of shallow foundation and pre- Searching efficiency depends on both used tech-
diction of soil proprieties. nique and problem characteristics. For example,
The main objectives of this research are: mimicking techniques can deal with inaccurate, fuzzy,
incomplete and even wrong data better than the
• Build a database for related researches
mathematical or logical techniques. On other hand,
• Study the progress of using (AI) in Geotechnical
mathematical and logical techniques can provide
problems.
proof and reason for their choice.
• Find out the share of each (AI) technique
Problem characteristics could be summarized in the
• Find out the share of each research point
following points:
• Determine current research directions
• Determine future research opportunities • Problem type most engineering problems are
classification problems (binary or multi classifica-
tion), regression problems (usually multi-variable
regression) or optimization problems.
2 Overview of Artificial Intelligence
• Knowledge quality since the previous knowledge is
used to train or learn the system, then its error or
Artificial Intelligence techniques are mathematical
uncertainty will affect the accuracy of the system.
approaches which developed to search for the most
Leak of knowledge quality may eliminate some
fitting solution according to certain criteria within the
(AI) techniques.
available time and resources. Accordingly, the best
• Knowledge distribution the used knowledge
found solution varies with the available time and
should uniformly cover all the variable ranges
resources, the more searching time and more powerful
(solution space), otherwise the accuracy of the
hard and software the wider solution space could be
system will varies over the solution space.
covered and hence, it is more likely to find more
• Restrictions present any limitations on variables
accurate solution.Artificial Intelligence techniques are
values or ranges proposed by user which restrict
mathematical approaches which developed to search
the searching zone in the solution space.
for the most fitting solution according to certain
criteria within the available time and resources. The following introduce a brief description for the
Accordingly, the best found solution varies with the most famous (AI) techniques
available time and resources, the more searching time
and more powerful hard and software the wider 2.1 Expert System
solution space could be covered and hence, it is more
likely to find more accurate solution. It is one of the earliest (AI) techniques. It was
Since the 1980’s, many searching technique were developed in the 1980’s. it depends on storing the
developed under the umbrella of the AI, some human past experience of single expert or group of
techniques are mimicking natural developed algo- experts regarding a certain problem in some kind of
rithm such as neurons connections, natural selection decision tree. Problem inputs are logically processed
evolution, behavior of group of creatures such as bees, through that tree to determine the suitable solution.
ants, birds,…etc. On other hand some searching The system usually required high level of confidence
techniques don’t mimic any natural algorithms but in input data. The main component of the expert
they depend on mathematical, logical and statistical system is shown in Fig. 1.
approaches to find the best solution. After storing the expert(s) knowledge in the
Generally, all (AI) techniques required some pre- ‘‘Knowledge base’’ by knowledge engineer, the pro-
vious knowledge related to the problem and that is cess could be forward if the user asks for expert
why (AI) techniques may be called ‘‘Knowledge- advice, or backward if the user asks for explanation
Based-Techniques’’. This knowledge is usually a set about a dissention. In both cases ‘‘User Interface’’
of case studies or test results, which used to learn the collects data from the user and sends it to ‘‘Interface

123
Geotech Geol Eng

Expert System

Human Knowledg Knowledge Interface User


User
Expert Engineer Base Engine Interface

Fig. 1 Components of expert system

Engine’’ which applies all the required logical oper- layers called ‘‘Hidden Layers’’. The neurons of each
ations using the ‘‘Knowledge base’’ and feeds the user layer are connected to the neurons of the previous and
back with the answer through the ‘‘User Interface’’. the next layers by ‘‘Links’’, each link has a certain
Expert systems can give reason and proof for its strength called ‘‘weight’’. The data passes from the
decisions. input layer to the hidden layers to the output layer
through that links. Each neuron acts as processing
2.2 Fuzzy System element that sums the data multiplied by links weights
from the previous layer and applying a nonlinear
Unlike expert systems, fuzzy systems are not only function on the summation to produce the out data to
based on logical approach, but it is also used statistical the next layer. Values of links weights should be
approach and that is why it can deal with uncertain adapted using previous knowledge in a process called
data. The approach based on assuming that each ‘‘Back Propagation Training’’, in other words, the
variable has a probability distribution function called previous knowledge is stored in the system as link
‘‘Membership Function’’, accordingly, ‘‘Membership weights. Figure 3 shows schematic for the network.
Function’’ of the output will be produced by applying Many developments and enhancement were added to
Boolean logical operators on the ‘‘Membership Func- the original ANN technique to improve its efficiency
tion’’ of the inputs. Figure 2 shows the main compo- and accuracy; some of the developed ANN are listed
nents of the fuzzy system. The process stars with below:
‘‘Fuzzifying’’ the input by the ‘‘Fuzzifier’’ and sends it
• Back Propagation Neural Network (BPNN)
to ‘‘Interface Engine’’ which applies all the required
• Feed Forward Neural Network (FFNN)
logical operations using the ‘‘Rule base’’ and feeds the
• Redial Basis Function Neural Network (RBFNN)
user with the answer through the ‘‘Defuzzifying’’.
• Bayesian Regression Neural Network (BRNN)
• Generalized Regression Neural Network (GRNN)
2.3 Artificial Neural Networks (ANN)
• Differentiated Evolution Neural Network (DENN)
• Levenberg-Marquardt Neural Network
One of the most famous and successful (AI) tech-
(LMNN)
niques, it mimics the connections between brain cells
‘‘Neurons’’. Generally, the network consists of a Also, the weights matrix of ANN was optimized
number of neurons to import the inputs called ‘‘Input using many other (AI) techniques such as fuzzy logic,
Layer’’ and another number of neurons to export the genetic algorithm and particles swarm optimization as
outputs called ‘‘Output Layer’’ and in between that shown below:
two layers there may be number of neurons arranged in

Fuzzy System

Rule Base

Input Interface Defuzzifier Output


Fuzzifier
Engine

Fig. 2 Components of Fuzzy system

123
Geotech Geol Eng

Fig. 3 General schematic


for artificial neural network

OUTPUTS
INPUTS

Input Hidden Output


Layer Layer Layer

• Adaptive Neuro-Fuzzy Interface System (ANFIS) determined using the previous knowledge. Fitness
• Recurrent Fuzzy Neural Network (RFNN) function is often SSE. The next step is to keep the most
• Local Linear Neural Fuzzy (LLNF) fitting solutions and eliminate the others; the selected
• Cuckoo Optimization Algorithm–ANN (COA- solutions are called the ‘‘Survivors’’. Genetic opera-
ANN) tors such as crossover and mutation will be applied on
• Support Vector Quintile Regression (SVQR) the survivors to generate the population of the next
• Genetic algorithm–ANN (GA-ANN) generation and the cycle goes on until the accepted
accuracy achieved. In order to carry out that process,
solutions must be encoded in genetic form (as
2.4 Support Vector Machine (SVM)
Chromosome). The chromosome consists of number
of gens in series; each gene is a part of the solution.
This technique is classifier based on statistical con-
During the process of generating population, cross-
cept. The original technique was searching for the best
over operator is applied by swapping some parts of
linear boundaries between classes (which have the
two chromosomes called ‘‘Parents’’ which generates
widest margins).
two new chromosomes called ‘‘Children’’; while
Figure 4 illustrates the meaning of boundaries and
mutation is applied by randomly change some genes
margins in 2-dimensions space, Later, the original
on some chromosomes.
technique was enhanced to use higher orders of
Figure 5 explains the crossover and mutation
polynomial and even radial functions to address the
processes.
nonlinear boundaries. Recently, (SVM) were mixed
with (ANN) to produce (SVQR) as mentioned before.
2.6 Genetic Programming (GP)
2.5 Genetic Algorithm (GA)
(GP) is a special application of (GA) where the
solutions are mathematical formulas. In order to put a
It is a mathematical simulation for the natural
mathematical formula in genetic form (as Chromo-
selection evolution process. It stars by generating a
some), the original technique used binary tree as an
set of solutions randomly called ‘‘Population’’, and
intermediate step between mathematical form and
then the fitness of each solution in population will be
genetic form. Figure 6 describes how to put a

123
Geotech Geol Eng

Fig. 4 Support vector


machine (SVM) in
2-dimensions space

(a) Linear Boundary (b) Nonlinear Boundary

Fig. 5 Genetic algorithm


operators

Parents Children Original Mutant


(a) Crossover process (b) Muta on Process

Fig. 6 Presenting
mathematical formula in
tree and genetic form /
/
+

(X+Y) / log (Z) ≡ + Log ≡ Log


X
Y

X Y Z Z

(a) Mathema cal Form (b) Tree Form (c) Gene c Form

mathematical formula in genetic form. After generat- formula. Accordingly, traditional (GP) could be
ing and encoding the initial population of formulas, classified as multi-variable regression technique.
the traditional (GA) is used to generate the best fitting

123
Geotech Geol Eng

Many sub-techniques were developed under the • Grey Wolf Optimizer (GWO)
umbrella of (GP) such as • Social Spider Optimization (SSO)
• Artificial Fish Swarm Algorithm (AFSA)
• Linear Genetic Programming (LGP)
• Whale Optimization Algorithm (WOA)
• Cartesian Genetic Programming (CGP)
• Salp Swarm Algorithm (SSA)
• Gene Expression Programming (GEP)
• Butterfly Optimization Algorithm (BOA)
• Multi- Gene Expression Programming (MGEP)
• Crow Search Algorithm (CSA)
• Bat Algorithm (BA)
2.7 Evolutionary Polynomial Regression
All previous sub-techniques followed the general
algorithm of (PSO) technique, the differences between
(EPR) is a special case of (GP) where all generated
each other are the detailed procedures like local
mathematical formulas are forced to be polynomials
searching procedure, communication with swarm
and algorithm optimizes their exponents to generate
procedure, combining local and global direction
the best fitting polynomial. Although (EPR) puts
procedure, adopting searching speed procedure …etc.
restriction on the generated solution to be polynomi-
als, but it is still wildly preferred because of the
2.9 Other (AI) Techniques
mathematical advantages of the polynomials such as
continuity, ability to differentiate and integrate.
Besides the previous eight techniques, there are many
other optimization and searching techniques that may
2.8 Particles Swarm Optimization (PSO)
be considered as (AI) techniques such as:Besides the
previous eight techniques, there are many other
(PSO) is an optimization technique that mimics the
optimization and searching techniques that may be
searching behavior of group of creatures’ acts together
considered as (AI) techniques such as:
as one swarm. The general concept of this technique is
to divide the solution space into number of zones and • Information Systems and Artificial Intelligence
assign one individual creature for each zone. Each (ISAI)
individual creature will search in his own zone for the • Generic Interaction Matrix (GIM)
optimum solution according to the pre-defined criteria, • Knowledge-Based Clustered Partitioning (KCP)
besides that, each individual creature can (somehow) • Naive Bayes Classifier (NBC)
tell the others about solutions it found. So, during • Functional Networks (FN)
searching process, each individual creature will follow • Multivariate Adaptive Regression Splines
the resultant of two directions, the first toward the (MARS)
local optimum within its zone and the second toward • Group Method Of Data Handling (GMDH)
the global optimum from all the swarm. Cycle after • Knowledge Discovery in Databases (KDD)
cycle, all individual creatures will be conversion to the • Multivariate Regression Analysis (MVRA)
global optimum solution and the process stops. • Imperialism Competitive Algorithm (ICA)
Figure 7 illustrates the main concept of local and • Bayesian Artificial Intelligence Model Averaging
global directions. The main advantage in this tech- (BAIMA)
nique is that it prevents trapping in local minima.
(PSO) is a general technique includes many sub-
techniques each sub-technique mimics the searching
3 Overview of Geotechnical Engineering
behavior of certain kind of creatures such as:
• Ant Colony Optimization (ACO) Geotechnical engineering presents the intersection
• Artificial Bee Colony (ABC) between Civil Engineering and Earth Science. It
• Firefly Algorithm (FA) concerns in studying soil and rock proprieties, behav-
• Spider Monkey Optimization (SMO) ior and inter action with other materials such as water
• Grasshopper Optimization Algorithm (GOA) and structures. Besides that, it is also consigning in
• Cuckoo Search (CS) stability, stresses and deformations within soil and

123
Geotech Geol Eng

Searching Zone 1 Searching Zone 2


Best local
soluon

Global speed vector Best global


soluon

Fig. 7 Main concept of local and global speed vectors in (PSO) technique

rock mass under both static and dynamic loads. • Soil-Structure interaction
Foundation types, behavior and design may be also
considered part of geotechnical engineering. Geotech-
• Deep excavation and Shoring
nical topics may be arranged with respect to subject as
• Flexible foundations
follows:
• Tunnels, pipelines and underground structures
• Soil and Rock properties
• Soil and Rock dynamics

• Physical proprieties
• Dynamic properties and behavior
• Chemical proprieties
• Seismic wave propagation
• Mechanical proprieties
• Soil Liquefaction
• Soil and Rock Classification and Profiling • Seismic hazard
• Soil improvement
• Classification with respect to particle size,
minerals …etc.
• Compaction
• Site investigation
• Grouting
• Field tests interpretation
• Freezing
• Soil-water interface • Consolidation
• Mixing with additives (cement, lime…etc.)
• Permeability and seepage • Foundation behavior
• Contamination dissipation
• Erosion and scouring
• Shallow foundation
• Dewatering and ground water control
• Deep foundation
• Soil and Rock Behavior and modeling • Foundation on rock
• Soil and Rock stability
• Constitutive relations
• Failure criteria
• Slope stability and landslide
• Plasticity theories
• Dams and Embankment stability

123
Geotech Geol Eng

• Nailing and anchoring classified in both techniques, for example a research


• Retaining structures and Earth pressure used neuro-fuzzy technique will be classified under
both artificial neural networks and fuzzy system. Also,
some researchers used more than one technique, they
classified under all used techniques as well. The total
4 Methodology
number of times of using (AI) techniques are 783 time
regardless the subject as shown in Table 3.
This research depends on collecting all the available
The collected researches were classified by subject
previous publications on the web regarding the
into fourteen categories which are Soil Proprieties,
application of (AI) techniques in geotechnical engi-
Rock Proprieties, Soil Classification and Profiling,
neering. More than 800 researches were downloaded
Slope Stability, Soil Surface Compaction, Soil-Water
in the period from 1984 to May-2019. The surveying
interaction, Soil Behavior and Modeling, Shoring and
includes eight of the most famous publishing web sites
Retaining structures, Tunnels, Soil and Rock Dynam-
which are:
ics, Soil Liquefaction, Shallow Foundation, Deep
• ASCE www.asce.org Foundation, state of the art and review researches.
• Elsevier www.elsevier.com Some researches addressed more than one subject,
• Wiley www.wiley.com they classified under all addressed subjects. Some-
• NRC Canada www.nrcresearchpress.com times the research addressed a combined subject such
• Springer www.springer.com as ‘‘slope stability under earthquake loads’’, in this
• Taylor and Francis www. taylorandfrancis.com case it was classified under both subjects slope
• IEEE www.ieee.org stability an soil dynamics. The total number of times
• Google Scholar www. scholar.google.com of addressing geotechnical subject is 727 times
regardless the used technique as shown in Table 1.
After filtering the downloaded researches to elim-
The total number of collected pairs (subject-tech-
inate the duplications and the out of scope researches,
nique) is 916 pair regardless the number of researches
only 626 researches reminded. The next step was
as shown in Table 5.
recording those researches in database; each record
The total number of collected pairs (subject-tech-
contained the following fields:
nique) is 916 pair regardless the number of researches
• Research Authors as shown in Table 5.
• Publication year
• Research Title
• Journal, Volume, Issue / Conference, Date, Loca- 5 Application of (AI) Techniques in Geotechnical
tion / University for thesis Engineering
• Pages
• DOI:/ ISBN (if any) The results of the survey are summaries in the
• Publisher following Tables:
Tables 1, 2 summarized the number and reference
Two more fields were added after classifying the
of researches classified by Subject and publication
researches with respect to subject and (AI) techniques
year respectively. Figure 8 presents the contents of
• Technique Table 1 graphically. Tables 3, 4 summarized the
• Subject number and reference of researches classified by
(AI) Technique and publication year respectively.
Eight of the most used (AI) techniques were
Figure 9 presents the contents of Table 3 graphically.
included in this research, which are expert systems,
Tables 5, 6 summarized the number and reference of
fuzzy system, artificial neural networks, support
researches classified Subject and (AI) Technique
vector machine, genetic algorithm, genetic program-
respectively. Figure 10 presents the contents of
ming, evolutionary polynomial regression and parti-
Table 5 graphically. Table 7 summarized the number
cles swarm optimization besides other miscellaneous
of researches classified by Publisher and publication
techniques. Researches used Hybrid techniques were
year which graphically presented in Fig. 11.

123
Table 1 Number of researches classified by Subject and publication year
Year Subject Total No. of
addressed
Slope Deep Lique- Rock Soil Soil Shoring Tun- Shallow Soil and Soil class. Soil and Water-soil Others geotechnical
sta- foun- faction propri eties prop- com- and nels foun- rock and rock inter- subject
bility dation erties paction retain- dation dynamics profil- modeling action
Geotech Geol Eng

ing ing
walls

1984 1 1
1985 0
1986 1 1 2
1987 1 1 1 3
1988 0
1989 1 1 2
1990 1 1
1991 1 1 2
1992 1 1 1 1 1 5
1993 1 1 1 3
1994 0
1995 1 1 1 1 1 1 6
1996 1 1 1 3
1997 1 1 1 1 4
1998 1 1 2 1 5
1999 2 1 1 1 2 1 8
2000 1 1 1 2 1 2 1 1 10
2001 3 1 1 2 3 10
2002 1 2 1 2 1 2 1 1 1 12
2003 1 1 1 1 2 1 1 2 1 11
2004 1 1 1 3 3 2 1 2 2 5 21
2005 1 2 1 1 2 4 1 12
2006 2 1 3 1 2 1 2 12
2007 2 2 1 2 1 8
2008 6 4 1 3 12 3 2 2 9 1 3 46
2009 2 2 7 1 1 1 3 1 3 1 1 23
2010 4 3 3 1 7 1 1 3 2 3 2 30
2011 5 7 3 4 15 2 3 2 3 4 3 51

123
Table 1 continued
Year Subject Total No. of
addressed
Slope Deep Lique- Rock Soil Soil Shoring Tun- Shallow Soil and Soil class. Soil and Water-soil Others

123
geotechnical
sta- foun- faction propri eties prop- com- and nels foun- rock and rock inter- subject
bility dation erties paction retain- dation dynamics profil- modeling action
ing ing
walls

2012 2 4 3 8 7 2 4 1 4 7 2 2 46
2013 8 8 1 9 8 3 1 4 2 3 8 2 2 59
2014 13 10 5 9 17 1 2 4 2 2 3 8 5 1 82
2015 4 7 5 6 14 1 2 2 3 3 3 3 4 57
2016 8 5 1 11 11 2 5 3 2 1 2 1 4 56
2017 3 7 1 4 10 2 1 2 2 1 2 3 38
2018 6 10 0 10 18 3 4 4 1 5 5 1 6 73
2019 2 3 1 2 7 2 2 2 1 2 24
Total 75 80 39 75 152 18 23 28 39 24 44 65 23 42 727
Geotech Geol Eng
Table 2 Researches references classified by subject and publication year
Year Slope Deep Lique- Rock Soil Soil Shoring Tun- Shallow Soil Soil Soil Water-soil Others
sta- foun- faction propri- prop- com- and nel foun- and Class. and rock interaction
bility dation eties erties paction Retaining dation rock and modeling
walls dynam- profiling
Geotech Geol Eng

ics

1984 – – – – – – – – – – – – – 157
1985 – – – – – – – – – – – – – –
1986 – – – – 439 – – – – – 439 – – –
1987 509 273 – – – – – – – – – – – 542
1988 – – – – – – – – – – – – – –
1989 – – – – 275 – – – – – 307 – – –
1990 – – – – – 71 – – – – – – – –
1991 21 – – 124 – – – – – – – – – –
1992 137 – – – – – 556 – 495 440 – – – 440
1993 – 600 – – – – – – 498 – – – – 182
1994 – – – – – – – – – – – – – –
1995 – – 23 284 – – 33 – – – 500 104 11 –
1996 – – 101 – 497 – – – – – – 101 – –
1997 597 141 – 597 325 – – – – – – – – –
1998 582 326 – – – – – – – – 82, 156 287 – –
1999 31 – 145 – 102 – – – 558 – 595, 623 – – 35
2000 32 410 138 – 181, 411 – – 323 278, 339 32 – 170 – –
2001 – – 140, – – 265 – 420 – – – 265, 568 – 34, 245,
331, 381
452
2002 201 – 105, 361 146, 592 – 272 – 376, 382 – 451 263 – 592
195
2003 427 – 139 551 223 – – – 336, 379 80 622 106, 428 – 360
2004 537 43 52 7, 147, 366 147, 226, 279 52, 436 – 26 52, 375 – 7, 274 46, 52, 375, – –
540, 591
2005 332 103, 337 220 – – – – 300 196, 338 – 25, 267, – 327 –
288,
560
2006 – 378, 517 311 – 125, 197, 621 – 194 – – – 123, 450 374 72, 277 –
2007 – – 42, 107 – 561, 606 – – – 388 – 259, 414 – – 134
2008 143, 172, 30, 299, 343, 559 218, 219, 577 45, 142, 204, 260, 494, – 29, 30, 364 – – 80, 172 357, 502 204, 218, 474 329,
180, 207, 297, 43 511, 518, 562, 607, 219, 230, 380,
313 609 312, 343, 449
467, 468,
469

123
Table 2 continued
Year Slope Deep Lique- Rock Soil Soil Shoring Tun- Shallow Soil Soil Soil Water-soil Others
sta- foun- faction propri- prop- com- and nel foun- and Class. and rock interaction

123
bility dation eties erties paction Retaining dation rock and modeling
walls dynam- profiling
ics

2009 319, 567 377, 586 – 236, 295, 423, 461, 564, 14 122 – 309 63, 347, 445 3, 56, 602 610 383
574, 593 599
2010 169, 395, 453, 203, 373, 199, 280 44, 169, 214, 356, 407, 93 397 233, 2, 538 – 280, 431, 407, 421 – –
604 617 510, 516, 608 484, 446
547 283
2011 36, 148, 198, 15, 94, 193, 429, 36, 148, 344, 4, 48, 206, 276, 291, – 397, 386 – – 89, 98, 177, 520 64, 68, 94 179, 402, 91, 96,
237, 520 202, 271, 430, 563 292, 294, 433, 491, 346 432, 462 262
342, 514 519 508, 513, 515, 552
2012 569, 576 16, 269, 290, 90, 200, 215, 216, 418, 9, 10, 88, 340, 350, 418, – – 522, 359, 406, 335 473, 565, 24, 28, 205, 426, 624 65, 350
310 579 478, 499, 555 523 441, 611, 215, 248,
526, 565, 493 109 266, 526
596
2013 57, 213, 231, 78, 108, 128, 151 22, 55, 186, 55, 92, 208, 210, 217, 12, 210, 108 97, 548, 601 18, 234, – 150, 186, 389, 575 217,
444, 548, 238, 363, 351, 419, 306, 419, 475 475 351, 539 318, 372, 581
566, 605, 613 457, 527, 434, 481, 396, 419, 512,
548 554, 613 598 527, 616
2014 27, 40, 58, 77, 5, 20, 183, 317, 27, 117, 162, 1, 149, 158, 167, 191, 545 387, 612 155, 229, 405 113, 341 249, 261, 117, 144, 100, 118, 403
79, 435, 437, 264, 365, 442, 191, 221, 241, 247, 261, 387, 250, 385 368, 371, 185, 328,
486, 532, 368, 371, 454, 387, 412, 437, 465, 482, 535, 387, 384, 438, 365
585, 614, 384, 437, 455, 466, 482 543, 545, 557, 612 412 442, 573
615, 625 545 458
2015 87, 212, 415, 19, 189, 209, 6, 459, 75, 190, 464, 49, 60, 161, 190, 243, 59 485, 570 75, 370, 479, 126, 224, 282, 358, 424, – 301,
464 239, 270, 460, 504, 524, 258, 268, 281, 304, 358 524 176, 447 571 367,
456, 521 572, 529 316, 392, 504, 534, 501 394,
626 544 544
2016 39, 70, 130, 240, 322, 492 76, 85, 114, 67, 129, 160, 165, 293, 463, 528 – 53, 76, 85, 136, 401, 490 114 50, 507 17 84, 246,
211, 285, 369, 399, 355, 398, 303, 355, 398, 476, 289, 257 302,
530, 541, 589 531 400, 470, 503, 528 320, 541
476, 488, 321
489, 507
2017 112, 119, 132 66, 74, 171, 349 41, 115, 315, 37, 41, 235, 242, 298, 73, 472 222 168, 188, 225 – 588 – 404, 506 588,
225, 255, 324 315, 422, 588, 603, 496 603,
348, 404 619 550
2018 153, 296, 353, 81, 127, 163, – 95, 111, 121, 61, 95, 111, 135, 164, 8, 471, 131, 152, – 54, 86, 487 8, 175, 69, 81, 352, 192 47, 133,
408, 584, 587 178, 227, 163, 184, 173, 174, 184, 305, 549 154, 525 480, 483, 533, 333,
228, 252, 296, 483, 308, 314, 345, 352, 546 553 83 413,
256, 362, 505, 533, 393, 416, 417, 448, 448,
425 553 533 620
2019 232, 590 99, 251, 254 120 244, 354 51, 62, 116, 166, 354, – 187, 391 334, 13, 477 232 – – – 253,580
578, 594 390
Geotech Geol Eng
Geotech Geol Eng

90
80
70
60 TOTAL
Soil Prop.
50 Deep F.
40 Rock Prop.
30 Slope
Modeling
20 Profiling
10 Others
0 Liquef.
1984
1985

Shallow F.
1986
1987
1988
1989
1990
1991

Tunnel
1992
1993
1994
1995
1996

Dynamics
1997
1998
1999
2000
2001
2002

Water-Soil
2003
2004
2005
2006
2007

Shoring
2008
2009
2010
2011
2012
2013
Compacon

2014
Compacon Shoring Water-Soil Dynamics Tunnel

2015
2016
2017
2018
2019
Shallow F. Liquef. Others Profiling Modeling
Slope Rock Prop. Deep F. Soil Prop. TOTAL

Fig. 8 Number of researches classified by Subject and publication year

Regarding the addressed subjects, survey results are • Correlating thermal and electrical conductivity of
discussed as follows; soil with density and water content
This subject was addressed 152 times as per
5.1 Soil Proprieties
Table 1. Sometimes, more than one technique were
used, hence, the total number of (subject-technique)
Soil proprieties are usually determined from field or
pairs are 192 for all (AI) techniques, 103 of them using
lab tests, but some tests are difficult, slow, expansive
(ANN) as per Table 5. All research references related
and may be unavailable in many labs that is why many
to this subject are sorted by publication year in
researches tried to correlate the easy determined
Table 2.
properties (mainly physical properties) to difficult
determined ones (mainly mechanical properties). This
5.2 Rock Proprieties
subject includes this type of researches, for example:
• Correlating Relative density of sand with shear Similar to previous subject, this subject is concerned
strength parameters in researches that correlate rock proprieties with each
• Correlating consistency limits of clay with shear other. For example:
strength parameters
• Predicting shear and tensile rock strength from the
• Correlating consistency limits of clay with com-
compressive strength
pressibility index
• Predicting the elastic modulus of rock from its
• Correlating density and water content of clay with
density and compressive strength
Un-drained cohesion

123
Table 3 Number of researches classified by AI Technique and publication year
Year AI techniques Total No. of
using (AI)

123
Expert Fuzzy Neural Particles Support Genetic Genetic Evolutionary Others techniques
system system networks Swarm Vector Algorithm programming polynomial
optimization Machine regression

1984 1 1
1985 0
1986 1 1
1987 2 1 3
1988 0
1989 1 1 2
1990 1 1
1991 2 2
1992 3 1 4
1993 1 1 1 3
1994 0
1995 2 4 6
1996 2 2
1997 1 1 1 3
1998 2 3 5
1999 1 2 4 1 8
2000 3 2 6 11
2001 9 9
2002 2 8 1 11
2003 4 9 13
2004 4 10 1 1 1 17
2005 4 9 1 1 15
2006 1 1 10 1 1 14
2007 5 1 1 1 1 9
2008 1 3 31 1 3 2 2 1 44
2009 2 15 5 1 2 2 1 28
2010 1 4 20 1 2 1 1 1 31
2011 1 11 26 2 8 5 1 3 57
2012 6 25 2 6 3 4 1 5 52
2013 4 27 3 7 3 8 2 4 58
2014 1 8 33 5 6 6 10 3 5 77
2015 6 27 9 6 3 10 2 2 65
2016 2 4 26 9 6 3 9 1 6 66
Geotech Geol Eng
Geotech Geol Eng

Total No. of • Predicting thermal and electrical conductivity of

techniques
using (AI) rock from its density and RQD
This subject was addressed 75 times as per Table 1.

43
93
29
783
Sometimes, more than one technique were used,
hence, the total number of (subject-technique) pairs
Others

are 106 for all (AI) techniques except expert systems,


(PSO), (GA) and (EPR). 42 pairs of them were
4
5

39 conducted using (ANN) as per Table 5. All research


references related to this subject are sorted by
Evolutionary

publication year in Table 2.


polynomial
regression

14

5.3 Soil Classification and Profiling

This subject is concern in interpret the results of field


programming

test to identify the site stratification and classify the


Genetic

soil of each strata. Generally, the following field tests


are involved in this type of researches:
2
9
2
68

• Standard cone penetration test (SPT)


• Static cone penetration test (CPT)
Algorithm

• Dynamic cone penetration test (DCPT)


Genetic

• Dilatometer test (DLM)


6
8
2
39

• Potentiometer test
• Van shear test
• Geophysical test (Resistivity surveying, Seismic
Machine
Support
Vector

surveying, Ground radar)


59
2
8
1

This subject was addressed 44 times as per Table 1.


Sometimes, more than one technique were used,
hence, the total number of (subject-technique) pairs
optimization

are 51 for all (AI) techniques, 21 of them using (ANN)


Particles
Swarm

as per Table 5. All research references related to this


subject are sorted by publication year in Table 2.
19

66
3

6
networks

5.4 Slope Stability


Neural

20
35
14
380

The main aim of the researches in this subject is to find


the critical sliding surface (2D or 3D) and estimate the
system

safety factor of the slope considering the site profile,


Fuzzy

ground water condition, external loads and seismic


6
6
4
91
AI techniques

hazard. This subject includes researches for all types


slopes, as follows:
Table 3 continued

system
Expert

• Natural slopes and landslides


2

27

• Man-made slopes, Embankments, Dams


• Soil and Rock slopes
• Plain and Reinforced (Geo-grid, nailing,
Year

Total
2017
2018
2019

anchoring…etc.)

123
Table 4 Researches references classified by AI Technique and publication year
Year Expert Fuzzy system Artificial neural networks Particles Swarm Support Genetic Genetic Evolutionary Others
system optimization vector algorithm programming Polynomial

123
machine regression

1984 157 – – – – – – – –
1985 – – – – – – – – –
1986 – 439 – – – – – – –
1987 273, 542 509 – – – – – – –
1988 – – – – – – – – –
1989 307 275 – – – – – – –
1990 71 – – – – – – – –
1991 21, 124 – – – – – – – –
1992 440, 137 – – – – – – –
495,556
1993 182 498 600 – – – – – –
1994 – – – – – – – – –
1995 – 11, 500 23, 33, 104, 284 – – – – – –
1996 – – 101, 497 – – – – – –
1997 325 597 141 – – – – – –
1998 82, 156 – 287, 326, 582 – – – – – –
1999 31 558, 623 35, 102, 145, 595 – – 110 – – –
2000 32, 278, 410, 411 138, 170, 181, 323, 339, 410 – – – – – –
323
2001 – – 34, 140, 245, 265, 331, 381, 420, 452, 568 – – – – – –
2002 – 146, 361 105, 201, 263, 272, 376, 382, 451, 592 – – – 195 – –
2003 – 336, 360, 428, 106, 139, 59, 223, 336, 379, 427, 428, 551, – – – – – –
622
2004 – 7, 147, 274, 375 26, 43, 46, 226, 279, 366, 375, 537, 540, 591 – 436 – 52 – 366
2005 – 25, 288, 300, 103, 220, 300, 330, 332, 337, 338, 409, 560 – – 267 196 – –
327
2006 277 72 123, 125, 194, 197, 311, 374, 378, 450, 517, 621 – 123 – 125 – –
2007 – – 42, 259, 414, 561, 606 134 107 – 388 – 561
2008 30 299, 357, 364 29, 80, 142, 143, 172, 180, 204, 207,218, 219, 230, 260, 297 343, 443, 449, 494 29, 45 – 562
286, 299, 312, 313, 329, 343, 364, 380, 449, 467, 468, 559
469, 474, 502, 511, 518, 577, 607, 609
2009 – 309, 586 14, 63, 236, 295,309, 347, 377, 383,423, 445, 461, 567, 122, 295, 319, 593, 602 445 – 3, 236 3, 56 564
574, 599, 610
2010 421 214, 280, 431, 44, 93, 169, 199, 203, 214, 233, 356,373, 407, 446, 453, 397 510, 516 604 – 2 395
453 484, 510, 516, 538, 547, 608, 617, 283
Geotech Geol Eng
Table 4 continued
Year Expert Fuzzy system Artificial neural networks Particles Swarm Support Genetic Genetic Evolutionary Others
system optimization vector algorithm programming Polynomial
machine regression

2011 552 36, 96, 148, 177, 4, 15, 48, 68, 89, 96, 98, 148, 198, 202, 206, 262, 271, 237, 386 276, 291, – 64, 91, 94, 271, 508 193, 344,
Geotech Geol Eng

179, 237, 402, 276, 291, 292, 342, 344, 346, 429, 430, 433, 513, 514, 292, 294, 519 563
432, 462, 491, 515, 520 429, 430,
618 513, 515
2012 – 9, 65, 340, 478, 9, 10, 28, 65, 88, 200, 215, 216, 266, 335, 359, 406, 418, 205, 248 16, 215, 216, 310, 523, 90, 269, 493, 24 216, 290,
579, 611 426, 473, 478, 493, 499, 522, 555, 569, 576, 579, 624, 335, 441, 526 526 350,
109 493 565,
596
2013 – 18, 150, 231, 12, 18, 22, 97, 108, 128, 208, 210, 217, 234, 238, 351, 213, 318, 605 12, 151, 351, 306, 581, 55, 78, 92, 186, 57, 372 444, 548,
616 372, 389, 396, 434, 457, 475, 512, 527, 536, 539, 554, 419, 481, 605 234, 363, 372, 605,
566, 575, 581, 598 554, 601 548 613
2014 403 118, 155, 250, 27, 38, 79, 117, 118, 155, 158, 162, 185, 191, 221, 241, 77, 149, 191, 438, 486 20, 247, 442, 1, 40, 144, 58, 100, 167, 5, 229, 249 113, 118,
317, 328, 387, 261, 264, 317, 341, 365, 368, 371, 384, 405, 412, 435, 545, 614, 183, 221, 221, 229, 264, 437,
532, 585 465, 466, 482, 535, 543, 545, 557, 573, 614, 615 625 385 454, 455,458, 545,
614 612
2015 – 161, 190, 268, 6, 19, 49, 60, 126, 161, 189, 190, 209,224, 239, 243, 19, 87, 190, 212, 282, 301, 59, 60, 212, 75, 190, 570 176, 209, 270, 370, 394 529, 572
415, 534, 626 258, 281, 282, 316, 370, 392, 424, 464, 479, 485, 521, 304, 358, 544 301, 501, 367, 370, 447,
524, 534, 571, 626 571 456, 459, 460,
504
2016 160, 355 285, 321, 398, 17, 39, 50, 84, 114, 129, 130, 160, 211, 240, 257, 53, 130, 136, 211, 246, 257, 67, 302, 303, 70, 76, 302 85, 165, 369, 369 302, 399,
476 285,289, 293, 302, 303, 322, 369, 400, 401, 463, 470, 302, 488, 589 320, 476, 463, 488, 489, 503,
476, 507, 541, 583 589 490, 492, 530 528,
530,
531
2017 – 115, 188, 235, 37, 41, 66, 73, 112, 168, 188, 225, 235, 242, 255, 298, 132, 222, 550 74, 255 73, 132, 255, 349 – 119, 171,
242, 255, 315 315, 348, 422, 472, 496, 506, 588, 603 225, 404, 324,
550, 588 619
2018 153, 553 47, 133, 135, 8, 54, 61, 95, 111, 131, 133, 135, 152, 153, 154, 174, 47, 83, 86, 95, 121, 133, 135, 111, 152, 95, 133, 127, 133, 163, 69 81, 121,
192, 352, 413 175, 192, 227, 228, 252, 256, 296, 308, 314, 345, 352, 153, 173, 174, 184, 192, 178, 413, 314, 345, 164, 362, 393, 152,
362, 393, 413, 416, 417, 448, 480, 533, 546, 549, 553, 305, 333, 352, 353, 408, 417, 425, 480, 483, 413, 471, 487 584,
620 505, 525 533, 553 505, 525 587
2019 – 13, 244, 354, 62, 99, 187, 232, 244, 251, 253, 334, 354, 390, 391, 580, 116, 254, 334, 390, 391, 578 578 244, 254 51, 166 – –
477 590, 594

123
Geotech Geol Eng

100
90
80
70
60
50
40
30
20 TOTAL
ANN
10
Fuzzy
0
GP
1984
1985
1986
1987

PSO
1988
1989
1990
1991
1992

SVM
1993
1994
1995
1996
1997

Others
1998
1999
2000
2001
2002
2003

GA
2004
2005
2006
2007
2008 Expert
2009
2010
2011
2012
2013
EPR

2014
2015
2016
2017
2018
2019
EPR Expert GA Others SVM
PSO GP Fuzzy ANN TOTAL

Fig. 9 Number of researches classified by AI Technique and publication year

This subject was addressed 75 times as per Table 1. related to this subject are sorted by publication year in
Sometimes, more than one technique were used, Table 2.
hence, the total number of (subject-technique) pairs
are 92 for all (AI) techniques, 35 of them using (ANN) 5.6 Soil-Water Interaction
as per Table 5. All research references related to this
subject are sorted by publication year in Table 2. This subject is concerned in correlating the hydraulic
proprieties of soil with other properties and predicts
5.5 Soil Surface Compaction the effect of surface and ground water on soil.
Generally, this subject includes topics such as:
Many researchers were carried out regarding this topic
• Predicting soil permeability based on grain size
because it’s the cheapest and most used soil improve-
analysis
ment technique. The collected researches covered the
• Predicting soil contamination using seepage char-
compaction process starting from predicting the
acteristics and soil type
compaction curve (maximum dry density and opti-
• Estimating soil erosion and scouring depth
mum water content) using grain size analysis results,
selecting the suitable equipment based on type of soil This subject was addressed 23 times as per Table 1.
and lift thickness, suggesting compaction plan for Sometimes, more than one technique were used,
certain soil type and compacting tool and finally, hence, the total number of (subject-technique) pairs
Correlating the compaction results (dry density) with are 27 for all (AI) techniques except (SVM) and
other proprieties such as electric resistivity. (EPR). 12 pairs of them were conducted using (ANN)
This subject was addressed 18 times as per Table 1. as per Table 5. All research references related to this
Sometimes, more than one technique were used, subject are sorted by publication year in Table 2.
hence, the total number of (subject-technique) pairs
are 23 for all (AI) techniques except expert systems,
(PSO) and (EPR). 12 pairs of them were conducted
using (ANN) as per Table 5. All research references

123
Geotech Geol Eng

Total no. of
5.7 Soil Behavior and Modeling

technique)
(subject-

pairs
Soil is behavior under loads is a very complicated

109
433

916
32

75
72
49
80
14
52
issue, it is highly nonlinear behavior and depends on
many parameters such as soil type, grain size distri-
Others

bution, relative density, water content, consistency


25

61
5
6

9
3
6
4
1
2
index, stress path,…etc. Most researches regarding
Interaction
Water-soil

this topic concentrated on predicting the results of


loading tests and estimating the soil deformation is
10
12

27
1

1
1

1
some case studies for example:
modeling
Soil and

• Predicting tri-axial test results


• Developing constitutive relations to be used in
rock

42

77
1
5

8
6
2
7
5
1
FEM software
profiling

• Predicting settlement of multi-layer soil profile


class.

• Estimating settlement-time curve


Soil

and

2
3
4
1
1
1
14
21

51

This subject was addressed 65 times as per Table 1.


dynamics
and rock

Sometimes, more than one technique were used,


Soil

hence, the total number of (subject-technique) pairs


2
1

1
17

27

are 77 for all (AI) techniques, 42 of them using (ANN)


foundation

as per Table 5. All research references related to this


Shallow

subject are sorted by publication year in Table 2.


2
8

3
3
2
8
3
1
22

52

5.8 Shoring and Retaining Structures


Tunnel

19

34
1
5

4
2
3

The scope of this topic may looks the same as the


previous one since soil-structure interaction problems
retaining
Shoring

usually use constitutive relations in FEM models, but


walls
and

2
3

6
1
2
1

2
12

29

this topic is concerned in the researches that predict


Table 5 Number of researches classified by Subject and AI Technique

the behavior of deep excavation shoring and retaining


Compaction

structures without using FEM as the following


examples:
Soil

4
1
3

2
12

23

• Predicting the deformations besides braced deep


Properties

excavation
• Optimizing the design of retaining structures
Soil

1
22

17
18

12

11
103

196

• Estimating the stability of retaining structures


• Optimizing Number and location of back ties
propri-
Rock

eties

(ground anchors)
3

9
9
16
42

10

10
106

• Selecting the optimum shoring technique


Lique-

tion
fac-

This subject was addressed 23 times as per Table 1.


3

1
21

11

43

Sometimes, more than one technique were used,


dation
foun-
Deep

hence, the total number of (subject-technique) pairs


2
4

2
9
5

2
9
50

15

98

are 29 for all (AI) techniques except (EPR). 17 pairs of


them were conducted using (ANN) as per Table 5. All
stabil-
Slope

research references related to this subject are sorted by


ity

4
6
4
1
12
35
16

10
92

publication year in Table 2.


EXPERT

OTHER
TOTAL
FUZZY
ANN

SVM

EPR
PSO

GA
GP

123
Table 6 Researches references classified by Subject and AI Technique
Slope Deep Lique- Rock Soil Soil Shoring Tunnel Shallow Soil and Soil Soil Water-soil Others
stability foun- faction propri- prop- com- and foun- rock class. and rock interaction

123
dation eties erties paction retaining dation dynamics and Modeling
walls profiling

EXPERT 21, 31, 32, 30, 273 – 124, 355, 553 160, 325, 355, 71 30, 556 323 278, 495 32, 440 82, 156, 421 277 157, 182,
153 552 307, 403,
553 440,
542
FUZZY 36, 137, 255, 299, 410, 317, 7, 36,115, 9, 135, 146, – 364, 387, 155, 13, 188, 18 7, 25, 47, 150, 352, 375, 11, 72, 118, 47, 65,
148,231, 586 579, 147, 148, 147, 161, 618 250, 309, 177, 428, 616 179, 192, 96, 133,
237, 285, 626 190, 244, 190, 214, 300, 336, 274, 327, 328, 360,413
415, 453, 280, 315, 235, 242, 321, 375, 280, 402, 432,
509, 532, 354, 361, 268, 275, 387 477, 288, 462
585, 597 387, 398, 315, 340, 498, 558 357,
476, 478, 352, 354, 431,
597 387, 398, 439,
411, 439, 500,
476, 491, 611,
534 622,
623
GA 40, 70, 110, 183, 225, 254, – 75, 76, 95, 1, 95, 190, 73 525, 570 75, 76, 225, 480 – 267, 385, 144, 526 404 133, 302,
132, 604, 310, 404 190, 221, 306, 314, 523 483, 449,
605 244, 483, 345, 494, 588 550,
505, 526 588 581,
588
GP 58, 530, 78, 94, 127, 52, 90, 55, 85, 163, 45, 51, 55, 92, 52, 463, 29 – 52, 85, 176, 234, 447 3, 52, 64, 94, 100 91, 133,
548, 614 163, 209, 195, 186, 221, 125, 164, 471 196, 487, 490 186, 372, 367,
255, 264, 349, 488, 489, 165, 166, 229, 526 413
269, 270, 454, 504, 526 167, 236, 370,
271, 362, 455, 393, 504 388,
363, 369, 458, 493, 548
456, 548 459,
460,
492,
519
EPR 57 5, 369 – – 508 – – – 2, 229, – 249 3, 24, 56, 69, – 394
370 372
Geotech Geol Eng
Table 6 continued
Slope Deep Lique- Rock Soil Soil Shoring Tunnel Shallow Soil and Soil Soil Water-soil Others
stability foun- faction propri- prop- com- and foun- rock class. and rock interaction
dation eties erties paction retaining dation dynamics and Modeling
walls profiling
Geotech Geol Eng

ANN 27, 39, 79, 15, 19, 43, 66, 6, 23, 22, 27, 41, 95, 4, 9, 10, 37, 8, 12, 29, 33, 26, 97, 54, 188, 18, 63, 80, 8, 109, 28, 46, 50, 68, 17, 118, 34, 35,
112, 130, 99, 103, 42, 111, 114, 38, 41, 44, 14, 108, 155, 225, 89, 98, 114, 101, 104, 185, 192, 65, 84,
143, 148, 108, 128, 101, 117, 148, 48, 49, 60, 73, 131, 168, 257, 126, 159, 123, 106, 117, 365, 389, 96, 133,
153, 169, 141, 189, 105, 162, 190, 61, 62, 88, 93, 152, 233, 309, 172, 232, 175, 170, 204, 426, 474, 217,
172, 180, 202, 203, 138, 191, 215, 95, 102, 210, 154, 283, 336, 234, 335, 224, 215, 218, 506, 575, 245,
198, 201, 209, 225, 139, 216, 218, 111, 125, 265, 187, 289, 338, 341, 346, 259, 219, 230, 610, 624 253,
207, 211, 227, 228, 140, 219, 221, 129, 135, 463, 194, 300, 339, 347, 401, 261, 263, 265, 262,
232, 285, 238, 239, 145, 244, 284, 142, 158, 472, 272, 323, 359, 539, 599 282, 266, 287, 302,
296, 313, 240, 251, 199, 296, 315, 160, 161, 475, 364, 334, 370, 414, 312, 343, 329,
332, 427, 252, 255, 200, 344, 351, 162, 169, 545, 391, 351, 375, 445, 352, 368, 380,
435, 453, 256, 264, 220, 354, 366, 174, 181, 549 485 390, 376, 446, 371, 372, 381,
464, 520, 271, 299, 311, 400, 412, 190, 191, 396, 379, 450, 374, 375, 383,
537, 541, 322, 326, 317, 418, 434, 197, 204, 412, 382, 451, 384, 407, 413,
566, 567, 337, 342, 331, 464, 466, 206, 208, 420, 405, 473, 424, 428, 448,
569, 576, 343, 348, 429, 470, 476, 210, 214, 484, 406, 502, 467, 468, 449,
582, 590, 362, 365, 430, 478, 482, 217, 223, 496, 479, 520, 469, 507, 541,
614, 615 368, 369, 452, 499, 507, 226, 235, 522, 480, 553, 512, 527, 580,
371, 373, 510, 524, 533, 236, 241, 598 493, 560, 533, 540, 581,
377, 378, 547, 551, 553, 242, 243, 524, 588, 568, 571, 588,
384, 410, 579, 554, 577 258, 260, 538, 546 595 573, 591 592,
457, 514, 626 261, 276, 603,
517, 521, 279, 281, 620
527, 545, 291, 292,
600, 617 293, 295,
298, 303,
308, 314,
315, 316,
345, 352,
354, 356,
392, 393,
407, 416,
417, 418,
422, 423,
433, 448,
461, 465,
475, 476,
482, 497,
511, 513,
515, 516,
518, 533,
534, 535,
543, 545,
555, 557,
561, 574,
583, 588,
592, 594,

123
Table 6 continued
Slope Deep Lique- Rock Soil Soil Shoring Tunnel Shallow Soil and Soil Soil Water-soil Others
stability foun- faction propri- prop- com- and foun- rock class. and rock interaction

123
dation eties erties paction retaining dation dynamics and Modeling
walls profiling

603, 606,
607, 608,
609, 621
PSO 77, 87, 130, 19, 254 – 95, 121, 184, 95, 116, 135, – 122, 222, 53, 334, 86, 136, – 47, 282 83, 205, 248, 192 47, 133,
132, 153, 190, 191, 149, 173, 386, 358, 257 318, 352, 134,
211, 212, 488, 505 174, 184, 391, 390 358, 438, 246,
213, 237, 190, 191, 397, 602 301,
297, 319, 295, 297, 525 302,
353, 408, 304, 305, 333,
486, 589, 352, 544, 544,
605 578, 593 550
SVM 212, 589, 16, 20, 74, 107, 111, 215, 216, 60, 67, 111, 12, 59, 152 320, 441, 493, 335, 501, 123, 445, 215, 343, 419, – 301, 302,
614, 625 178, 255, 151, 351, 419, 247, 276, 436, 351, 601 553 442, 533, 413
343, 425, 429, 476, 481, 291, 292, 545 571
443, 545 430, 533, 553, 294, 303,
442, 554 417, 419,
510, 476, 513,
559 515, 516,
533, 545,
578
OTHER 119, 395, 81, 171, 193, 572 121, 216, 324, 350, 437, 503, 528, 545 152, 612 – 548 113 565 81 118 302, 350
437, 444, 290, 399, 344, 366, 528, 545,
530, 548, 437, 531, 529, 563, 561, 562,
584, 587, 545, 548 565, 596, 563, 564,
605, 613 613 612, 619
Geotech Geol Eng
Geotech Geol Eng

Fig. 10 Number of
researches classified by
Subject and AI Technique

120

100

80

60
ANN
40 FUZZY
20 GP
0 PSO
SVM
OTHER
GA

EXPERT

EPR

5.9 Tunnels correlating their values with other soil and rock
properties is the goal of this subject. Many collected
Although tunnels and underground structures are pure researches regarding this subject such as:
soil-structure interaction problems, but this subject is
• Predicting shear wave velocity in soil
concerned in applying (AI) techniques not FEM,
• Predicting elastic modulus and damping ratio of
accordingly, the included topics under this subject
soil
could be as follows:
• Estimating the effect of dynamic loads on slopes
• Predicting ground settlement due to tunneling and dams stability
• Selecting optimum tunneling technique based on • Estimating Analyzing and simulating ground
soil profile and tunnel depth motion due to blast loads
• Estimating the stresses and deformations of
This subject was addressed 24 times as per Table 1.
lining
Sometimes, more than one technique were used,
This subject was addressed 28 times as per Table 1. hence, the total number of (subject-technique) pairs
Sometimes, more than one technique were used, are 27 for all (AI) techniques except (PSO), (GA) and
hence, the total number of (subject-technique) pairs (EPR). 17 pairs of them were conducted using (ANN)
are 34 for all (AI) techniques except (GP) and (EPR). as per Table 5. All research references related to this
19 pairs of them were conducted using (ANN) as per subject are sorted by publication year in Table 2.
Table 5. All research references related to this subject
are sorted by publication year in Table 2. 5.11 Soil Liquefaction

5.10 Soil and Rock Dynamics The scope of this subject is related to the previous one
since liquefaction is usually occurs due to dynamic
Mechanical wave velocity, Dynamic shear strength, loads, but this subject is concerned in predicting the
Dynamic elastic and rigidity modulus are the most probability of liquefaction based on field tests and
important dynamic proprieties of soil and rock, physical and mechanical soil proprieties such as:

123
Table 7 Number of researches classified by Publisher and publication year
Year Publisher Total No. of researches

123
ASCE Elsevier Wiley NRC Canada Springer Taylor and Francis IEEE Others

1984 1 1
1985 0
1986 1 1
1987 1 2 3
1988 0
1989 1 1 2
1990 1 1
1991 2 2
1992 1 3 4
1993 1 1 1 3
1994 0
1995 2 1 1 2 6
1996 2 2
1997 1 1 1 3
1998 1 1 1 1 1 5
1999 1 2 1 1 3 8
2000 4 1 2 1 1 9
2001 2 7 9
2002 5 1 1 4 11
2003 2 1 2 1 5 11
2004 1 4 1 2 1 6 15
2005 3 4 2 1 1 1 2 14
2006 5 4 3 12
2007 1 2 1 4 8
2008 6 4 2 2 2 1 1 21 39
2009 2 3 1 3 1 2 11 23
2010 6 2 1 3 3 12 27
2011 3 10 1 1 7 2 21 45
2012 3 13 2 1 4 1 2 15 41
2013 4 15 1 0 8 3 16 47
2014 11 12 10 7 24 64
Geotech Geol Eng
Geotech Geol Eng

Total No. of researches • Predicting soil liquefaction using field tests (CPT,
SPT)
• Predicting soil liquefaction using relative density,
grain size distribution
• Predicting soil liquefaction using shear wave
velocity in soil

626
50
48
31
59
22 This subject was addressed 39 times as per Table 1.
Sometimes, more than one technique were used,
hence, the total number of (subject-technique) pairs
Others

are 43 for all (AI) techniques except (PSO), (GA) and


236
24
12
11
17
6

(EPR). 21 pairs of them were conducted using (ANN)


as per Table 5. All research references related to this
subject are sorted by publication year in Table 2.
IEEE

11
1
1
1

5.12 Shallow Foundation

This subject is concerning in estimating the capacity


Taylor and Francis

and predicting the settlement and optimizing the


design of shallow foundations using (AI) techniques.
Foundation types included in this subject are Isolated,
combined, strip and raft foundation. Some examples
22

for the related researches are listed below:


2
1
3
2

• Estimating the ultimate bearing capacity for shal-


low foundation
Springer

• Predating the settlement below shallow foundation


117
14
11
10
24
13

on multilayer soil profile


• Minimizing the cost of constructing shallow
foundation
NRC Canada

This subject was addressed 39 times as per Table 1.


Sometimes, more than one technique were used,
hence, the total number of (subject-technique) pairs
28
1

are 52 for all (AI) techniques. 22 pairs of them were


conducted using (ANN) as per Table 5. All research
references related to this subject are sorted by
Wiley

publication year in Table 2.


15
2

1
1

5.13 Deep Foundation


Elsevier

Similar to the previous subject, this one is concerning


114
17

in estimating the capacity and predicting the settle-


6

5
8

ment and optimizing the design of deep foundations


Publisher

using (AI) techniques. Foundation types included in


ASCE
Table 7 continued

this subject are pile, pier and caisson foundation. Some


83

examples of the related researches are listed below:


3
5
2
5
1

• Estimating the ultimate bearing and friction capac-


ities for deep foundation
Year

Total
2015
2016
2017
2018
2019

123
Geotech Geol Eng

70
60
50
Publisher
40
Others
30
Springer
20
Elsevier
10
0 ASCE
1984
1985
1986
1987

NRC Canada
1988
1989
1990
1991
1992
1993
1994
1995

Taylor &…
1996
1997
1998
1999
2000
2001
2002
2003

Wiley
2004
2005
2006
2007
2008
2009
2010
2011
IEEE

2012
2013
IEEE Wiley Taylor & Francis

2014
2015
2016
2017
2018
NRC Canada ASCE Elsevier

2019
Springer Others Publisher

Fig. 11 Number of researches classified by Publisher and publication year

• Predating the vertical and horizontal deformations • A Review: Evolutionary Computations (GA and
of deep foundation PSO) in Geotechnical Engineering
• Predicting the behavior of group of piles • Machine learning algorithms for applications in
• Optimizing the design of deep foundation geotechnical engineering
• Application of Optimization and other Evolution-
This subject was addressed 80 times as per Table 1.
ary Techniques in Geotechnical Engineering
Sometimes, more than one technique were used,
• Genetic Programming for Modeling of Geotech-
hence, the total number of (subject-technique) pairs
nical Engineering Systems
are 98 for all (AI) techniques. 50 pairs of them were
conducted using (ANN) as per Table 5. All research This subject was addressed 42 times as per Table 1.
references related to this subject are sorted by Sometimes, more than one technique were used,
publication year in Table 2. hence, the total number of (subject-technique) pairs
are 61 for all (AI) techniques. 25 pairs of them were
5.14 Other Subjects conducted using (ANN) as per Table 5. All research
references related to this subject are sorted by
This subject contains all collected state of the art and publication year in Table 2.
review researches regarding application of (AI) tech-
niques in geotechnical engineering. Each research
summarizes the geotechnical application for one or
more of the (AI) techniques up to its publication date
such as:
• The application of artificial neural network in
geotechnical engineering

123
Geotech Geol Eng

6 Implementation of (AI) Techniques the installation process is controlled by (AI)


system.
6.1 Current Implementations • Interpreting the geo-physical tests measurements
• Enhancing the accuracy of the finite element
For geotechnical engineering, the most famous real- software by using (AI) based constitutive relations.
world implementation is the ‘‘intelligent compaction
system’’. It is a modern soil compacting system
consists of traditional compactor equipped with sen-
7 Conclusions
sors to measure the compaction efficiency and a GPS
antenna to determine the compactor location. An (AI)
The results of this research could be summarized in the
algorithm is used to automatically adapt lift thickness
following points:
and compactions process.
• During the last 35 years, the rate of using of (AI)
6.2 Future Implementations and Challenges techniques in geotechnical engineering increased
from one research to about 100 researches per year
Many results of applying (AI) techniques in geotech- in almost exponential rate as shown in Fig. 12
nical engineering are not implemented in real-world • The survey results shows two drops in using (AI)
for the following reasons: techniques in geotechnical field in the years 2007
and 2017 followed by two jumps in 2008 and 2018,
• The used data set is limited and hence, the results
this may be due to delay in publishing.
are only valid (or accurate) for certain cases (or in a
• No. of applied (AI) techniques increased from one
narrow range of parameters)
in 1984 to eight in 2009 in almost linear rate. Also,
• Leak of confidence in the used data set.
No. of research points increased almost linearly
• The output format of the used (AI) technique is
from 1984 to 2000 where all research points
difficult for implementations such as the weights
addressed
matrix of ANN.
• (ANN) and its enhancements presents about 48%
• The (AI) techniques results (closed form equation,
of the total used (AI) techniques in the geotechni-
weights matrix or other format) have no scientific
cal field, the share of Fuzzy systems, (GP), (PSO)
background or physical meaning accordingly, it is
and (SVM) techniques is about (8-12%) each and
difficult to grantee or predict their validity for any
the rest is shared by other techniques as shown in
considered case.
Fig. 13.
However, the previous points could be overcome by • Soil and Rock properties presented together about
extensive studies of many researchers using a wide 30% of the total addressed subjects while slope
range of parameters values to gain confidence in used stability, deep foundations and and modeling came
data and ensure the results validity. On other hand, in next with share of about 10% each the rest 40%
identifying suitable inputs or features verses multi- was shared by other subjects as shown in Fig. 14.
objective feature selection and choosing the suit- • ASCE, Elsevier and Springer together presents
able (AI) technique for the considered problem 50% of the downloaded researches, while the share
fascists the results implementations in the real-word of Google scholar alone is 38% and other web sites
applications (Table 8). shared the rest 12% as shown in Fig. 15.
Some of the expected future implementations of • Empty cells in Table 5 indicate the missing
(AI) techniques in geotechnical engineering are: (subject-technique) pairs which may be filled in
future studies.
• Intelligent tunneling machines, where tunneling
• The output format of some (AI) techniques is
process is automatically adapted by (AI) system
difficult for implementation and it may need some
using the measurements of monitoring sensors.
modifications and simplifications by professional
• Intelligent hammering machines, where the capac-
engineers to be implement in real-world
ity of the driven pile is automatically evaluated and
applications.

123
Geotech Geol Eng

Table 8 Researches ID and research reference


ID References ID References ID References ID References

1 Besalatpour et al. (2014) 41 Asadi (2017) 81 Jebur et al. (2018) 121 Hussain et al. (2018)
2 Javadi et al. (2010) 42 Hanna et al. (2007) 82 Al-Rawas et al. (1998) 122 Ahmadi-Nedushan and Varaee
(2009)
3 Javadi and Rezania (2009) 43 Hanna et al. (2004) 83 Rezaeeian et al. (2018) 123 Bhattacharya and Solomatine
(2006)
4 Abdollahzadeh et al. (2011) 44 Shalmani et al. (2010) 84 Alavi et al. (2016) 124 Denby and Kizil (1991)
5 Ahangar-Asra et al. (2014) 45 Baykasog et al. (2008) 85 Alavi et al. (2017) 125 Narendra et al. (2006)
6 Ardakani and Kohestani 46 Basma and Nabil (2004) 86 Gandomi and Ali (2018) 126 Bafghi and Entezari (2015)
(2015)
7 Aydin (2004) 47 Bilski (2018) 87 Gandomi et al. (2015) 127 Tarawneh (2018)
8 Salahudeen et al. (2018) 48 Asadi et al. (2011) 88 Alavi and Amir (2012a) 128 Tarawneh (2013)
9 Besalatpour et al. (2012a) 49 Kordnaeij et al. (2015) 89 Alavi and Amir 2011a 129 Tarawneh (2016)
10 Besalatpour et al. (2012b) 50 Ghodrati and Ata (2016) 90 Alavi and Amir (2012b) 130 Gordan et al. (2016)
11 Birdossy et al. (1995) 51 Elbosraty et al. (2019) 91 Alavi and Amir (2011b) 131 Gordan et al. (2018)
12 Gomes et al. (2013) 52 Ebid (2004) 92 Alavi et al. (2013) 132 Jellali and Wissem (2017)
13 Gupta et al. (2019) 53 Marwan et al. (2016) 93 Alavi et al. (2010) 133 Bharanidhar (2018)
14 Alavi et al. (2009) 54 Khudier (2018) 94 Alavi et al. (2011) 134 Bharanidhar and Premalatha
(2007)
15 Ismail and Jeng (2011) 55 Ozbeka et al. (2013) 95 Mahdiyar et al. (2018) 135 Pham et al. (2018)
16 Zhao et al. (2012) 56 Javadi et al. (2009) 96 Adoko and Wu (2011) 136 Ukritchon and Suraparb (2016)
17 Mishra et al. (2016) 57 Javadi et al. (2013) 97 Adoko et al. (2013) 137 Juang et al. (1992)
18 Verma and Singh (2013) 58 Garg et al. (2014a) 98 Alimoradi et al. (2011) 138 Juang et al. (2000)
19 Kordnaeij et al. (2015) 59 Sabat (2015a) 99 Shatnawi et al. (2019) 139 Juang et al. (2003)
20 Kordjazi et al.( 2014) 60 Sabat (2015b) 100 Garg et al. (2014b) 140 Juang et al. (2001)
21 Wislocki and Bentley (1991) 61 Al-Rashid et al. (2018) 101 Goh (1996) 141 Teh et al. (1997)
22 Sayadi et al. (2013) 62 Dehghanbanadaki et al. (2019) 102 Goh (1999a) 142 Kayadelen (2008)
23 Goh (1995) 63 Cabalar and Abdulkadir (2009) 103 Goh et al. (2005) 143 Melchiorre et al. (2008)
24 Javadi et al. (2012) 64 Cabalar and Abdulkadir (2011) 104 Gohl (1995) 144 Pereira et al. (2014)
25 Goktepe et al. (2005) 65 Cabalar et al. (2012) 105 Goh (2002) 145 Juang et al. (1999)
26 Benardos and Kaliampakos 66 Ghorbani and Mostafa (2017) 106 Goh and Fred (2003) 146 Gokceoglu (2002)
(2004)
27 Li et al. (2014a) 67 Heidaripanah et al. (2016) 107 Goh and Goh (2007) 147 Gokceoglu and Kivanc (2004)
28 Choobbasti et al. (2012) 68 Mollahasani et al. (2011) 108 Goh and Chai (2013) 148 Chen Changfu (Chen et al. 2011)
29 Mens et al. (2008) 69 Nassr et al. (2018) 109 Ribeiro et al. (2012) 149 Zhu et al. (2014)
30 Koelewijn and André (2008) 70 Kashani et al. (2016) 110 Goh (1999b) 150 Chen and Jiasheng (2013)
31 Al-Homoud and Al-Masri 71 Touran (1990) 111 Negara et al. (2018) 151 Lee and Shuh-Gi (2013)
(1999)
32 Al-Homoud and Tahtamoni 72 Uyumaz et al. (2006) 112 Chakraborty and Diganta 152 Qi and Xiaolin (2018)
(2000) (2017)
33 Goh et al. (1995) 73 Ardakani and Afshin (2017) 113 Alimoradi and James (2014) 153 Qi et al. (2018)
34 Goh (2001) 74 Ardakani and Vahid (2017) 114 Patel and Snehamoy (2016) 154 Yoo et al. (2018)
35 Sub-committee A2K053 75 Salimi et al. (2015) 115 Mahmoud and Ahmed 155 Bouayad and Emeriault (2014)
(1999) (2017)
36 Daftaribesheli et al. (2011) 76 Salimi et al. (2016) 116 Choobbasti et al. (2019) 156 Toll and Giolas (1998)
37 Al-Taie et al. (2017) 77 Alireza and Mehdi (2014) 117 Araei Araei (2014) 157 Sriram (1984)
38 Abdulabbas and Ulabbas 78 Alkroosh and Nikraz (2013) 118 Nadiri et al. (2014) 158 Kanungo et al. (2014)
(2014)
39 Dutta (2016) 79 Bhardwaj and Venkatachalam 119 Shirzadi et al. (2017) 159 Jeng et al. (2003)
(2014)
40 Saha (2014) 80 Turan et al. (2008) 120 Sabbar et al. (2019) 160 Armaghani et al. (2016)

123
Geotech Geol Eng

Table 8 continued
ID References ID References ID References ID References

161 Armaghani et al. (2015) 201 Mayoraz and Vulliet (2002) 241 Rad et al. (2014) 281 Zadhesh et al. (2015)
162 Armaghani et al. (2014) 202 Nejad and Jaksa (2011) 242 Citakoglu (2017) 282 Kurek et al. (2015)
163 Armaghani et al. (2018a) 203 Nejad and Mark (2010) 243 Dine et al. (2015) 283 Gholamnejad and Tayarani
(2010)
164 Armaghani et al. (2018b) 204 Sarmadian and Mehrjardi (2008) 244 Rad et al. (2019) 284 Bandyopadhyay et al. (1995)
165 Mohammadzadeh et al. 205 Weihua (2012) 245 Adeli (2001) 285 Viloria et al. (2016)
(2016)
166 Mohammadzadeh et al. 206 Asimakopoulou et al. (2011) 246 Zhao et al. (2016) 286 Liu et al. (2008)
(2019)
167 Mohammadzadeh et al. 207 Farrokhzad et al. (2008) 247 Tran and Nhat-Duc Tran 287 Zhu et al. (1998)
(2014) and Nhat-Duc (2014)
168 Daniel et al. (2017) 208 Namdarvand et al. (2013) 248 Li et al. (2012) 288 Chen and Chang-Hua (2005)
169 Das (2010) 209 Milad et al. (2015) 249 Salehzadeh et al. (2014) 289 Lai et al. (2016)
170 Penumadu and Rongda 210 Isik and Gurkan (2013) 250 Khamesi et al. (2014) 290 Tinoco (2012)
(2000)
171 Cui et al. (2017) 211 Kang et al. (2016) 251 Moayedi et al. (2019a) 291 Tinoco et al. (2011a)
172 Ural and Mert (2008) 212 Kang and Junjie (2015) 252 Moayedi et al. (2019b) 292 Tinoco et al. (2011b)
173 Bui et al. (2018a) 213 Kang et al. (2013) 253 Moayedi and Danial (2018) 293 Tinoco et al. (2016)
174 Bui et al. (2018b) 214 Ozcep et al. (2010) 254 Moayedi and Abbas (2019) 294 Tinoco et al. (2011c)
175 Tsiaousi et al. (2018) 215 Martins and Tiago (2012) 255 Moayedi and Sajad (2017) 295 Tinoco et al. (2011d)
176 Dindarloo (2015b) 216 Martins et al. (2012) 256 Moayedi and Sajad (2018) 296 Tinoco et al. (2018)
177 Boumezerane et al. (2011) 217 Boadu et al. (2013) 257 Rezaei et al. (2016) 297 Joerg et al. (2008)
178 Prayogo and Yudas (2018) 218 Arunakumari and Latha (2008a) 258 Tabari et al. (2015) 298 Dungca and Joenel (2017)
179 Caniani et al. (2011) 219 Arunakumari and Latha (2008b) 259 Elarab and Yasir (2007) 299 Jeon and Rahman (2008)
180 Caniani et al. (2008) 220 Saygili et al. (2005) 260 Elarabi and Ali (2008) 300 Rangel et al. (2005)
181 Chang and Shafiqul (2000) 221 Li et al. (2014b) 261 Elarabi and Nahed (2014) 301 Chou and Anh-Duc (2015)
182 Bernard and Sardinha 222 Bekdas and Rasim (2017) 262 Park (2011) 302 Chou and Julian (2016)
(1993)
183 Momeni et al. (2014a) 223 Habibagahi and Alireza (2003) 263 Basheer (2002) 303 Chou et al. (2016)
184 Mohamad et al. (2018) 224 Sarkar et al. (2015) 264 Alkrooshn and Nikraz (2014) 304 Chou et al. (2015)
185 Ojo and Matawal (2014) 225 Singh Gurdeepak and Walia 265 Basheer (2001) 305 Chou and Ngoc-Tri (2018)
(2017)
186 Ravandi et al. (2013) 226 Pande and Hyu-Soung (2004) 266 AlArfaj et al. (2012) 306 Trivedi et al. (2013)
187 Ghaleini et al. (2019) 227 Maizir and Suryanita (2018) 267 Gonos and Ioannis (2005) 307 Wong et al. (1989)
188 Momeni et al. (2017) 228 Harandizadeh et al. (2018) 268 Markou et al. (2015) 308 Cui and Xiang (2018)
189 Momeni et al. (2015b) 229 Shahnazari et al. (2014) 269 Alkroosh and Hamid (2012) 309 Gopalakrishnan and Halil
(2009)
190 Momeni et al. (2015a) 230 Shin et al. (2008) 270 Alkroosh et al. (2015) 310 Tran et al. (2012)
191 Momeni et al. (2014b) 231 Basarira Hakan and David 271 Alkroosh (2011) 311 Young-Su and Kim (2006)
(2013)
192 Sharghi et al. (2018) 232 Javdanian and Biswajeet (2019) 272 Jan et al. (2002) 312 Kolay et al. (2008)
193 Pancar and Erhan (2011) 233 Saeidi and Mansour (2010) 273 Santamarina (1987) 313 Neaupane et al. (2008)
194 Hsiao et al. (2006) 234 Güllü (2013) 274 Facciorusso and Uzielli (2004) 314 Pieczarka et al. (2018)
195 Fattah et al. (2002) 235 Güllü and Halil (2017) 275 Chameau and Santamarina 315 Sharma et al. (2017)
(1989)
196 Fattah et al. (2005) 236 Anakci et al. (2009) 276 Tinoco et al. (2011d) 316 Pan et al. (2015)
197 Amegashie et al. (2006) 237 Li et al. (2011a) 277 Martin and Toll (2006) 317 Yaseen et al. (2014)
198 Farrokhzad et al. (2011) 238 Maizir and Khairul (2013) 278 Adeli (2000) 318 Meng and Zhang (2013)
199 Farrokhzad et al. (2010) 239 Maizir et al. (2015) 279 Shang et al. (2004) 319 Li et al. Li et al. (2009)
200 Farrokhzad et al. (2012) 240 Maizir et al. (2016) 280 Hamidi et al. (2010) 320 Zhang et al. (2016a)

123
Geotech Geol Eng

Table 8 continued
ID References ID References ID References ID References

321 Zhang et al. (2016b) 361 (2002) 401 Gandomi et al. (2016) 441 Samui (2012)
322 Xu et al. (2016) 362 Fatehnia and Gholamreza 402 Saadatpour et al. (2011) 442 Samui (2014)
(2018)
323 Wei and Qing (2000) 363 Nakhaee and Ali (2013) 403 Akram et al. (2014) 443 Samui (2008)
324 Sousa et al. (2017) 364 Cheng et al. (2008) 404 Khan et al. (2017) 444 Samui (2013)
325 Matmatte et al. (1997) 365 Cheng et al. (2014) 405 Ornek (2014) 445 Samui et al. (2009)
326 Kiefa (1998) 366 Miranda et al. (2004) 406 Ornek et al. (2012) 446 Samui and Sitharam (2010)
327 Amini et al. (2005) 367 Shahin (2015a) 407 Zaman et al. (2010) 447 Samui et al. (2015)
328 Prasad and Giridhar 368 Shahin (2014a) 408 Himanshu and Burman (2018) 448 Pirnia et al. (2018)
(2014)
329 Jaksa et al. (2008) 369 Shahin (2016) 409 Farag et al. (2005) 449 Basudhar (2008)
330 Banimahd et al. (2005) 370 Shahin (2015b) 410 Nawari and Liang (2000a) 450 Kurup and Erin (2006)
331 Chiru-Danzer et al. (2001) 371 Shahin (2014b) 411 Nawari and Liang (2000b) 451 Kurup and Nitin (2002)
332 Sakellariou and Ferentinou 372 Shahin (2013a) 412 Zhao (2014) 452 Kurup and Dudani (2001)
(2005)
333 Hajihassani et al. (2018) 373 Shahin (2010) 413 Juwaied (2018) 453 Biswajeet and Pirasteh (2010)
334 Hajihassani et al. (2019) 374 Shahin and Indraratna 414 Caglar and Hasan Caglar and 454 Muduli and Arat (2014)
(2006) Hasan (2007)
335 Mohamadnejad et al. 375 Shahin et al. (2004) 415 Khan et al. (2015) 455 Muduli and Sarat (2014)
(2012)
336 Shahin et al. (2003a) 376 Shahin et al. (2002a) 416 Yousefpour and Sogol (2018) 456 Muduli et al. (2015)
337 Shahin and Jaksa (2005) 377 Shahin and Mark (2009) 417 Puri et al. (2018) 457 Muduli et al. (2013)
338 Shahin et al. (2005) 378 Shahin and Mark (2006) 418 Ceryan et al. (2012) 458 Muduli and Arat (2014)
339 Shahin et al. (2000) 379 Shahin et al. (2003b) 419 Ceryan et al. (2013) 459 Kumar and Sarat (2015)
340 Taha and Firoozi (2012) 380 Shahin et al. (2008) 420 Flores and Romo (2001) 460 Kumar et al. (2015)
341 Saadata et al. (2014) 381 Shahin et al. (2001) 421 Sariyar and Ural (2010) 461 Solanki et al. (2009)
342 Pal (2011) 382 Shahin et al. (2002b) 422 Sanuade et al. (2017) 462 Santra et al. (2011)
343 Pal and Surinder (2008) 383 Shahin et al. (2009) 423 Sivrikaya and Mahmut (2009) 463 Ranasing MRATM and Jaksa
(2016)
344 Khandelwal (2011) 384 Shahin (2014b) 424 Kisi et al. (2015) 464 Babapour et al. (2015)
345 Khandelwal et al. (2018) 385 Attwa et al. (2014) 425 Debnath and Dey (2018) 465 Chitra and Manish (2014)
346 Khandelwal et al. (2011) 386 Khajehzadeh et al. (2011) 426 Talaee et al. (2012) 466 Trivedi et al. (2014)
347 Khandelwal and Singh 387 Rezaei et al. (2014) 427 Lu and Rosenbaum (2003) 467 Meij R van (2008a)
(2009)
348 Mosallanezhad and 388 Rezania and Javadi (2007) 428 Provenzano (2003) 468 Meij (2008b)
Hossein (2017)
349 Goharzay et al. (2017) 389 Zounemat-Kermani (2013) 429 Samui and Sitharam (2011a) 469 Meij (2008c)
350 Ferentinou et al. (2012) 390 Koopialipoor et al. (2019a) 430 Samui and Sitharam (2011b) 470 Viswanathan and Pijush (2016)
351 Martins and Randa (2013) 391 Koopialipoor et al. (2019b) 431 Bhargavi and Jyothi (2010) 471 Ranasinghe et al. (2018)
352 Mokhtar and Mahmoud 392 Al-Neami and Ami (2015) 432 Camarinha et al. (2011) 472 Ranasinghe et al. (2017)
(2018)
353 Shinoda and Yoshihisa 393 Benbouras et al. (2018) 433 Kolay et al. (2011) 473 Muhamedyev et al. Muhamedyev
(2018) et al. (2012)
354 Rashidi et al. (2019) 394 Hussain et al. (2015) 434 Dhekne et al. (2013) 474 Jana et al. (2008)
355 Liang et al. (2016) 395 Taha et al. (2010) 435 Tsangaratos and Andreas (2014) 475 Al-saffar et al. (2013)
356 Bilgili (2010) 396 Hajihassani (2013) 436 Cortez et al. (2004) 476 Barzegar et al. (2016)
357 Tumay et al. (2008) 397 Khajehzadeh et al. (2010) 437 Pavani (2014) 477 Pramanik et al. (2019)
358 Zhou et al. (2015) 398 Asadi (2016) 438 Lin et al. (2014) 478 Singh et al. (2012)
359 Tolon and Derin (2012) 399 Shahr-Babak et al. (2016) 439 Mullarkey and Steven (1986) 479 Nazir et al. (2015)
360 Oberguggenberger (2003) 400 Asadizadeh and Mohammad 440 Vergobbi et al. (1992) 480 Mohanty and Sarat (2018)
Asadizadeh and
Mohammad (2016)

123
Geotech Geol Eng

Table 8 continued
ID References ID References ID References ID References

481 Gholami et al. (2013) 521 Das and Shakti (2015) 561 Miranda (2007) 601 Wanga et al. (2013)
482 Kaunda (2014) 522 Mahdevari and Seyed (2012) 562 Miranda et al. (2008) 602 Zhang et al. (2009a)
483 Mikaeil et al. (2018) 523 Mahdevari et al. (2012) 563 Miranda et al. (2011a) 603 Alshkane (2017)
484 Rim et al. (2010) 524 Ziaee et al. (2015) 564 Miranda et al. (2009) 604 Li et al. (2010)
485 Alias et al. (2015) 525 Hashemi and Iraj (2018) 565 Miranda and Luı́s (2012) 605 Cheng and Zong (2013)
486 Kalatehjari et al. (2014) 526 Sheng-Jun et al. (2012) 566 Tsangaratos and Benardos (2013) 606 Erzin (2007)
487 Faradonbeh et al. (2018) 527 Shahin (2013a) 567 Lee et al. (2009) 607 Erzin (2008)
488 Faradonbeh and Danial (2016) 528 Suman et al. (2016a) 568 Turk et al. (2001) 608 Erzin et al. (2010)
489 Faradonbeh et al. (2016a) 529 Suman et al. (2015) 569 Kaya et al. (2012) 609 Erzin et al. (2008)
490 Faradonbeh et al. (2016b) 530 Suman et al. (2016b) 570 Dagdeviren and Kaymak (2015) 610 Erzin et al. (2009)
491 Li et al. (2011b) 531 Suman et al. (2016c) 571 Kohestani and Hassanlourad (2015) 611 Yang et al. (2012)
492 Sahoo and Sarat (2016) 532 Feng et al. (2014) 572 Kohestani et al. (2015) 612 Huang et al. (2014)
493 Adarsh et al. (2012) 533 Aboutaleb et al. (2018) 573 Rashidian and Hassanlourad (2014) 613 Liu et al. (2013)
494 Levasseur et al. (2008) 534 Motamedi et al. (2015) 574 Desai et al. (2009) 614 Liu et al. (2014b)
495 Meyer (1992) 535 Bekhor and Moshe (2014) 575 Nourani and Ali (2013) 615 Liu et al. (2014b)
496 Moosazadeh et al. (2017) 536 Bekhor and Moshe (2013) 576 Nourani and Hamid (2012) 616 Long-Yun et al. (2013)
497 Pezeshk et al. (1996) 537 Li and Yingxi (2004) 577 Maji and Sitharam (2008) 617 Jianbin et al. (2010)
498 Valliappan and Pham (1993) 538 Saride et al. (2010) 578 Nhu et al. (2019) 618 Luo et al. (2011)
499 Yagiz et al. (2012) 539 Thomas et al. (2013) 579 Kumar et al. (2012) 619 Yin et al. (2018)
500 Mazaheri et al. (1995) 540 Leu and Hsien-Chuang (2004) 580 Singh et al. (2019) 620 Chao et al. (2018)
501 Dindarloo and Elnaz (2015) 541 Kostic et al. (2016) 581 Chandwani et al. (2013) 621 Li et al. (2006)
502 Yasrebi and Emami (2008) 542 Fenves (1987) 582 Xu and Shao (1998) 622 Zhang and Mehmet (2003)
503 Khan et al. (2016) 543 Bhatt and Pradeep (2014) 583 Qazi et al. (2016) 623 Zhang and Mehmet (1999)
504 Dindarloo (2015a) 544 Nama et al. (2015) 584 Chen et al. (2018) 624 Moreshwar (2012)
505 Yagiz et al. (2018) 545 Khuntia (2014) 585 Gong et al. (2014) 625 Zhang et al. (2014)
506 Saha et al. (2017) 546 Sasmal and Rabi (2018) 586 Xiao and Bo (2009) 626 Kaya (2015)
507 Hussain et al. (2016) 547 Salem and Khalid (2010) 587 Feng et al. (2018)
508 Salehzadeh et al. (2011) 548 Senapati (2013) 588 Niu and Shike (2017)
509 Santamarina (1987) 549 Imran et al. (2018) 589 Xue (2016)
510 Das (2010) 550 Andrab et al. (2017) 590 Bui et al. (2019)
511 Das and Prabir (2008) 551 Sitharam et al. (2003) 591 Hashash et al. (2004)
512 Das (2013) 552 Miranda et al. (2011b) 592 Yang and Rosenbaum (2002)
513 Das et al. (2011a) 553 Miranda et al. (2018) 593 Zhang et al. (2009b)
514 Das et al. (2011b) 554 Miranda et al. (2013) 594 Chu et al. (2019)
515 Das et al. (2011c) 555 Roy et al. (2012) 595 Najjar et al. (1999)
516 Das and Rajankanta (2010) 556 Adam (1992) 596 Lee et al. (2012)
517 Das and Prabir (2006) 557 Eleftheriadou et al. (2014) 597 El-Shayeb et al. (1997)
518 Das (2008) 558 Fetz et al. (1999) 598 Mobarra et al. (2013)
519 Das and Pradyut (2011) 559 Oommen and Laurie (2008) 599 Tsompanakis et al. (2009)
520 Das et al. (2011d) 560 Behrens et al. (2005) 600 Yeh et al. (1993)

123
Geotech Geol Eng

100

Others 38%
80 Springer 19%
Publicaons number

60

40 Elsevier 18%
IEEE 2%

20 Wiley 2%
ASCE 13%
Taylor &
Francis 4%
0
Year
NRC Canada 4%
1985 1990 1995 2000 2005 2010 2015 2020

Fig. 15 Percentage of addressed Publishers


Fig. 12 Rate of published researches in using AI techniques in
geotechnical engineering
References
EPR 2% Expert 3% Abdollahzadeh A, Mukhlisin M, El Shafie A (2011) Predict soil
GA 5% erosion with artificial neural network in Tanakami (Japan).
ANN 48% Wseas Trans Comput 10(2):51–60
Others
5% Abdulabbas AA, Ulabbas YKB (2014) Estimation of shear
SVM 8% strength parameters of soils using ann technique. Int J Civil
Struct Environ Infrastruct Eng Res Dev 4(3):1–10
PSO 8% Aboutaleb S, Mahmoud B, Raheb B, Behzad B (2018) Using
non-destructive tests for estimating uniaxial compressive
Fuzzy 12% GP 9% strength and static Young’s modulus of carbonate rocks via
some modeling techniques. Bull Eng Geol Environ
77:1717–1728. https://doi.org/10.1007/s10064-017-1043-
2
Adam TM (1992) Expert system for retaining wall selection
Fig. 13 Percentage of used AI Technique Phase I. Report No. CDOT - DTD-R-93-5
Adarsh S, Dhanya R, Krishna G, Merlin R, Tina J (2012) Pre-
diction of ultimate bearing capacity of cohesionless soils
using soft computing techniques. Int Sch Res Netw. https://
Compacon 3% Water- doi.org/10.5402/2012/628496
Shoring 3% Soil Dynamics 3% Adeli H (2001) Neural networks in civil engineering:
3% Tunnel 4% 1989–2000. Comput Aided Civil Infrastruct Eng
Soil Prop. 21% Shallo
16(2001):126–142
w F.
6% Adoko AC, Wu L (2011) Fuzzy inference systems-based
Liquef. 5% approaches in geotechnical engineering-a review. EJGE
Deep F. 11%
Others 6%
16(2011):1543–1558
Adoko A-C, Yu-Yong J, Li W, Hao W, Zi-Hao W (2013) Pre-
Rock Prop. 10% dicting tunnel convergence using multivariate adaptive
Modeling 9% regression spline and artificial neural network. Tunnel
Slope 10% Undergr Space Technol 38(2013):368–376. https://doi.org/
Profiling 10.1016/j.tust.2013.07.023
6%
Ahangar-Asra A, Javadi AA, Johari A, Chen Y (2014) Lateral
load bearing capacity modelling of piles in cohesive soils in
Fig. 14 Percentage of studied Subjects undrained conditions: An intelligent evolutionary
approach. Appl Soft Comput J 2014:1–5. https://doi.org/
10.1016/j.asoc.2014.07.027
• Prof. Mohamed Shahin and Prof. Sarat Kumar Das Ahmadi-Nedushan B, Varaee H (2009) Optimal design of
are the most active researchers in this field with 25 reinforced concrete retaining walls using a Swarm intelli-
researches each. gence technique. In: First international conference on soft
computing technology in civil, structural and environ-
mental engineering, Scotland, Civil-Comp Press

123
Geotech Geol Eng

Akram M, Ismail Abdul R, Irfana M (2014) A review on expert Alimoradi A, James LB (2014) Machine-learning methods for
system and its applications in civil engineering. Int J Civil earthquake ground motion analysis and simulation. J Eng
Eng Built Environ 1(1):2289–6317 Mech. https://doi.org/10.1061/(ASCE)EM.1943-7889.
AlArfaj I, Amar K, Tuna E (2012) Application of advanced 0000869
computational intelligence to rate of penetration predic- Alimoradi A, Hashem S, Abolghasem KR (2011) Prediction of
tion. In: 2012 UKSim-AMSS 6th European modelling shear wave velocity in underground layers using SASW
symposium, pp 33–38, Doi: 10.1109/EMS.2012.79, IEEE and artificial neural networks. Engineering 3:266–275.
Alavi AH, Amir HG (2011a) Prediction of principal ground- https://doi.org/10.4236/eng.2011.33031
motion parameters using a hybrid method coupling artifi- Alireza K, Mehdi J (2014) Heterogeneous slope stability opti-
cial neural networks and simulated annealing. Comput mization using firefly algorithm, simulate annealing and
Struct 89(2011):2176–2194. https://doi.org/10.1016/j. imperialistic competitive algorithm. Int Res J Appl Basic
compstruc.2011.08.019 Sci 8(9):1222–1235
Alavi AH, Amir HG (2011b) A robust data mining approach for Alkroosh ISJ (2011) Modelling pile capacity and load-settle-
formulation of geotechnical engineering systems. Eng ment behaviour of piles embedded in sand and mixed soils
Comput 28(3):242–274. https://doi.org/10.1108/ using artificial intelligence, Ph.D. thesis, Curtin University
02644401111118132 Alkroosh I, Hamid N (2012) Predicting axial capacity of driven
Alavi AH, Amir HG (2012a) Discussion on ‘‘Models to predict piles in cohesive soils using intelligent computing. Eng
the deformation modulus and the coefficient of subgrade Appl Artif Intell 25(2012):618–627. https://doi.org/10.
reaction for earth filling structures’’ by Ismail Dinçer. Adv 1016/j.engappai.2011.08.009
Eng Softw 52(2012):44–46. https://doi.org/10.1016/j. Alkroosh I, Nikraz H (2013) Evaluation of pile lateral capacity
advengsoft.2012.06.001 in clay applying evolutionary approach. Int J Geomate
Alavi AH, Amir HG (2012b) Energy-based numerical models 4(1):462–465
for assessment of soil liquefaction. Geosci Front Alkroosh IS, Bahadori M, Nikraz H, Bahadori A (2015)
3(4):541–555. https://doi.org/10.1016/j.gsf.2011.12.008 Regressive approach for predicting bearing capacity of
Alavi AH, Sadrossadat E (2016) New design equations for bored piles from cone penetration test data. J Rock Mech
estimation of ultimate bearing capacity of shallow foun- Geotech Eng 7:584–592. https://doi.org/10.1016/j.jrmge.
dations resting on rock masses. Geosci Front 2015.06.011
7(2016):91–99. https://doi.org/10.1016/j.gsf.2014.12.005 Alkrooshn I, Nikraz H (2014) Predicting pile dynamic capacity
Alavi AHA, Gandomi AH, Gandomi M, Sadat Hosseini SS via application of an evolutionary algorithm. Soils Found
(2009) Prediction of maximum dry density and optimum 54(2):233–242. https://doi.org/10.1016/j.sandf.2014.02.
moisture content of stabilised soil using RBF neural net- 013
works. IES J Part A Civil Struct Eng 2(2):98–106. https:// Al-Neami MA, Ami M (2015) Prediction of unconfined com-
doi.org/10.1080/19373260802659226 pressive strength of soil using artificial neural network. In:
Alavi AH, Amir HG, Ali M, Ali AH, Azadeh R (2010) Modeling The 2nd international conference of buildings, construction
of maximum dry density and optimum moisture content of and environmental engineering (BCEE2-2015)
stabilized soil using artificial neural networks. J Plant Nutr Al-Rashid QA, Abuel-Naga HM, Leong E-CB, Lu Y, Al Abadi
Soil Sci 173:368–379. https://doi.org/10.1002/jpln. H (2018) Experimental-artificial intelligence approach for
200800233 characterizing electrical resistivity of partially saturated
Alavi AH, Pejman A, Amir HG, Milad AE (2011) Genetic- clay liners. Appl Clay Sci 156(2018):1–10. https://doi.org/
based modeling of uplift capacity of suction caissons. 10.1016/j.clay.2018.01.023
Expert Syst Appl 38(2011):12608–12618. https://doi.org/ Al-Rawas A, Saleh A-A, Adnan B, Yaqoob A-A (1998) Soil
10.1016/j.eswa.2011.04.049 classification decision support system using an expert
Alavi AH, Amir HG, Ali M, Jafar BB (2013) Linear and tree- system approach. Eng J Univ Qatar 11(1998):103–115
based genetic programming for solving geotechnical Al-saffar RZ, Suhail IK, Salim TY (2013) Prediction of soil’s
engineering problems. Metaheuristics Water Geotech compaction parameter using artificial neural network. Al-
Transp Eng 2013:289–310. https://doi.org/10.1016/B978- Rafidain Eng 27(3):15–27
0-12-398296-4.00012-X Alshkane YM (2017) Discussion on ‘‘property correlations and
Alavi AH, Gandomi AH, Lary DJ, Alavi AH (2016) Progress of statistical variations in the geotechnical properties of (CH)
machine learning in geosciences: preface. Geosci Front clay soils’’. Geotech Geol Eng. https://doi.org/10.1007/
7(2016):1–2. https://doi.org/10.1016/j.gsf.2015.10.006 s10706-017-0416-4
Al-Homoud AS, Al-Masri GA (1999) CSEES: an expert system Al-Taie AJ, Ahmed FA, Zahir NMT (2017) Compression index
for analysis and design of cut slopes and embankments. and compression ratio prediction by artificial neural net-
Environ Geol 39(1):75–89 works. J Eng 23(12):96–106
Al-Homoud AS, Tahtamoni WW (2000) SARETL: an expert Amegashie F, Shang JQ, Yanful EK, Ding W, Al-Martini S
system for probabilistic displacement-based dynamic 3-D (2006) Using complex permittivity and artificial neural
slope stability analysis and remediation of earthquake networks to identify and classify copper, zinc, and lead
triggered landslides. Environ Geol 39(8):849–874 contamination in soil. Can Geotech J 43(2006):100–109.
Alias R, Anuar K, Mohd RT (2015) Artificial neural networks https://doi.org/10.1139/T05-085
approach for predicting the stability of cantilever RC Amini M, Afyuni M, Fathianpour N, Khademi H, Fluhler H
retaining walls. Int J Appl Eng Res 10(10):26005–26014 (2005) Continuous soil pollution mapping using fuzzy
logic and spatial interpolation. Geoderma

123
Geotech Geol Eng

124(2005):223–233. https://doi.org/10.1016/j.geoderma. Asadi M (2016) Optimized Mamdani fuzzy models for pre-
2004.05.009 dicting the strength of intact rocks and anisotropic rock
Anakcı HC, Adil B, Hamza G (2009) Prediction of compressive masses. J Rock Mech Geotech Eng 8(2016):218–224.
and tensile strength of Gaziantep basalts via neural net- https://doi.org/10.1016/j.jrmge.2015.11.005
works and gene expression programming. Neural Comput Asadi A (2017) Application of artificial neural networks in
Appl 2009(18):1031–1041. https://doi.org/10.1007/ prediction of uniaxial compressive strength of rocks using
s00521-008-0208-0 well logs and drilling data. Procedia Eng
Andrab SG, Ali H, Zulkifli BY (2017) A review: evolutionary 191(2017):279–286. https://doi.org/10.1016/j.proeng.
computations (GA and PSO) in geotechnical engineering. 2017.05.182
Comput Water Energy Environ Eng 6:154–179. https://doi. Asadi A, Hossein M, Bujang BKH, Alireza P, Mohd RT (2011)
org/10.4236/cweee.2017.62012 Artificial neural networks approach for electrochemical
Araei AA (2014) Artificial neural networks for modeling resistivity of highly organic soil. Int J Electrochem Sci
drained monotonic behavior of rockfill materials. Int J 6(2011):1135–1145
Geomech 14(04014005):1–15. https://doi.org/10.1061/ Asadizadeh M, Mohammad FH (2016) Predicting rock mass
(ASCE)GM.1943-5622.0000323 deformation modulus by artificial intelligence approach
Ardakani A, Afshin K (2017) Soil compaction parameters pre- based on dilatometer tests. Arab J Geosci 9(96):1–15.
diction using GMDH-type neural network and genetic https://doi.org/10.1007/s12517-015-2189-5
algorithm. Eur J Environ Civil Eng. https://doi.org/10. Asimakopoulou FE, Georgios JT, Ioannis FG, Ioannis AS
1080/19648189.2017.1304269 (2011) Artificial neural network approach on the seasonal
Ardakani A, Kohestani VR (2015) Evaluation of liquefaction variation of soil resistance. In: 7th Asia-Pacific interna-
potential based on CPT results using C4.5 decision tree. tional conference on lightning, November 1–4, 2011,
J AI Data Mini 3(1):85–92. https://doi.org/10.5829/idosi. Chengdu, China, pp 794–799, 978-1-4577-1466-5/11/
JAIDM.2015.03.01.09 $26.00, IEEE
Ardakani A, Vahid RK (2017) Prediction of lateral bearing Attwa M, Khaled G, Mohamed E, Sara Z (2014) Application of
capacity of pile in clay using support vector machine. genetic algorithm (GA) for soil characterization using DC
J Civil Environ Eng 47(2):1–10 resistivity data: a case study in Tenth of Ramadan city,
Armaghani DJ, Mohsen H, Behnam YB, Aminaton M, Edy TM Egypt. Adv Nat Appl Sci 8(1):38–50
(2014) Indirect measure of shale shear strength parameters Aydin A (2004) Fuzzy set approaches to classification of rock
by means of rock index tests through an optimized artificial masses. Eng Geol 74(2004):227–245. https://doi.org/10.
neural network. Measurement 55(2014):487–498. https:// 1016/j.enggeo.2004.03.011
doi.org/10.1016/j.measurement.2014.06.001 Babapour R, Naghdi R, Ghajar I, Ghodsi R (2015) Modeling the
Armaghani DJ, Edy TM, Ehsan M, Mogana SN, Mohd FMA proportion of cut slopes rock on forest roads using artificial
(2015) An adaptive neuro-fuzzy inference system for pre- neural network and ordinal linear regression. Environ
dicting unconfined compressive strength and Young’s Monit Assess 2015:1–14. https://doi.org/10.1007/s10661-
modulus: a study on Main Range granite. Bull Eng Geol 015-4688-y
Environ 74:301–1319. https://doi.org/10.1007/s10064- Bafghi BK, Entezari ZH (2015) Prediction of permanent
014-0687-4 earthquake-induced deformation in earth dams and
Armaghani DJ, Edy TM, Ehsan M, Masoud M, Mogana SN embankments using artificial neural networks. Civil Eng
(2016) Prediction of the strength and elasticity modulus of Infrastruct J 48(2):271–283
granite through an expert artificial neural network. Arab J Bandyopadhyay JK, Srinivas SY, Gauri KL (1995) Artificial
Geosci 9(48):1–16. https://doi.org/10.1007/s12517-015- neural networks and durability of sphinx limestone. J Mater
2057-3 Civil Eng 7:174–177
Armaghani DJ, Roohollah SF, Hossein R, Ahmad SAR, Hassan Banimahd M, Yasrobi SS, Woodward PK (2005) Artificial
BA (2018a) Settlement prediction of the rock-socketed neural network for stress–strain behavior of sandy soils:
piles through a new technique based on gene expression knowledge based verification. Comput Geotech
programming. Neural Comput Appl 29:1115–1125. https:// 32:377–386. https://doi.org/10.1016/j.compgeo.2005.06.
doi.org/10.1007/s00521-016-2618-8 002
Armaghani DJ, Vali S, Ahmad F, Mohd FMA, Masoud M, Mir Barzegar R, Masoud S, Mohammad RN, Asghar AM (2016)
AM (2018b) Uniaxial compressive strength prediction Comparative evaluation of artificial intelligence models for
through a new technique based on gene expression pro- prediction of uniaxial compressive strength of travertine
gramming. Neural Comput Appl 30:3523–3532. https:// rocks, Case study: Azarshahr area, NW ran. Model Earth
doi.org/10.1007/s00521-017-2939-2 Syst Environ 2(76):1–13. https://doi.org/10.1007/s40808-
Arunakumari G, Latha GM (2008) Stress-strain prediction of 016-0132-8
jointed rocks using artificial neural networks. In: 12th Basarira Hakan H, David S (2013) Assessment of slope stability
international association for computer methods and using fuzzy sets and systems. Int J Min Reclam Environ
advances in geomechanics (IACMAG), Goa, India, 27(5):312–328. https://doi.org/10.1080/17480930.2012.
pp 1872–1879 702000
Arunakumari G, Latha GM (2008) Numerical prediction of Basheer IA (2001) Empirical modeling of the compaction curve
stress-strain response of jointed rocks. In: Continuum and of cohesive soils. Can Geotech J 38:29–45
distinct element numerical modeling in geo-engineering, Basheer IA (2002) Stress-strain behavior of geomaterials in
ISBN 978-0-9767577-1-9 loading reversal simulated by time-delay neural networks.

123
Geotech Geol Eng

J Mater Civil Eng 14(3):270–273. https://doi.org/10.1061/ Bharanidhar TS, Premalatha J (2018) Advanced civil engi-
(ASCE)0899-1561(2002)14:3(270) neering optimization by artificial intelligent systems:
Basma AA, Nabil K (2004) Modeling soil collapse by artificial review. J Res 3(12):2395–7549
neural networks. Geotech Geol Eng 22:427–438 Bhardwaj AB, Venkatachalam G (2014) Landslide hazard
Basudhar PK (2008) Application of optimization and other evaluation using artificial neural networks and GIS.
evolutionary techniques in geotechnical engineering. In: Landslide Sci Safer Geoenviron 2:397–403. https://doi.
12th international association for computer methods and org/10.1007/978-3-319-05050-8_62
advances in geomechanics (IACMAG), Goa, India, Bhargavi P, Jyothi S (2010) Fuzzy C-means classifier for soil
pp 133–145 data. Int J Comput Appl 6(4):0975–8887
Baykasog A, Hamza G, Hanifi C, Lale O (2008) Prediction of Bhatt S, Pradeep KJ (2014) Prediction of California bearing
compressive and tensile strength of limestone via genetic ratio of soils using artificial neural network. Am Int J Res
programming. Expert Syst Appl 35(2008):111–123. Sci Technol Eng Math 8(2):156–161
https://doi.org/10.1016/j.eswa.2007.06.006 Bhattacharya BB, Solomatine DP (2006) Machine learning in
Behrens T, Helga F, Thomas S, Ulrich S, Ernst-Dieter S, soil classification. Neural Netw 19(2006):186–195. https://
Michael G (2005) Digital soil mapping using artificial doi.org/10.1016/j.neunet.2006.01.005
neural networks. J Plant Nutr Soil Sci 168:1–13. Bilgili M (2010) Prediction of soil temperature using regression
Bekdaş G, Rasim T (2017) Grey wolf optimizer for optimum and artificial neural network models. Meteorol Atmos Phys
design of reinforced concrete cantilever retaining walls. Int 110:59–70. https://doi.org/10.1007/s00703-010-0104-x
Conf Numer Anal Appl Math. https://doi.org/10.1063/1. Bilski A (2018) Survey of AI methods for the purpose of
5043893 geotechnical profile creation. ACS. https://doi.org/10.
Bekhor S, Moshe L (2013) Limitation of the artificial neural 1007/978-3-030-03314-9_2
networks methodology for predicting the vertical swelling Birdossy A, Bronsterts A, Merz B (1995) l-, 2- and 3-dimen-
percentage of expansive clays. J Mater Civil Eng sional modeling of water movement in the unsaturated soil
25:1731–1741. https://doi.org/10.1061/(ASCE)MT.1943- matrix using a fuzzy approach. Adv Water Resour
5533.0000720 18(4):237–251
Bekhor S, Moshe L (2014) Using the artificial neural networks Biswajeet P, Pirasteh S (2010) Comparison between prediction
methodology to predict the vertical swelling percentage of capabilities of neural network and fuzzy logic techniques
expansive clays. J Mater Civil Eng 26(06014007):1–5. for land slide susceptibility mapping. Disaster Adv
https://doi.org/10.1061/(ASCE)MT.1943-5533.0000931 3(3):26–34
Benardos AG, Kaliampakos DC (2004) Modelling TBM per- Boadu FK, Frederick O-N, Francis A, Samuel IKA (2013)
formance with artificial neural networks. Tunnel Undergr Artificial neural network and statistical models for pre-
Space Technol 19(2004):597–605. https://doi.org/10.1016/ dicting the basic geotechnical properties of soils from
j.tust.2004.02.128 electrical measurements. Near Surface Geophysics
Benbouras MA, Ratiba RK, Hamma Z, Alexandru-Ionut P, 2013(11):599–612. https://doi.org/10.3997/1873-0604.
NourredineNourredine M, Fatiha D (2018) A new 2013011
approach to predict the compression index using artificial Bouayad D, Emeriault F (2014) Application of the hybrid ACP/
intelligence methods. Mar Georesour Geotechnol ANFIS method for the prediction of surface settlement
2018:1–18. https://doi.org/10.1080/1064119X.2018. induced by an earth pressure tunnel boring machine with
1484533 consideration of the encountered geology. In: Proceedings
Bernard E, Sardinha PRC (1993) Concept and practice of expert of the 8th European conference on numerical methods in
systems in civil engineering. Trans Inf Commun Technol geotechnical engineering, Delft, The Netherlands,
1:417–428 pp 333–338
Besalatpour A, Hajabbasi MA, Ayoubi S, Afyuni M, Jalalian A, Boumezerane D, Ezerane SB, Bojan Z (2011) Fuzzy-sets deci-
Schulin R (2012a) Soil shear strength prediction using sion-support system for geotechnical site soundings. Acta
intelligent systems: artificial neural networks and an Geotechnica Slovenica 1:51–63
adaptive neuro-fuzzy inference system. Soil Sci Plant Nutr Bui DT, Nhat-Duc H, Viet-Ha N (2018a) A swarm intelligence-
58(2):149–160. https://doi.org/10.1080/00380768.2012. based machine learning approach for predicting soil shear
661078 strength for road construction: a case study at Trung Luong
Besalatpour A, Hajabbasi MA, Ayoubi S (2012) Using gamma National Expressway Project (Vietnam). Eng Comput.
test to determine the optimum input variables for soil shear https://doi.org/10.1007/s00366-018-0643-1
strength prediction by neural networks. In: 8th interna- Bui T, Viet-Ha N, Nhat-Duc H (2018b) Prediction of soil
tional soil science congress on ‘‘land degradation and compression coefficient for urban housing project using
challenges in sustainable soil management’’, Çeşme-İzmir, novel integration machine learning approach of swarm
Turkey, pp 249–254 intelligence and Multi-layer Perceptron Neural Network.
Besalatpour A, Ayoubi S, Hajabbasi MA, Yousefian Jazi A, Adv Eng Inform 38(2018):593–604. https://doi.org/10.
Gharipour A (2014) Feature selection using parallel 1016/j.aei.2018.09.005
genetic algorithm for the prediction of geometric mean Bui X-N, Mohammed AN, Hoang N (2019) Optimizing
diameter of soil aggregates by machine learning methods. Levenberg–Marquardt backpropagation technique in pre-
Arid Land Res Manag 28(2014):383–394. https://doi.org/ dicting factor of safety of slopes after two-dimensional
10.1080/15324982.2013.871599 OptumG2 analysis. Eng Comput. https://doi.org/10.1007/
s00366-019-00741-0

123
Geotech Geol Eng

Cabalar AF, Abdulkadir C (2009) Modelling damping ratio and Chen C, Jiasheng Z (2013) Constitutive modeling of loose sands
shear modulus of sand–mica mixtures using neural net- under various stress paths. Int J Geomech 13(1):1–8.
works. Eng Geol 104(2009):31–40. https://doi.org/10. https://doi.org/10.1061/(ASCE)GM.1943-5622.0000191
1016/j.enggeo.2008.08.005 Chen C, Zhiyu X, Genbao Z (2011) Stability assessment model
Cabalar AF, Abdulkadir C (2011) Triaxial behavior of sand– for epimetamorphic rock slopes based on adaptive neuro-
mica mixtures using genetic programming. Expert Syst fuzzy inference system. EJGE 16(2011):93–107
Appl 38(2011):10358–10367. https://doi.org/10.1016/j. Chen W, Himan S, Ataollah S, Haoyuan H, Aykut A, Yingying
eswa.2011.02.051 T, Junzhi L, Zhu A-X, Shaojun L (2018) Novel hybrid
Cabalar AF, Abdulkadir C, Candan G (2012) Some applications artificial intelligence approach of bivariate statistical-
of adaptive neuro-fuzzy inference system (ANFIS) in methods-based kernel logistic regression classifier for
geotechnical engineering. Comput Geotech landslide susceptibility modeling. Bull Eng Geol Env.
40(2012):14–33. https://doi.org/10.1016/j.compgeo.2011. https://doi.org/10.1007/s10064-018-1401-8
09.008 Cheng Y-M, Zong WG (2013) Hybrid Heuristic optimization
Caglar N, Hasan A (2007) The applicability of neural networks methods in geotechnical engineering. Metaheuristics
in the determination of soil profiles. Bull Eng Geol Environ Water Geotech Transp Eng 2013:205–229. https://doi.org/
66:295–301. https://doi.org/10.1007/s10064-006-0075-9 10.1016/B978-0-12-398296-4.00009-X
Camarinha PIM, Trannin ICB, Simões SJC, Bernardes GP Cheng M-Y, Hsing-Chih T, Chien-Ho K, Wen-Te C (2008)
(2011) Fuzzy logic and geostatistical techniques for spa- Evolutionary Fuzzy neural inference system for decision
tialization of soil texture in region with rough Terrains. making in geotechnical engineering. J Comput Civil Eng
Procedia Environ Sci 7(2011):347–352. https://doi.org/10. 22:272–280. https://doi.org/10.1061/ASCE0887-
1016/j.proenv.2011.07.060 3801200822:4272
Caniani D, Stefania P, Francesco S, Aurelia S (2008) Neural Cheng M-Y, Minh-Tu C, Yu-WeiYu-Wei W (2014) Predicting
networks and landslide susceptibility: a case study of the equilibrium scour depth at bridge piers using volutionary
urban area of Potenza. Nat Hazards 45:55–72. https://doi. radial basis function neural network. J Comput Civil Eng
org/10.1007/s11069-007-9169-3 04014070:1–10. https://doi.org/10.1061/(ASCE)CP.1943-
Caniani D, Donata SL, Ignazio MM, Salvatore M (2011) 5487.0000380
Application of fuzzy logic and sensitivity analysis for soil Chiru-Danzer M, Juang CH, Christopher RA, Suber J (2001)
contamination hazard classification. Waste Manag Estimation of liquefaction-induced horizontal displace-
31(2011):583–594. https://doi.org/10.1016/j.wasman. ments using artificial neural networks. Can Geotech J
2010.09.012 38(2001):200–207. https://doi.org/10.1139/cgj-38-1-200
Ceryan N, Umut O, Ayhan K (2012) Application of generalized Chitra R, Manish G (2014) Neural networks for assessing shear
regression neural networks in predicting the unconfined strength of soils. Int J Recent Dev Eng Technol 3(4):24–32
compressive strength of carbonate rocks. Rock Mech Rock Choobbasti AJ, Shooshpasha E, Farrokhzad F (2012) 3-D
Eng 45:1055–1072. https://doi.org/10.1007/s00603-012- modeling of soil’s unsaturated depth using artificial neural
0239-9 network (case study of Babol). Unsaturat Soils Res Appl
Ceryan N, Umut O, Pijush S, Sener C (2013) Modeling of tensile 2:317–324. https://doi.org/10.1007/978-3-642-31343-1
strength of rocks materials based on support vector Choobbasti A, Obbasti J, Saman SK, Mobina TPA (2019)
machines approaches. Int J Numer Anal Methods Geomech Modeling of compressive strength of cemented sandy soil.
37:2655–2670. https://doi.org/10.1002/nag.2154 J Adhes Sci Technol 2019:1–18. https://doi.org/10.1080/
Chakraborty A, Diganta G (2017) Prediction of slope stability 01694243.2018.1548535
using multiple linear regression (MLR) and artificial neural Chou J-S, Anh-Duc P (2015) Smart artificial firefly colony
network (ANN). Arab J Geosci 10:385. https://doi.org/10. algorithm-based support vector regression for enhanced
1007/s12517-017-3167-x forecasting in civil engineering. Comput Aided Civil
Chameau JL, Santamarina JC (1989) Knowledge-based system Infrastruct Eng 30(2015):715–732. https://doi.org/10.
for soil improvement. J Comput Civil Eng 3(3):253–267 1111/mice.12121
Chandwani V, Vinay A, Ravindra N (2013) Applications of soft Chou J-S, Julian PPT (2016) Metaheuristic optimization within
computing in civil engineering: a review. Int J Comput machine learning-based classification system for early
Appl 81(10):13–20 warnings related to geotechnical problems. Autom Constr
Chang D-H, Shafiqul I (2000) Estimation of soil physical 68(2016):65–80. https://doi.org/10.1016/j.autcon.2016.03.
properties using remote sensing and artificial neural net- 015
work. Remote Sens Environ 74:534–544 Chou J-S, Ngoc-Tri N (2018) Engineering strength of fiber-
Chao Z, Guotao M, Ye Z, Yanjie Z, Hengyang H (2018) The reinforced soil estimated by swarm intelligence optimized
application of artificial neural network in geotechnical regression system. Neural Comput Appl 30:2129–2144.
engineering. Int Conf Civil Hydraulic Eng 1:7. https://doi. https://doi.org/10.1007/s00521-016-2739-0
org/10.1088/1755-1315/189/2/022054 Chou J-S, Kuo-Hsin Y, Jusieandra PP, Anh-Duc P (2015)
Chen J-W, Chang-Hua C (2005) Application of Fuzzy soil Evolutionary metaheuristic intelligence to simulate tensile
classification in visualizing 3-D soil strata. J Marine Sci loads in reinforcement for geosynthetic-reinforced soil
Technol 13(4):265–270 structures. Comput Geotech 66(2015):1–15. https://doi.
Chen B-RC, Feng DX-T (2007) CSV-PSO and its application in org/10.1016/j.compgeo.2015.01.001
geotechnical engineering. Swarm Intell Focus Ant Particle Chou J-S, Kuo-Hsin Y, Jie-Ying L (2016) Peak shear strength of
Swarm Optim 15:263–288 discrete fiber-reinforced soils computed by machine

123
Geotech Geol Eng

learning and metaensemble methods. J Comput Civil Eng Das SK, Pradyut KM (2011) Evaluation of liquefaction potential
04016036:1–17. https://doi.org/10.1061/(ASCE)CP.1943- of soil using genetic programming. In: Indian geotechnical
5487.0000595 conference, 2011, Kochi (Paper No. N-082.), pp 827–830
Chu Y, Songyu L, Guojun C, Hanliang B (2019) Artificial neural Das SKB, Rajankanta DB (2010) Parameter estimation of soil
network prediction models of heavy metal polluted soil slopes using artificial neural networks. In: Indian
resistivity. Eur J Environ Civil Eng. https://doi.org/10. Geotechnical Conference–2010, GEOtrendz, IGS Mumbai
1080/19648189.2019.1585962 Chapter and IIT Bombay, pp 829–832
Citakoglu H (2017) Comparison of artificial intelligence tech- Das SK, Shakti S (2015) Prediction of lateral load capacity of
niques for prediction of soil temperatures in Turkey. Theor pile in clay using multivariate adaptive regression spline
Appl Climatol 130:545–556. https://doi.org/10.1007/ and functional network. Arab J Sci Eng 40:1565–1578.
s00704-016-1914-7 https://doi.org/10.1007/s13369-015-1624-y
Cortez P, Rui M, Antonio G (2004) Artificial intelligence Das SK, Pijush S, Akshaya KS, Sitharam TG (2010) Prediction
applied to compaction rules and management. In: Project of swelling pressure of soil using artificial intelligence
POCI/ECM/6lll4/2004 Interaction soil-railway track for techniques. Environ Earth Sci 2010(61):393–403. https://
high speed trains, Portugal doi.org/10.1007/s12665-009-0352-6
Cui K, Xiang J (2018) Research on prediction model of Das SK, Pijush S, Shakilu ZK, Nagarathnam S (2011a) Machine
geotechnical parameters based on BP neural network. learning techniques applied to prediction of residual
Neural Comput Appl 2018:1–11. https://doi.org/10.1007/ strength of clay. Central Eur J Geosci 3(4):449–461.
s00521-018-3902-6 https://doi.org/10.2478/s13533-011-0043-1
Cui D-M, Weizhong Y, Xiao-Quan W, Lie-Min L (2017) Das SK, Manna B, Baidya DK (2011) Prediction of the dynamic
Towards intelligent interpretation of low strain pile integ- soil-pile interaction under coupled vibration using artificial
rity testing results using machine learning techniques. neural network approach. In: Geo-Frontiers 2011, ASCE
Sensors 17(2443):1–15. https://doi.org/10.3390/ Das SK, Pijush S, Akshaya KS (2011c) Application of artificial
s17112443 intelligence to maximum dry density and unconfined
Daftaribesheli A, Mohammad A, Farhang S (2011) Assessment compressive strength of cement stabilized soil. Geotech
of rock slope stability using the Fuzzy Slope Mass Rating Geol Eng 2011(29):329–342. https://doi.org/10.1007/
(FSMR) system. Appl Soft Comput 11(2011):4465–4473. s10706-010-9379-4
https://doi.org/10.1016/j.asoc.2011.08.032 Das SK, Rajani KB, Sivakugan N, Bitanjaya D (2011d) Clas-
Dağdeviren U, Kaymak B (2015) Optimum design of reinforced sification of slopes and prediction of factor of safety using
concrete retaining walls using artificial Bee Colony algo- differential evolution neural networks. Environ Earth Sci
rithm. In: ICOCEE–CAPPADOCIA2015, Nevsehir, Tur- 2011(64):201–210. https://doi.org/10.1007/s12665-010-
key, pp 1171–1180 0839-1
Daniel P, Debrup B, Chiman K, Minh D, Yuzhong S, Kris K, Debnath P, Dey AK (2018) Prediction of bearing capacity of
Giovanni M, Jiang L (2017) Deep learning for effective geogrid-reinforced stone columns using support vector
detection of excavated soil related to illegal tunnel activi- regression. Int J Geomech 18(2):04017147. https://doi.org/
ties. In: 978-1-5386-1104-3/17/$31.00 2017 IEEE. This 10.1061/(ASCE)GM.1943-5622.0001067
work was supported by the DARPA under contract Dehghanbanadaki A, Mohammad AS, Iman G, Azin K, Marjan I
D17PC00025., 1-7, DOI 978-1-5386-1104-3/17/$31.00, (2019) Prediction of geotechnical properties of treated
IEEE fibrous peat by artificial neural networks. Bull Eng Geol
Das SK (2008) Swelling pressure of soil: artificial intelligence Env 78:1345–1358. https://doi.org/10.1007/s10064-017-
technique approaches. In: 12th international association for 1213-2
computer methods and advances in geomechanics (IAC- Denby B, Kizil MS (1991) An application of expert systems in
MAG), Goa, India, pp 1880–1884 geotechnical risk assessment for surface coal mine design.
Das SK (2010) Prediction of lateral displacement of liquefaction Int J Surf Min Reclam Environ 5(2):75–82. https://doi.org/
induced ground using extreme learning. In: Fifth interna- 10.1080/09208119108944289
tional conference on recent advances in geotechnical Desai VGM, Veena D, Rao DH (2009) Prediction of compres-
earthquake engineering and soil dynamics, http:// sion index using artificial neural networks. In: IGC 2009,
scholarsmine.mst.edu/icrageesd/05icrageesd/session04/ Guntur, INDIA, pp 614–617
31, Scholars’ Mine Dhekne PY, Manoj P, Jade RK (2013) Artificial intelligence and
Das SK (2013) Artificial neural networks in geotechnical prediction of rock fragmentation. In: 22nd mine planning
engineering: modeling and application issues. Meta- and equipment selection conference, Dresden, Germany,
heuristics Water Geotech Transp Eng 2013:231–270. pp 891–898, Doi: 10.1007/978-3-319-02678-7_86
https://doi.org/10.1016/B978-0-12-398296-4.00010-6 Dindarloo SR (2015a) Peak particle velocity prediction using
Das SK, Prabir KB (2006) Undrained lateral load capacity of support vector machines: a surface blasting case study.
piles in clay usingartificial neural network. Comput Geo- J Southern African Inst Mini Metall 115:637–643. https://
tech 33(2006):454–459. https://doi.org/10.1016/j. doi.org/10.17159/2411-9717/2015/v115n7a10
compgeo.2006.08.006 Dindarloo SR (2015b) Prediction of blast-induced ground
Das SK, Prabir KB (2008) Prediction of residual friction angle vibrations via genetic programming. Int J Mining Sci
of clays using artificial neural network. Eng Geol Technol. https://doi.org/10.1016/j.ijmst.2015.09.020
100(2008):142–145. https://doi.org/10.1016/j.enggeo.
2008.03.001

123
Geotech Geol Eng

Dindarloo SR, Elnaz S-I (2015) Estimating the unconfined conductivity of compacted fine-grained soils. Can Geotech
compressive strength of carbonate rocks using gene J 46(2009):955–968. https://doi.org/10.1139/T09-035
expression programming. Eur J Sci Res 135(3):309–316 Erzin Y, Rao BH, Patel A, Gumaste SD, Singh DN (2010)
Dine HK, Mous ED, Hebatalrahman A, Hesham KA, Khalid E Artificial neural network models for predicting electrical
(2015) Study for application of artificial neural networks in resistivity of soils from their thermal resistivity. Int J
soil stabilization by nanotechnology. In: 7th International Thermal Sci 49(2010):118–130. https://doi.org/10.1016/j.
conference on Nano-technology in construction (NTC ijthermalsci.2009.06.008
2015), Sharm El-Shikh, Egypt, HBRC Facciorusso J, Uzielli M (2004) Stratigraphic profiling by
Dungca JR, Joenel GG (2017) Artificial neural network per- cluster analysis and fuzzy soil classification from
meability modeling of soil blended with fly ash. Int J mechanical cone penetration tests. In: Proceedings ISC-2
GEOMATE 12(31):77–82. https://doi.org/10.21660/2017. on geotechnical and geophysical site characterization,
31.6549 pp 905–912, ISBN 90 5966 009 9, Millpres
Dutta A (2016) Application of soft computing techniques for Faradonbeh RS, Danial JA (2016) Genetic programing and non-
prediction of slope failure in opencast mines. Research to linear multiple regression techniques to predict backbreak
fulfill the degree of B. Tech & M. Tech Dual Degree in in blasting operation. Eng Comput 2016(32):123–133.
Mining Engineering, National Institute of Technology, https://doi.org/10.1007/s00366-015-0404-3
Rourkela Faradonbeh RS, Danial JA, Hassan BA, Edy TM (2016a) Pre-
Ebid AM (2004) Applications of genetic programming in diction and minimization of blast-induced flyrock using
geotechnical engineering, Ph.D. thesis, Ain Shams Uni., gene expression programming and firefly algorithm. Neu-
Cairo, Egypt ral Comput Appl 29:269–281. https://doi.org/10.1007/
Yaseen LK, Een, ERYKB (2014) Neuro-Fuzzy technique for the s00521-016-2537-8
estimation of liquefaction potential of soil. In: International Faradonbeh RS, Danial JA, Hassan BA, Edy TM (2016b)
journal of scientific engineering and technology research, Genetic programming and gene expression programming
vol 03, no 04, pp 617–623, SEMAR GROUPS for flyrock assessment duetomineblasting. Int J Rock Mech
Elarab H, Yasir A (2007) Soil profile prediction in khartoum Min Sci 88:254–264. https://doi.org/10.1016/j.ijrmms.
using artificial neural networks. In: 4th African Regional 2016.07.028
conference on soil mechanics an geotechnical Faradonbeh RS, Mahdi H, Hassan BA, Danial JA, Masoud M
Elarabi H, Ali K (2008) Prediction of soil parameters using (2018) Development of GP and GEP models to estimate an
Artificial Neural Network. The Digital Soil Mapping environmental issue induced by blasting operation. Envi-
Conference, USA, pp 395–407 ron Monit Assess 190:1–15. https://doi.org/10.1007/
Elarabi H, Nahed FT (2014) Developing of prediction models s10661-018-6719-y
for soil profile and its parameters using Artificial Neural Farag NO, El-Zahaby KM, Bazaraa AS (2005) Quantifying soil-
Networks. Sci Res 2(3):43–48. https://doi.org/10.11648/j. raft-superstructure interaction using field testing. In:
sr.20140203.13 Numerical analysis and artificial neural networks, ANNs,
Elbosraty AH, Ahmed ME, Ayman LF (2019) Predicting Nk Structures Congress 2005, ASCE
factor of CPT test using GP: comparative study of MEPX Farrokhzad F, Choobbasti AJ, Barari A (2008) Prediction of
& GN7. Int J Sci Eng Res 10(3):613–620 slope stability using artificial neural network (case study:
Eleftheriadou T, Nikos A, Vasilios PA, Ioannis FG, Georgios D, Noabad, Mazandaran, Iran). Int Confer Case Histories
Ioannis AS (2014) Ground resistance estimation using Geotech Eng 41:1–9
feed-forward neural networks, linear regression and feature Farrokhzad F, Choobbasti AJ, Barari A (2010) Artificial neural
selection models, SETN 2014, LNAI 8445, pp 418–429, network model for prediction of liquefaction potential in
Springer soil deposits. In: Fifth international conference on recent
El-Shayeb Y, Thierry V, Christophe D (1997) Fuzzy Reasoning advances in geotechnical earthquake engineering and soil
for the analysis of risks in geotechnical engineering dynamics, http://scholarsmine.mst.edu/icrageesd/
Application to a French Case. In: European congress on 05icrageesd/session04/4, Scholars’ Mine
intelligent techniques and soft computing, Aachen, Farrokhzad F, Barari A, Choobbasti AJ, Ibsen LB (2011) Neural
Germany network-based model for landslide susceptibility and soil
Erzin Y (2007) Artificial neural networks approach for swell longitudinal profile analyses: two case studies. J Africa
pressure versus soil suction behaviour. Can Geotech J Earth Sc 61(2011):349–357. https://doi.org/10.1016/j.
44(2007):1215–1223. https://doi.org/10.1139/T07-052 jafrearsci.2011.09.004
Erzin Y (2008) The use of artificial neural networks for the Farrokhzad F, Choobbasti AJ, Barari A (2012) Liquefaction
prediction of swell pressure. In: 12th international associ- microzonation of Babol city using artificial neural network.
ation for computer methods and advances in geomechanics J King Saud Univ Sci 24:89–100. https://doi.org/10.1016/j.
(IACMAG), Goa, India, pp 1890–1897 jksus.2010.09.003
Erzin Y, Rao BH, Singh DN (2008) Artificial neural network Fatehnia M, Gholamreza A (2018) A review of genetic pro-
models for predicting soil thermal resistivity. Int J Thermal gramming and artificial neural network applications in pile
Sci 47(10):1347–1358. https://doi.org/10.1016/j. foundations. Fatehnia Amirinia Geo-Eng 9:1–20. https://
ijthermalsci.2007.11.001 doi.org/10.1186/s40703-017-0067-6
Erzin Y, Gumaste SD, Gupta AK (2009) Artificial neural net- Fattah EA, Hossam EAA, Ahmed ME (2002) Prediction of soil
work (ANN) models for determining hydraulic liquefaction using genetic programming. In: III Middel
East Regional conference on civil engineering technology

123
Geotech Geol Eng

and III international symposium on environmental materials. Int J Geomech 04016060:1–20. https://doi.org/
hydrology 10.1061/(ASCE)GM.1943-5622.0000660
Fattah EA, Hossam EAA, Ahmed ME (2005) Prediction of Gholami R, Vamegh R, Andisheh A (2013) Improved RMR
uplift capacity for shallow foundations using genetic pro- rock mass classification using artificial intelligence algo-
gramming. In: Eleventh international colloquium on rithms. Rock Mech Rock Eng 46:1199–1209. https://doi.
structural and geotechnical engineering, Ain Shams org/10.1007/s00603-012-0338-7
University-Cairo Gholamnejad J, Tayarani N (2010) Application of artificial
Feng S, Aimin Y, Yanfei D (2014) Fuzzy comprehensive neural networks to the prediction of tunnel boring machine
evaluation of open-pit slope stability. Adv Mater Res penetration rate. Mining Sci Technol 20(2010):0727–0733.
962–965(2014):1029–1033. https://doi.org/10.4028/www. https://doi.org/10.1016/S1674-5264(09)60271-4
scientific.net/AMR.962-965.1029 Ghorbani A, Mostafa FN (2017) Evaluation of induced settle-
Feng X, Shuchen L, Chao Y, Peng Z, Yang S (2018) Prediction ments of piled rafts in the coupled static-dynamic loads
of slope stability using naive bayes classifier. KSCE J Civil using neural networks and evolutionary polynomial
Eng 22(3):941–950. https://doi.org/10.1007/s12205-018- regression. Appl Comput Intell Soft Comput 2017:1–23.
1337-3 https://doi.org/10.1155/2017/7487438
Fenves SJ (1987) Role of artificial intelligence and knowledge- Goh ATC (1995) Predicting seismic liquefaction using neural
base expert system methods in civil engineering. In: networks. Int Confer Recent Adv Geotech Earthq Eng Soil
University Libraries, Carnegie Mellon University, Pitts- Dyn 15:261–264
burgh, Pennsylvania, vol 15213, pp 1–24 Goh ATC (1996) Neural-network modeling of CPT seismic
Ferentinou M, Thomas H, Michael S (2012) Application of liquefaction data. J Geotech Eng 122(1):70–73
computational intelligence tools for the analysis of marine Goh ATC (1999a) Soil laboratory data interpretation using
geotechnical properties in the head of Zakynthos canyon, generalized regression neural network. Civil Eng Environ
Greece. Comput Geosci 40:166–174. https://doi.org/10. Syst 16(3):175–195. https://doi.org/10.1080/
1016/j.cageo.2011.06.022 02630259908970261
Fetz T, Michael O, Johannes J, David K, Gunther K, Heimo L, Goh ATC (1999b) Genetic algorithm search for critical slip
Rudolf FS (1999) Fuzzy models in geotechnical engi- surface in multiple-wedge stability analysis. Can Geotech J
neering and construction management. Comput Aided 36:382–391
Civil Infrastruct Eng 14:93–106 Goh ATE (2001) Neural network applications in geotechnical
Flores CO, Romo MPO (2001) Dynamic behavior of tailings. Int engineering. Scientia Iranica 8(1):1–9
Conf Recent Adv Geot Earthq Eng Soil Dyn 41:1–6 Goh ATC (2002) Probabilistic neural network for evaluating
Gandomi AH, Ali RK (2018) Construction cost minimization of seismic liquefaction potential. Can Geotech J
shallow foundation using recent swarm intelligence tech- 39(2002):219–232. https://doi.org/10.1139/T01-073
niques. IEEE Trans Industr Inf 14(3):1099–1106. https:// Goh ATC, Chai GC (2013) Geotechnical applications of baye-
doi.org/10.1109/TII.2017.2776132 sian neural networks. Metaheuristics Water Geotech
Gandomi AH, Ali RK, Mehdi M, Mehdi J (2015) Slope stability Transp Eng 2013:271–287. https://doi.org/10.1016/B978-
analyzing using recent swarm intelligence techniques. Int J 0-12-398296-4.00011-8
Numer Anal Methods Geomech 39:295–309. https://doi. Goh ATC, Fred HK (2003) Neural network approach to model
org/10.1002/nag.2308 the limit state surface for reliability analysis. Can Geotech J
Gandomi M, Mohsen S, Mohammad RZ, Amir HG (2016) 40(2003):1235–1244. https://doi.org/10.1139/T03-056
Prediction of peak ground acceleration of Iran’s tectonic Goh ATC, Goh SH (2007) Support vector machines: their use in
regions using a hybrid soft computing technique. Geosci geotechnical engineering as illustrated using seismic liq-
Front 7(2016):75–82. https://doi.org/10.1016/j.gsf.2014. uefaction data. Comput Geotech 34(2007):410–421.
10.004 https://doi.org/10.1016/j.compgeo.2007.06.001
Garg A, Ankit G, Tai K, Sreedeep S (2014a) An integrated Goh ATC, Wong KS, Broms BB (1995) Estimation of lateral
SRM-multi-gene genetic programming approach for pre- wall movements in braced excavations using neural net-
diction of factor of safety of 3-D soil nailed slopes. Eng works. Can Geotech J 32:1059–1064
Appl Artif Intell 30:30–40. https://doi.org/10.1016/j. Goh ATC, Fred HK, Chua CG (2005) Bayesian neural network
engappai.2013.12.011 analysis of undrained side resistance of drilled shafts.
Garg A, Akhil G, Tai K, Barontini S (2014b) A computational J Geotech Geoenviron Eng 131(1):84–93. https://doi.org/
intelligence-based genetic programming approach for the 10.1061/(ASCE)1090-0241
simulation of soil water retention curves. Transp Porous Goharzay M, Ali N, Ahmadreza MA, Mostafa J (2017) A
Med 2014(103):497–513. https://doi.org/10.1007/s11242- worldwide SPT-based soil liquefaction triggering analysis
014-0313-8 utilizing gene expression programming and Bayesian
Ghaleini EN, Mohammadreza K, Mohammadreza M, Mehdi probabilistic method. J Rock Mech Geotech Eng
ES, Edy TM, Behrouz G (2019) A combination of artificial 9(2017):683–693. https://doi.org/10.1016/j.jrmge.2017.
bee colony and neural network for approximating the 03.011
safety factor of retaining walls. Eng Comput 35:647–658. Gohl ATC (1995) Modeling soil correlations using neural net-
https://doi.org/10.1007/s00366-018-0625-3 works. J Comput Civil Eng 9(4):275–278
Ghodrati A, Ata AA (2016) Artificial neural networks for Gokceoglu C (2002) A fuzzy triangular chart to predict the
modeling shear modulus and damping behavior of gravelly uniaxial compressive strength of the Ankara agglomerates
from their petrographic composition. Eng Geol 66:39–51

123
Geotech Geol Eng

Gokceoglu C, Kivanc Z (2004) A fuzzy model to predict the methods. Eng Comput. https://doi.org/10.1007/s00366-
uniaxial compressive strength and the modulus of elasticity 018-00699-5
of a problematic rock. Eng Appl Artif Intell Hamidi JK, Kourosh S, Bahram R, Hadi B (2010) Application of
17(2004):61–72. https://doi.org/10.1016/j.engappai.2003. Fuzzy set theory to rock engineering classification systems:
11.006 an illustration of the rock mass excavability index. Rock
Goktepe AB, Altun S, Sezer A (2005) Soil clustering by fuzzy Mech Rock Eng 43:335–350. https://doi.org/10.1007/
c-means algorithm. Adv Eng Softw 36(2005):691–698. s00603-009-0029-1
https://doi.org/10.1016/j.advengsoft.2005.01.008 Hanna AM, George M, Mary H (2004) Efficiency of pile groups
Gomes CA, Cortez P, Tinoco J, Marques R (2013) Artificial installed in cohesionless soil using artificial neural net-
intelligence applications in transportation geotechnics. works. Can Geotech J 41(2004):1241–1249. https://doi.
Geotech Geol Eng 31:861–879. https://doi.org/10.1007/ org/10.1139/T04-050
s10706-012-9585-3 Hanna AM, Derin U, Gokhan S (2007) Evaluation of liquefac-
Gong W, Lei W, Sara K, Juang CH, Hongwei H, Jie Z (2014) tion potential of soil deposits using artificial neural net-
Robust geotechnical design of earth slopes using fuzzy works. Eng Comput 24(1):5–16. https://doi.org/10.1108/
sets. J Geot Geoenviron Eng 2014(04014084):1–9. https:// 02644400710718547
doi.org/10.1061/(ASCE)GT.1943-5606.0001196 Harandizadeh H, Toufigh MM, Toufigh V (2018) Different
Gonos IF, Ioannis AS (2005) Estimation of multilayer soil neural networks and modal tree method for predicting
parameters using genetic algorithms. IEEE Trans Power ultimate bearing capacity of piles. Int J Optim Civil Eng
Deliv 20(1):100–106. https://doi.org/10.1109/TPWRD. 8(2):311–328
2004.836833 Hashash YMA, Jung S, Ghaboussi J (2004) Numerical imple-
Gopalakrishnan KL, Halil C (2009) Adaptive neuro-fuzzy mentation of a neural network based material model in
inference system-based backcalculation approach to air- finite element analysis. Int J Numer Methods Eng
port pavement structural analysis. In: Geotechnical/mate- 59:989–1005. https://doi.org/10.1002/nme.905
rials engineering conference presentations and proceedings Hashemi SM, Iraj R (2018) Numerical comparison of the per-
Gordan B, Danial JA, Mohsen H, Msoud M (2016) Prediction of formance of genetic algorithm and particle swarm opti-
seismic slope stability through combination of particle mization in excavations. Civil Eng J 4(9):2186–2196.
swarm optimization and neural network. Eng Comput https://doi.org/10.28991/cej-03091149
32:85–97. https://doi.org/10.1007/s00366-015-0400-7 Heidaripanah A, Mojtaba N, Fazlollah S (2016) Prediction of
Gordan B, Mohammadreza K, Clementking A, Hossein T, Edy resilient modulus of lime-treated subgrade soil using dif-
TM (2018) Estimating and optimizing safety factors of ferent kernels of support vector machine. Int J Geomech
retaining wall through neural network and bee colony 06016020:1–6. https://doi.org/10.1061/(ASCE)GM.1943-
techniques. Eng Comput 2018:1–10. https://doi.org/10. 5622.0000723
1007/s00366-018-0642-2 Himanshu N, Burman A (2018) determination of critical failure
Güllü H (2013) On the prediction of shear wave velocity at local surface of slopes using particle swarm optimization tech-
site of strong ground motion stations: an application using nique considering seepage and seismic loading. Geotech
artificial intelligence. Bull Earthq Eng 11:969–997. https:// Geol Eng. https://doi.org/10.1007/s10706-018-0683-8
doi.org/10.1007/s10518-013-9425-8 Hsiao ECL, Gordon TCKung, Juang CH, Matt S (2006) Esti-
Güllü H, Halil IF (2017) On the prediction of unconfined mation of wall deflection in braced excavation in clays
compressive strength of silty soil stabilized with bottom using artificial neural networks. GeoCongress, ASCE
ash, jute and steel fibers via artificial intelligence. Geomech Huang ZH, Zhang LL, Cheng SY, Zhang J, Xia XH (2014)
Eng 12(3):441–464. https://doi.org/10.12989/gae.2017.12. Back-analysis and parameter identification for deep exca-
3.441 vation based on pareto multiobjective optimization.
Gupta A, Biswas S, Arora VK (2019) Selection of most suit- J Aerospace Eng A4014007:1–11. https://doi.org/10.1061/
able stabilized/solidified dredged soil to use in highway (ASCE)AS.1943-5525.0000464
subgrade layer construction. J Soft Comput Civil Eng Hussain MS, Ahangar-asr A, Chen Y, Javadi AA (2015) A new
3–1:1–15. https://doi.org/10.22115/SCCE evolutionary approach to geotechnical and geo-environ-
Habibagahi G, Alireza B (2003) A neural network framework mental modelling. Handbook Genetic Programm Appl
for mechanical behavior of unsaturated soils. Can Geotech 19:483–499. https://doi.org/10.1007/978-3-319-20883-1_
J 40(2003):684–693. https://doi.org/10.1139/T03-004 19
Hajihassani M (2013) Tunneling-induced ground movement Hussain S, Noor M, Mujahid K, Zahid UR, Mohammad T
and building damage prediction using hybrid artificial (2016) Comparative analysis of rock mass rating prediction
neural networks, Ph.D. thesis, Universiti Teknologi, using different inductive modeling techniques. Int J Mining
Malaysia Eng Miner Process 5(1):9–15. https://doi.org/10.5923/j.
Hajihassani M, Armaghani DJ, Kalatehjari R (2018) Applica- mining.20160501.02
tions of particle swarm optimization in geotechnical Hussain A, Surendar A, Clementking A, Sujith K, Lubov KI
engineering: a comprehensive review. Geotech Geol Eng (2018) Rock brittleness prediction through two optimiza-
2018(36):705–722. https://doi.org/10.1007/s10706-017- tion algorithms namely particle swarm optimization and
0356-z imperialism competitive algorithm. Eng Comput. https://
Hajihassani M, Kalatehjari R, Marto A, Mohamad H, Khosro- doi.org/10.1007/s00366-018-0648-9
tash M (2019) 3D prediction of tunneling-induced ground Imran SA, Manik B, Sesh C, Musharraf Z, Moeen N (2018)
movements based on a hybrid ANN and empirical Artificial neural network–based intelligent compaction

123
Geotech Geol Eng

analyzer for real-time estimation of subgrade quality. Int J Jeng D-S, Cha DH, Blumenstein M (2003) Application of neural
Geomech 18(6):04018048. https://doi.org/10.1061/ network in civil engineering problems. In: International
(ASCE)GM.1943-5622.0001089 conferences on advances in the internet, processing, sys-
Isik F, Gurkan O (2013) Estimating compaction parameters of tems and interdisciplinary research, Belgrade, Yugoslavia,
fine- and coarse-grained soils by means of artificial neural Griffith University
networks. Environ Earth Sci 69:2287–2297. https://doi. Jeon JK, Rahman MS (2008) Fuzzy neural network models for
org/10.1007/s12665-012-2057-5 geotechnical problems, Final report, RESEARCH PRO-
Ismail A, Jeng D-S (2011) Modelling load–settlement behaviour JECT FHWA/NC/2006-52, North Carolina State
of piles using high-orderneural network (HON-PILE- University
model). Eng Appl Artif Intell 24(2011):813–821. https:// Jianbin Z, Tu J, Shi Y (2010) An ANN model for predicting
doi.org/10.1016/j.engappai.2011.02.008 level ultimate bearing capacity of PHC pipe pile. In: Earth
Jaksa MB, Maier HR, Shahin MA (2008) Future challenges for and space 2010: engineering, science, construction, and
artificial neural network modelling in geotechnical engi- operations in challenging environments, pp 3168–3176,
neering. In: 12th international association for computer ASCE
methods and advances in geomechanics (IACMAG), Goa, Joerg M, Winfried S, Lisa B, Alessandro C, Tom S (2008)
India, pp 1710–1719 Inverse parameter identification technique using PSO
Jan JC, Shih-Lin H, Chi SY, Chern JC (2002) Neural network algorithm applied to geotechnical modeling. J Artif Evol
forecast model in deep excavation. J Comput Civil Eng Appl. https://doi.org/10.1155/2008/574613
2002(16):59–65. https://doi.org/10.1061/ASCE0887- Juang CH, Lee DH, Sheu DH (1992) Mapping slope failure
3801200216:159 potential using fuzzy sets. J Geotech Eng 118(3):475–494
Jana RB, Binayak PM, Everett P (2008) Multiscale Bayesian Juang CH, Chen CJ, Tien Y-M (1999) Appraising cone pene-
neural networks for soil water content estimation. Water tration test based liquefaction resistance evaluation meth-
Resour Res 44:1–16. https://doi.org/10.1029/ ods: artificial neural network approach. Can Geotech J
2008WR006879 36:443–454
Javadi AA, Rezania M (2009) Applications of artificial intelli- Juang CH, Caroline JC, Tao J, Ronald DA (2000) Risk-based
gence and data mining techniques in soil modeling. Geo- liquefaction potential evaluation using standard penetra-
mech Eng 1(1):53–74 tion tests. Can Geotech J 37:195–1208
Javadi AA, Moura M, Asaad F, Alireza A-A (2009) An artificial Juang CH, Ronald DA, Tao J, Caroline JC (2001) Probability-
intelligence based finite element method. ISAST Trans based liquefaction evaluation using shear wave velocity
Comput Intell Syst 1(2):1–7 measurements. In: International conferences on recent
Javadi AA, Faramarzi A, Ahangar-Asr A, Mehravar M (2010) advances in geotechnical earthquake engineering and soil
Finite element analysis of three dimensional shallow dynamics, Vol 20, pp 1–6
foundation using artificial intelligence based constitutive Juang CH, Haiming Y, Der-Her L, Ping-Sien L (2003) Simpli-
model. In: Proceedings of the international conference on fied cone penetration test-based method for evaluating
computing in civil and building engineering, Nottingham liquefaction resistance of soils. J Geotech Geoenviron Eng
University Press 129(1):66–80. https://doi.org/10.1061/(ASCE)1090-
Javadi AA, Ahangar-Asr A, Johari A, Faramarzi A, Toll D 0241(2003)129:1(66)
(2012) Modelling stress–strain and volume change beha- Juwaied NS (2018) Applications of artificial intelligence in
viour of unsaturated soils using an evolutionary based data geotechnical engineering. ARPN J Eng Appl Sci
mining technique, an incremental approach. Eng Appl 13(8):2764–2785
Artif Intell 25(2012):926–933. https://doi.org/10.1016/j. Kalatehjari R, Ahmad SAR, Nazri A, Mohsen H (2014) The
engappai.2012.03.006 contribution of particle swarm optimization to three-di-
Javadi AA, Lireza A-A, Asaad F, Nasim M (2013) An EPR mensional slope stability analysis. Sci World J. https://doi.
approach to the modeling of civil and geotechnical engi- org/10.1155/2014/973093
neering systems. Metaheuristics Water Geotech Transp Kang F, Junjie L (2015) Artificial Bee Colony algorithm opti-
Eng 2013:311–326. https://doi.org/10.1016/B978-0-12- mized support vector regression for system reliability
398296-4.00013-1 analysis of slopes. J Comput Civil Eng 04015040:1–13.
Javdanian H, Biswajeet P (2019) Assessment of earthquake- https://doi.org/10.1061/(ASCE)CP.1943-5487.0000514
induced slope deformation of earth dams using soft com- Kang F, Junjie L, Zhenyue M (2013) An artificial bee colony
puting techniques. Landslides 16:91–103. https://doi.org/ algorithm for locating the critical slip surface in slope
10.1007/s10346-018-1078-x stability analysis. Eng Optim 45(2):207–223. https://doi.
Jebur AA, William A, Rafid MA (2018) Feasibility of an evo- org/10.1080/0305215X.2012.665451
lutionary artificial intelligence (AI) scheme for modelling Kang F, Jing-Shuang L, Yuan W, Junjie L (2016) Extreme
of load settlement response of concrete piles embedded in learning machine-based surrogate model for analyzing
cohesionless soil. Ships Offshore Struct 2018:1–15. https:// system reliability of soil slopes. Eur J Environ Civil Eng
doi.org/10.1080/17445302.2018.1447746 2016:1–22. https://doi.org/10.1080/19648189.2016.
Jellali B, Wissem F (2017) Constrained particle swarm opti- 1169225
mization algorithm applied to slope stability. Int J Geo- Kanungo DP, Shaifaly S, Anindya P (2014) Artificial Neural
mech 17(12):06017022. https://doi.org/10.1061/ Network (ANN) and Regression Tree (CART) applications
(ASCE)GM.1943-5622.0001019 for the indirect estimation of unsaturated soil shear strength

123
Geotech Geol Eng

parameters. Front Earth Sci 8(3):439–456. https://doi.org/ Khandelwal M, Aminaton M, Seyed AF, Mahyar G, Danial JA,
10.1007/s11707-014-0416-0 Singh TN, Omid T (2018) Implementing an ANN model
Kashani AR, Amir HG, Mehdi M (2016) Imperialistic com- optimized by genetic algorithm for estimating cohesion of
petitive algorithm: a metaheuristic algorithm for locating limestone samples. Eng Comput 2018(34):307–317.
the critical slip surface in 2-Dimensional soil slopes. https://doi.org/10.1007/s00366-017-0541-y
Geosci Front 7(2016):83–89. https://doi.org/10.1016/j.gsf. Khudier AS (2018) Prediction of bearing capacity for soils in
2014.11.005 Basrah City using artificial neural network (ANN) and
Kaunda R (2014) New artificial neural networks for true triaxial multilinear regression (MLR) Models. Int J Civil Eng
stress state analysis and demonstration of intermediate Technol 9(4):853–864
principal stress effects on intact rock strength. J Rock Mech Khuntia S (2014) Modelling of geotechnical problems using soft
Geotech Eng 6(2014):338–347. https://doi.org/10.1016/j. computing, M.Sc. thesis, National Institute of Technology,
jrmge.2014.04.008 Rourkela
Kaya Z (2015) Predicting liquefaction-induced lateral spreading Kiefa MAA (1998) General regression neural networks for
by using neural network and neuro-Fuzzy techniques. Int J driven piles in cohesionless soils. J Geouch Geoenviron
Geomech 04015095:1–14. https://doi.org/10.1061/ Eng 124(12):1177–1185
(ASCE)GM.1943-5622.0000607 Kisi O, Mustafa T, Mohammad ZK (2015) Modeling soil tem-
Kaya T, Kenan G, Ali EB (2012) Landslide stability analysis peratures at different depths by using three different neural
based on artificial neural networks. In: Istanbul Interna- computing techniques. Theor Appl Climatol 121:377–387.
tional Geophysical Conference and Oil and Gas Exhibition, https://doi.org/10.1007/s00704-014-1232-x
Istanbul,Turkey. http://library.seg.org/ Koelewijn AR, André AMJ (2008) Geobrain: Dutch feasibility
Kayadelen C (2008) Estimation of effective stress parameter of database for installing sheet pile walls. In: Sixth interna-
unsaturated soils by using artificial neural networks. Int J tional conference on case histories in geotechnical engi-
Numer Anal Meth Geomech 32:1087–1106. https://doi. neering, http://scholarsmine.mst.edu/icchge/6icchge/
org/10.1002/nag.660 session11b/5, Scholars’ Mine
Khajehzadeh M, Mohd RT, El-S A, Mabdiyeh E (2010) Eco- Kohestani VR, Hassanlourad M (2015) Modeling the mechan-
nomic design of retaining wall using particle Swarm opti- ical behavior of carbonate sands using artificial neural
mization with passive congregation. Austr J Basic Appl Sci networks and support vector machines. Int J Geomech
4(11):5500–5507 16(1):04015038. https://doi.org/10.1061/(ASCE)GM.
Khajehzadeh M, Mohd RT, Ahmed E-S, Mahdiyeh E (2011) 1943-5622.0000509
Modified particle swarm optimization for optimum design Kohestani VR, Hassanlourad M, Ardakani A (2015) Evaluation
of spread footing and retaining wall. J Zhejiang Univ-Sci A of liquefaction potential based on CPT data using random
12(6):415–427. https://doi.org/10.1631/jzus.A1000252 forest. Nat Hazards 79:1079–1089. https://doi.org/10.
Khamesi H, Seyed RT, Hossein M-N, Zakarya G (2014) 1007/s11069-015-1893-5
Improving the performance of intelligent back analysis for Kolay PK, Rosmina AB, Ling NW (2008) Settlement Prediction
tunneling using optimized fuzzy systems: case study of the of Tropical Soft Soil by Artificial Neural Network (ANN).
karaj subway line 2 in Iran. J Comput Civil Eng In: 12th international association for computer methods
05014010:1–12. https://doi.org/10.1061/(ASCE)CP.1943- and advances in geomechanics (IACMAG), Goa, India,
5487.0000421 pp 1843–1849
Khan N, Vijaya RB, Reddy AM, Kumar MTP (2015) A state-of- Kolay PK, Rosmina AB, Shirley Y (2011) Prediction of com-
the-art review on stability analysis of slopes using fuzzy pression index for tropical soil by using Artificial Neural
logic approach. Int J Emerg Technol Adv Eng Network (ANN). In: 13th international conference of the
5(4):148–151 IACMAG 2011–Melbourne, Australia, pp 542–547
Khan SZ, Shakti S, Pavani M, Das SK (2016) Prediction of the Koopialipoor M, Ahmad F, Ebrahim NG, Mohammadreza M,
residual strength of clay using functional networks. Geosci Danial JA (2019a) Development of a new hybrid ANN for
Front 7(2016):67–74. https://doi.org/10.1016/j.gsf.2014. solving a geotechnical problem related to tunnel boring
12.008 machine performance. Eng Comput 2019:1–13. https://doi.
Khan M, Mohammad T, Hazi MA, Azamathulla I, Noor M org/10.1007/s00366-019-00701-8
(2017) Genetic functions-based modelling for pier scour Koopialipoor M, Bhatawdekar RM, Ahmadreza H, Danial JA,
depth prediction in coarse bed streams. Proc Inst Civil Eng. Behrouz G, Edy TM (2019b) The use of new intelligent
https://doi.org/10.1680/jwama.15.00075 techniques in designing retaining walls. Eng Comput.
Khandelwal M (2011) Prediction of thermal conductivity of https://doi.org/10.1007/s00366-018-00700-1
rocks by soft computing. Int J Earth Sci 100:1383–1389. Kordjazi A, Nejad FP, Jaksa MB (2014) Prediction of ultimate
https://doi.org/10.1007/s00531-010-0550-1 axial load-carrying capacity of piles using a support vector
Khandelwal M, Singh TN (2009) Prediction of blast-induced machine based on CPT data. Comput Geotech
ground vibration using artificial neural network. Int J Rock 55(2014):91–102. https://doi.org/10.1016/j.compgeo.
Mech Min Sci 46(2009):1214–1222. https://doi.org/10. 2013.08.001
1016/j.ijrmms.2009.03.004 Kordjazi A, Nejad FP, Jaksa MB (2015) The evaluation of
Khandelwal M, Kumar DL, Mohan Y (2011) Application of soft ultimate axial-loading capacity of piles using artificial
computing to predict blast-induced ground vibration. Eng intelligence methods. Geotech Eng Infrastruct Dev. https://
Comput 27:117–125. https://doi.org/10.1007/s00366-009- doi.org/10.1680/ecsmge.60678
0157-y

123
Geotech Geol Eng

Kordnaeij A, Farzin K, Behrouz K, Hossein M-A (2015) Pre- Numer Anal Meth Geomech 2008(32):189–213. https://
diction of recompression index using GMDH-type neural doi.org/10.1002/nag.614
network based on geotechnical soil properties. Soils Found Li SL, Yingxi L (2004) Intelligent forecast procedures for slope
55(6):1335–1345. https://doi.org/10.1016/j.sandf.2015.10. stability with evolutionary artificial neural network. In:
001 International symposium on neural networks Dalian,
Kostic S, Nebojša V, Kristina T, Andreja S (2016) Application China, pp 792–798, Springer
of artificial neural networks for slope stability analysis in Li Z, Donna R, Nancy H, Lori S (2006) Using geostatistics and
geotechnical practice. In: 13th symposium on neural net- artificial neural networks to determine the location of a
works and applications (NEUREL), SAVA Center, Bel- contaminant source. In: GeoCongress 2006, ASCE
grade, Serbia, 1-6, 978-1-5090-1530-6/16, IEEE Li L, Hi-bao L, Xue-song C, Guang-ming Y (2009) A combi-
Kumar MP, Sarat KD (2015) Model uncertainty o fSPT-based natorial search method based on harmony search algorithm
method for evaluation of seismic soil liquefaction potential and particle swarm optimization in slope stability analysis.
using multi-gene genetic programming. Soils Found In: IEEE 2009 international conference on computational
55(2):258–275. https://doi.org/10.1016/j.sandf.2015.02. intelligence and software engineering-Wuhan, China,
003 pp 978-1-4244-4507-3/09, IEEE
Kumar V, Kumar V, Yeetendra K (2012) Liquefaction potential Li Y-C, Yun-Min C, Tony LYZ, Dao-Sheng L, Peter JC (2010)
evaluation of alluvial soil by neuro-Fuzzy technique. Int J An efficient approach for locating the critical slip surface in
Emerg Technol Adv Eng 2(3):174–184 slope stability analyses using a realcoded genetic algo-
Kumar P, Muduli, Sarat KD (2015) Evaluation of liquefaction rithm. Can Geotech J 47(2010):806–820. https://doi.org/
potential of soil based on shearwave velocity using multi- 10.1139/T09-124
gene genetic programming. Handbook Genetic Programm Li H, Junjie L, Fei K (2011a) Risk analysis of dam based on
Appl 12:309–343. https://doi.org/10.1007/978-3-319- artificial bee colony algorithm with fuzzy c-means clus-
20883-1_12 tering. Can J Civil Eng 38(2011):483–492. https://doi.org/
Kurek J, Michał K, Piotr B, Oguz A, Simon R, Grzegorz W 10.1139/L11-020
(2015) The application of ensemble classification tech- Li R, Xianfeng S, Zheng D, Ming P (2011) Using Fuzzy
niques in soil classification system on the basis of dmt and approach to build a continuous relationship between SCS
cpt data. In: 3rd international conference on artificial curve number and soil properties. In: 9th international
intelligence and computer science (AICS2015), Penang, conference on geoinformatics, 24–26 June 2011, Shanghai,
MALAYSIA, 38-45, e-ISBN 978-967-0792-06-4 China, https://doi.org/10.1109/geoinformatics.2011.
Kurup PU, Dudani NK (2001) CPT evaluation of liquefaction 5980785, IEEE
potential using neural networks. Int Confer Recent Adv Li H, Hong Z, Zuwen Y, Xuedong Z (2012) Particle Swarm
Geotech Earthq Eng Soil Dyn 28:1–6 optimization algorithm coupled with finite element limit
Kurup PU, Erin PG (2006) Prediction of soil composition from equilibrium method for geotechnical practices. Math
CPT data using general regression neural network. J Com- Problems Eng. https://doi.org/10.1155/2012/498690
put Civil Eng 20:281–289. https://doi.org/10.1061/ Li AI, Khoo SY, Wang Y, Lyamin AY (2014) Application of
ASCE0887-3801200620:4281 neural network to rock slope stability assessments. In:
Kurup PU, Nitin KD (2002) Neural networks for profiling stress Proceedings of the 8th European conference on numerical
history of clays from PCPT data. J Geotechn Geoenviron methods in geotechnical engineering, Delft, The Nether-
Eng 128(7):569–579. https://doi.org/10.1061/ lands, pp 473–478, Taylor & Francis Group
(ASCE)1090-0241(2002)128:7(569) Li G, Zhiqiang Y, Qian G, Shuhua Z (2014b) Rock mass con-
Lai J, Junling Q, Zhihua F, Jianxun C, Haobo F (2016) Predic- stitutive model identification based on artificial intelli-
tion of soil deformation in tunnelling using artificial neural gence technology. EJGE 19:875–886
networks. Comput Intell Neurosci. https://doi.org/10.1155/ Liang M, Edy TM, Roohollah SF, Saber G, Liang M (2016)
2016/6708183 Rock strength assessment based on regression tree tech-
Lee C-Y, Shuh-Gi C (2013) Application of a support vector nique. Eng Comput 32:343–354. https://doi.org/10.1007/
machine for liquefaction assessment. J Mar Sci Technol s00366-015-0429-7
21(3):318–324. https://doi.org/10.6119/JMST-012-0518-3 Lin P, Xiaoli L, Hong-Xin C, Jinxie K (2014) Ant Colony
Lee T-L, Hung-ming L, Yuh-pin L (2009) Assessment of optimization analysis on overall stability of high arch dam
highway slope failure using neural networks. J Zhejiang basis of field monitoring. Sci World J 483243:1–15. https://
Univ Sci A 10(1):101–108 doi.org/10.1155/2014/483243
Lee Y-F, Yun-Yao C, Juang CH, Der-Her L (2012) Reliability Liu J, Guangyue W, Ying C (2008) Research and application of
analysis of rock wedge stability: knowledge-based clus- GA neural network model on dam displacement forecast-
tered partitioning approach. J Geotech Geoenviron Eng ing. In: 11th ASCE aerospace division international con-
2012(138):700–708. https://doi.org/10.1061/(ASCE)GT. ference (Earth and Space 2008) Long Beach, CA, USA,
1943-5606.0000618 ASCE
Leu S-S, Hsien-Chuang L (2004) Neural-network-based Liu Z, Jianfu S, Weiya X, Fei X (2013) Comprehensive stability
regression model of ground surface settlement induced by evaluation of rock slope using the cloud model-based
deep excavation. Autom Constr 13(2004):279–289. https:// approach. Rock Mech Rock Eng 2013:46. https://doi.org/
doi.org/10.1016/S0926-5805(03)00018-9 10.1007/s00603-013-0507-3
Levasseur S, Malecot Y, Boulon M, Flavigny E (2008) Soil Liu Z, Jianfu S, Weiya X, Chen H, Shi C (2014a) Comparison on
parameter identification using a genetic algorithm. Int J landslide nonlinear displacement analysis and prediction

123
Geotech Geol Eng

with computational intelligence approaches. Landslides investigation and fuzzy regression modeling. Can Geotech
11:889–896. https://doi.org/10.1007/s10346-013-0443-z J 52(2015):868–882. https://doi.org/10.1139/cgj-2013-
Liu Z, Jianfu S, Weiya X, Hongjie C, Yu Z (2014b) An extreme 0297
learning machine approach for slope stability evaluation Martin JC, Toll DG (2006) The development of a knowledge-
and prediction. Nat Hazards 73:787–804. https://doi.org/ based system for the preliminary investigation of contam-
10.1007/s11069-014-1106-7 inated land. Comput Geotech 33(2006):93–107. https://
Long-Yun Z, Zhang Q-Y, Yang S-Y, Chen X-G (2013) Fuzzy doi.org/10.1016/j.compgeo.2006.03.002
optimization method and its application of similar material Martins FF, Randa TFS (2013) Prediction of hard rock TBM
ratio in 3D geo-mechanical model. J Theor Appl Inf penetration rate based on Data Mining techniques. In:
Technol 49(1):331–341 Proceedings of the 18th international conference on soil
Lu P, Rosenbaum MS (2003) Artificial neural networks and grey mechanics and geotechnical engineering, Paris 2013,
systems for the prediction of slope stability. Nat Hazards pp 1751–1754
30(2003):383–398 Martins FF, Tiago FSM (2012) Estimation of the rock defor-
Luo Z, Sez A, Juang CH, Hongwei H, Ping-Sien L (2011) mation modulus and RMR based on data mining tech-
Probability of serviceability failure in a braced excavation niques. Geotech Geol Eng 30:787–801. https://doi.org/10.
in a spatially random field: Fuzzy finite element approach. 1007/s10706-012-9498-1
Comput Geotech 38(2011):1031–1040. https://doi.org/10. Martins FF, Arlindo B, Braga MAS (2012) Prediction of the
1016/j.compgeo.2011.07.009 mechanical behavior of the Oporto granite using Data
Mahdevari S, Seyed RT (2012) Prediction of tunnel conver- Mining techniques. Expert Syst Appl
gence using Artificial Neural Networks. Tunnel Undergr 39(2012):8778–8783. https://doi.org/10.1016/j.eswa.2012.
Space Technol 28(2012):218–228. https://doi.org/10.1016/ 02.003
j.tust.2011.11.002 Marwan A, Meng-Meng Z, Abdelrehim MZ, Günther M (2016)
Mahdevari S, Seyed RT, Masoud M (2012) Application of Optimization of artificial ground freezing in tunneling in
artificial intelligence algorithms in predicting tunnel con- the presence of seepage flow. Comput Geotech
vergence to avoid TBM jamming phenomenon. Int J Rock 75(2016):112–125. https://doi.org/10.1016/j.compgeo.
Mech Min Sci 55(2012):33–44. https://doi.org/10.1016/j. 2016.01.004
ijrmms.2012.06.005 Matmatte L, Jean LF, Reda MB (1997) GDQ-Expert: an expert
Mahdiyar A, Danial JA, Aminaton M, Mehrbakhsh N, Syuhaida system for assessing geotechnical data quality application
I (2018) Rock tensile strength prediction using empirical to the menard pressuremeter test. Geosci Water Resour
and soft computing approaches. Bull Eng Geol Environ. Environ Data Model 2374:244. https://doi.org/10.1007/
https://doi.org/10.1007/s10064-018-1405-4 978-3-642-60627-4
Mahmoud AMH, Ahmed MS (2017) Side resistance assessment Mayoraz LF, Vulliet DL (2002) Neural networks for slope
of drilled shafts socketed into rocks: empirical versus movement prediction. Int J Geomech 2(2):153–173.
artificial intelligence approaches. In: 1st GeoMEast inter- https://doi.org/10.1061/(ASCE)1532-3641(2002)2:2(153)
national congress and exhibition, Egypt, pp 288-302, Mazaheri SA, Koppi AJ, McBratney AB (1995) A fuzzy allo-
10.1007/978-3-319-61642-1_22 cation scheme for the Australian Great Soil Groups Clas-
Maizir H, Khairul AK (2013) Neural network application in sification system. In: Eurcipeun Journul of Soil Science,
prediction of axial bearing capacity of driven piles. In: December 1995, Vol 46, pp 601–612, Blackwell Publishers
International multiconference of engineers and computer Meij R van der (2008) Predicting horizontal deformations
scientists, Vol I, pp 1–5, ISBN: 978-988-19251-8-3 depending on the construction scheme using artificial
Maizir H, Suryanita R (2018) Evaluation of axial pile bearing intelligence. In: Second international workshop on
capacity based on pile driving analyzer (PDA) test using geotechnics of soft soils, Glasgow, Scotland, pp 181–187,
Neural Network. In: The 4th International seminar on ISBN: 978-0-203-88333-4, Taylor & Francis Group
sustainable urban development, pp 1-6, 10.1088/1755- Meij R van der (2008) Predicting Horizontal Deformations
1315/106/1/012037 under an Embankment using an artificial Neural Network.
Maizir H, Nurly G, Khairul AK (2015) Artificial neural network In: 12th international association for computer methods
model for prediction of bearing capacity of driven pile. and advances in geomechanics (IACMAG), Goa, India,
Jurnal Teknik Sipil 22(1):49–56 pp 1787–1794
Maizir H, Reni S, Hendra J (2016) Estimation of pile bearing Meij R van der (2008) Quickly and accurately predicting hori-
capacity of single driven pile in sandy soil using finite zontal deformations under an embankment using an Arti-
element and artificial neural network methods. In: Inter- ficial Neural Network. In: 12th international association for
national conference on engineering and technology, com- computer methods and advances in geomechanics (IAC-
puter, basic and applied sciences ECBA, 2016, Osaka, MAG), Goa, India
Japan, ISBN 978-969-670-466-9 Melchiorre C, Matteucci M, Azzoni A, Zanchi A (2008) Arti-
Maji VB, Sitharam TG (2008) Prediction of elastic modulus of ficial neural networks and cluster analysis in landslide
jointed rock mass using artificial neural networks. Geotech susceptibility zonation. Geomorphology
Geol Eng 2008(26):443–452. https://doi.org/10.1007/ 94(2008):379–400. https://doi.org/10.1016/j.geomorph.
s10706-008-9180-9 2006.10.035
Markou IN, Dimitrios NC, Papadopoulos BK (2015) Penetra- Meng L, Zhang S (2013) A new Ant Colony algorithm for finite
bility of microfine cement grouts: experimental element analysis. Appl Mech Mater 299(2013):121–124.
https://doi.org/10.4028/www.scientific.net/AMM.299.121

123
Geotech Geol Eng

Mens AMJ, van Tol AF, Koelewijn AR (2008) Optimizing Mishra AK, Kumar B, Dutta J (2016) DRC-12-23-S4Prediction
foundation engineering, validating models against experi- of hydraulic conductivity of soil bentonite mixture using
ence using artificial intelligence. In: 12th international hybrid-ANN approach. J Environ Inf 27(2):98–105. https://
association for computer methods and advances in doi.org/10.3808/jei.201500292
geomechanics (IACMAG), Goa, India, pp 3384–3391 Moayedi H, Abbas R (2019) An artificial neural network
Meyer S (1992) Preliminary foundation design using EDESYN. approach for under-reamed piles subjected to uplift forces
Optim Artif Intell Civil Struct Eng 2:333–354 in dry sand. Neural Comput Appl 31:327–336. https://doi.
Mikaeil R, Sina SH, Seyed HH (2018) Rock penetrability org/10.1007/s00521-017-2990-z
classification using artificial Bee Colony (ABC) algorithm Moayedi H, Danial JA (2018) Optimizing an ANN model with
and self-organizing map. Geotech Geol Eng ICA for estimating bearing capacity of driven pile in
36:1309–1318. https://doi.org/10.1007/s10706-017-0394- cohesionless soil. Eng Comput 34:347–356. https://doi.
6 org/10.1007/s00366-017-0545-7
Milad F, Tawfiq K, Hataf N, Ozguven EE (2015) New method Moayedi H, Sajad H (2017) Artificial intelligence design charts
for predicting the ultimate bearing capacity of driven piles for predicting friction capacity of driven pile in clay.
by using flap number. KSCE J Civil Eng 19(3):611–620. Neural Comput Appl 2017:1–17. https://doi.org/10.1007/
https://doi.org/10.1007/s12205-013-0315-z s00521-018-3555-5
Miranda T (2007) Geomechanical parameters evaluation in Moayedi H, Sajad H (2018) Applicability of a CPT-based neural
underground structures. Artificial Intelligence, Bayesian network solution in predicting load-settlement responses of
Probabilities and Inverse Methods, Ph.D. thesis, University bored pile. Int J Geomech 18(6):1–11. https://doi.org/10.
of Minho, Portugal 1061/(ASCE)GM.1943-5622.0001125
Miranda T, Luı́s RS (2012) Application of data mining tech- Moayedi H, Mansour M, Ahmad SAR, Wan AWJ, Mohammed
niques for the development of new geomechanical char- AM (2019a) A systematic review and meta-analysis of
acterization models for rock masses. In: Sousa V, artificial neural network application in geotechnical engi-
Fernandes A (eds) Innovative numerical modeling in 832 neering: theory and applications. Neural Comput Appl
geomechanics, CRC Press, London, pp 245-264 2019:1–24. https://doi.org/10.1007/s00521-019-04109-9
Miranda T, Gomes C, Ribeiroe ASL (2004) Use of AI tech- Moayedi H, Mehdi R, Abolhasan S, Wan AWJ, Ahmad SAR
niques and updating in geomechanical characterisation. In: (2019b) Optimization of ANFIS with GA and PSO esti-
Course on geomechanical parameter evaluation in rock mating a ratio in driven piles. Eng Comput 2019:1–12.
engineering practice, research project POCI/ECM/57495/ https://doi.org/10.1007/s00366-018-00694-w
2004, entitled Geotechnical Risk in Tunnels for High Mobarra Y, Alireza H, Mohammadali R (2013) Application of
Speed Trains artificial neural networks to the prediction of TBM pene-
Miranda T, António GC, Luı́s RS (2008) Development of new tration rate in TBM-driven golab water transfer tunnel. In:
models for geomechanical characterisation using data International conference on civil engineering architecture
mining techniques. In: Geomechanik und Tunnelbau 1, and urban sustainable development 2013, Tabriz, Iran
Heft, vol 5, pp 328–334, 10.1002/geot.200800032 Mohamad ET, Armaghani DJ, Momeni E, Yazdavar AH,
Miranda T, Lino C, António GC, Luı́s RS (2009) Back analysis Ebrahimi M (2018) Rock strength estimation: a PSO-based
of geomechanical parameters using classical and artificial BP approach. Neural Comput Appl 2018(30):1635–1646.
intelligence techniques. In: Congreso de Métodos https://doi.org/10.1007/s00521-016-2728-3
Numéricos en Ingenierı́a 2009, Barcelona, SEMNI Mohamadnejad M, Gholami R, Ataei M (2012) Comparison of
Miranda T, Dias D, Eclaircy-Caudron S, Gomes Correia A, intelligence science techniques and empirical methods for
Costa L (2011a) Back analysis of geomechanical parame- prediction of blasting vibrations. Tunnel Undergr Space
ters by optimisation of a 3D model of an underground Technol 28(2012):238–244. https://doi.org/10.1016/j.tust.
structure. Tunnel Undergr Space Technol 2011.12.001
26(2011):659–673. https://doi.org/10.1016/j.tust.2011.05. Mohammadzadeh SD, Jafar BB, Amir AH (2014) An evolu-
010 tionary computational approach for formulation of com-
Miranda T, António GC, Manuel S, Luı́s RS, Paulo C (2011b) pression index of fine-grained soils. Eng Appl Artif Intell
New models for strength and deformability parameter 33(2014):58–68. https://doi.org/10.1016/j.engappai.2014.
calculation in rock masses using data-mining techniques. 03.012
Int J Geomech 11:44–58. https://doi.org/10.1061/ Mohammadzadeh SD, Jafar BB, Yazd SHVJ, Amir HA (2016)
ASCEGM.1943-5622.0000071 Deriving an intelligent model for soil compression index
Miranda T, Sousa LR, Ruggenthen W, Sousa RL (2013) utilizing multi-gene genetic programming. Environ Earth
Application of data mining techniques for the development Sci 75:1–11. https://doi.org/10.1007/s12665-015-4889-2
of new rock mechanics constitutive models. Const Model Mohammadzadeh D, Seyed-Farzan K, Amir M (2019) Evolu-
Geomater Adv New Appl. https://doi.org/10.1007/978-3- tionary prediction model for fine-grained soils compression
642-32814-5 index using gene-expression programming. https://doi.org/
Miranda T, Sousa LR, Gomes AT, Tinoco J, Ferreira C (2018) 10.20944/preprints201903.0049.v1, QUTePrints
Geomechanical characterization of volcanic rocks using Mohanty R, Sarat KD (2018) Settlement of shallow foundations
empirical systems and data mining techniques. J Rock on cohesionless soils based on SPT value using multi-ob-
Mech Geotech Eng 10:138–150. https://doi.org/10.1016/j. jective feature selection. Geotech Geol Eng 36:3499–3509.
jrmge.2017.11.003 https://doi.org/10.1007/s10706-018-0549-0

123
Geotech Geol Eng

Mokhtar M, Mahmoud B (2018) Comparison of LLNF, ANN, using multi-gene genetic programming. In: Georisk:
and COA-ANN techniques in modeling the uniaxial com- assessment and management of risk for engineered systems
pressive strength and static Young s modulus of limestone and geohazards, vol 8, no 1, pp 14–28, https://doi.org/10.
of the Dalan formation. Nat Resour Res 28(1):223–239. 1080/17499518.2013.845720
https://doi.org/10.1007/s11053-018-9383-6 Muduli PK, Manas RD, Sarat KD, Swagatika S (2015) Lateral
Mollahasani A, Amir HA, Amir HG, Azadeh R (2011) Non- load capacity of piles in clay using genetic programming
linear neural-based modeling of soil cohesion intercept. and multivariate adaptive regression spline. Indian Geo-
KSCE J Civil Eng 15(5):831–840. https://doi.org/10.1007/ tech J 45(3):349–359. https://doi.org/10.1007/s40098-014-
s12205-011-1154-4 0142-2
Momeni E, Nazir R, Armaghani DJ, Maizir H (2014a) Predic- Muhamedyev RI, Kuchin YI, Muhamedyeva EL (2012) Geo-
tion of pile bearing capacity using a hybrid genetic algo- physical research of boreholes: artificial neural networks
rithm-based ANN. Measurement 57(2014):122–131. data analysis. In: SCIS-ISIS 2012, Kobe, Japan,
https://doi.org/10.1016/j.measurement.2014.08.007 pp 825–829, IEEE
Momeni E, Danial JA, Mohsen H, Mohd FMA (2014b) Pre- Mullarkey PW, Steven JF (1986) Fuzzy logic in a geotechnical
diction of uniaxial compressive strength of rock samples knowledge-based system:CONE. Civil Eng Syst
using hybrid particle Swarm optimization-based artificial 3(2):58–81. https://doi.org/10.1080/02630258608970429
neural networks. Measurement. https://doi.org/10.1016/j. Nadiri AA, Nima C, Frank T-C, Asghar AM (2014) Bayesian
measurement.2014.09.075 artificial intelligence model averaging for hydraulic con-
Momeni E, Ramli N, Danial JA, Harnedi M (2015a) Application ductivity estimation. J Hydrol Eng 2014(19):520–532.
of artificial neural network for predicting shaft and tip https://doi.org/10.1061/(ASCE)HE.1943-5584.0000824
resistances of concrete piles. Eart Sci Res J 19(1):85–93. Najjar YM, Imad AB, Hossam E, Richard LM (1999) Charac-
https://doi.org/10.15446/esrj.v19n1.38712 terizing the swelling potential of soils via neuro-reliability
Momeni E, Ramli N, Danial JA, Mohd FMA, Edy TM (2015b) approach. In: Intelligent engineering systems through
Prediction of unconfined compressive strength of rocks: a artificial neural networks (ANNIE), Vol 9, pp 1201–1206
review paper. Jurnal Teknologi Sci Eng 77(11):43–50 Nakhaee M, Ali L (2013) Genetic-based modeling of undrained
Momeni E, Danial JA, Seyed AF, Ramli N (2017) Prediction of lateral load capacity of piles in cohesion soil. Global J Sci
bearing capacity of thin-walled foundation:a simulation Eng Technol 5:123–133
approach. Eng Comput. https://doi.org/10.1007/s00366- Nama S, Apu KS, Sima G (2015) Parameters optimization of
017-0542-x geotechnical problem using different optimization algo-
Moosazadeh S, Namazi E, Aghababaei H, Marto A, Mohamad rithm. Geotech Geol Eng 33:1235–1253. https://doi.org/
H, Hajihassani M (2017) Prediction of building damage 10.1007/s10706-015-9898-0
induced by tunnelling through an optimized artificial Namdarvand FN, Alireza J, Gholamabbas S (2013) Estimation
neural network. Eng Comput. https://doi.org/10.1007/ of soil compression coefficient using artificial neural net-
s00366-018-0615-5 work and multiple regressions. Int Res J Appl Basic Sci
Moreshwar ZP (2012) Applications of artificial neural networks 4(10):3232–3236
in civil engineering. Seminar Report, Civil Engineering Narendra BS, Sivapullaiah PV, Suresh S, Omkar SN (2006)
Department, Sinhgad Academy of Engineering, Pune Prediction of unconfined compressive strength of soft
Mosallanezhad M, Hossein M (2017) Developing hybrid arti- grounds using computational intelligence techniques: a
ficial neural network model for predicting uplift resistance comparative study. Comput Geotech 33(2006):196–208.
of screw piles. Arab J Geosci 10(479):1–10. https://doi.org/ https://doi.org/10.1016/j.compgeo.2006.03.006
10.1007/s12517-017-3285-5 Nassr A, Mahzad E-F, Hooshang K, Akbar J (2018) A new
Motamedi S, Shahaboddin S, Dalibor P, Roslan H (2015) approach to modeling the behavior of frozen soils. Eng
Application of adaptive neuro-fuzzy technique to predict Geol. https://doi.org/10.1016/j.enggeo.2018.09.018
the unconfined compressive strength of PVA-Sand-Ce- Nawari NO, Liang R (2000) Intelligent hybrid system for the
ment mixture. Powder Technol. https://doi.org/10.1016/j. design of pile foundations. In: ASCE geotechnical special
powtec.2015.02.045 publication, Issue Number: 100, New technological and
Muduli PK, Arat KD (2014) First-order reliability method for design developments in deep foundations, pp 312-326,
probabilistic evaluation of liquefaction potential of soil ISBN: 0784405115, ASCE
using genetic programming. Int J Geomech 15(3):1–16. Nawari NO, Liang DR (2000b) Fuzzy-based approach for
https://doi.org/10.1061/(ASCE)GM.1943-5622.0000377 determination of characteristic values of measured
Muduli PK, Sarat KD (2014) Evaluation of liquefaction poten- geotechnical parameters. Can Geotech J 37:1131–1140
tial of soil based on standard penetration test using multi- Nazir R, Ehsan M, Kadir M, Harnedi M (2015) An artificial
gene genetic programming model. Acta Geophys neural network approach for prediction of bearing capacity
62(3):529–543. https://doi.org/10.2478/s11600-013-0181- of spread foundations in sand. Jurnal Teknologi Sci Eng
6 72(3):9–14
Muduli PK, Manas RD, Sarat KD, Swagatika S (2013) Predic- Neaupane KM, Shiva HA, Mongkut P (2008) Landslide hazard
tion of lateral load capacity of piles using extreme learning assessment: a qualitative and a knowledge-based tech-
machine. Int J Geotech Eng 7(4):388–394. https://doi.org/ nique. In: Geocongress 2008: characterization, monitoring,
10.1179/1938636213Z.00000000041 and, modeling of geosystems, pp 870–877, ASCE
Muduli PK, Sarat KD, Subhamoy B (2014) CPT-based proba- Negara A, Syed A, Ali A, Hasan K, Asok N, Zahra A, Baker H
bilistic evaluation of seismic soil liquefaction potential (2018) Utilizing artificial intelligence techniques for

123
Geotech Geol Eng

predicting rock failure parameters. In: SPE-192340-MS, 5(2013):325–329. https://doi.org/10.1016/j.jrmge.2013.


SPE Kingdom of Saudi Arabia annual technical sympo- 05.006
sium and exhibition held in Dammam, Saudi Arabia, Ozcep F, Eray Y, Okan T, Metin A, Savas K (2010) Correlation
pp 23–26 between electrical resistivity and soil-water content based
Nejad FP, Jaksa MB (2011) Prediction of pile behavior using artificial intelligent techniques. Int J Phys Sci 5(1):47–56
artificial neural networks based on standard penetration test Pal M (2011) Modelling pile capacity using generalised
data. In: 13th international conference of the IACMAG regression neural network. In: Indian Geotechnical Con-
2011–Melbourne, Australia, pp 564–569 ference December 15-17, 2011, Kochi
Nejad FP, Mark BJ (2010) Prediction of pile settlement using Pal M, Surinder D (2008) Modeling pile capacity using support
artificial neural networks based on cone penetration test vector machines and generalized regression neural net-
data. In: GeoFlorida 2010: advances in analysis, modeling work. J Geotech Geoenviron Eng 134(7):1021–1024.
and design, (GSP 199), pp. 1432–1441, ASCE https://doi.org/10.1061/ASCE1090-0241
Nhu V-H, Nhat-Duc H, Van-Binh D, Hong-Dang V, Dieu TB Pan LX, Cao MS, Zhang YR, Novak D (2015) Parameter sen-
(2019) A hybrid computational intelligence approach for sitivity analysis of geotechnical engineering system using
predicting soil shear strength for urban housing construc- neural network ensemble. In: International conference on
tion: a case study at Vinhomes Imperia project, Hai Phong artificial intelligence and industrial engineering (AIIE
city (Vietnam). Eng Comput. https://doi.org/10.1007/ 2015), pp 196-199, Atlantis Press
s00366-019-00718-z Pancar EB, Erhan BP (2011) Information systems and artificial
Niu X, Shike Z (2017) Application of artificial intelligence intelligence technology applied in pile design. In: Inter-
inversion for characterization of geotechnical parameters. national conference on advanced computing and commu-
Boletı́n Técnico 55(1):103–110 nication technologies (ACCT 2011), pp 126–131, ISBN:
Nourani V, Ali B (2013) Integration of artificial neural networks 978-981-08-7932-7, RG Education Society
with radial basis function interpolation in earthfill dam Pande GN, Hyu-Soung S (2004) Artificial intelligence v.
seepage modeling. J Comput Civil Eng 27:183–195. equations. In: Proceedings of ICE civil engineering 157
https://doi.org/10.1061/(ASCE)CP.1943-5487.0000200 February 2004, Paper 13242, 39–42, ICE
Nourani V, Hamid G (2012) Assessment of slope stability in Park HI (2011) Study for application of artificial neural net-
Embankment dams using artificial neural network (case works in geotechnical problems. In: C Leung, P Hui (eds)
study: Zonouz Embankment Dam). In: International jour- Artificial neural networks-application, Chapter 15,
nal of advances in civil engineering and architecture pp 303–336, ISBN: 978-953-307-188-6, InTech
(IJACEA), Vol 1, Issue 1, pp 65–75 Patel AK, Snehamoy C (2016) Computer vision-based lime-
Oberguggenberger M (2003) Fuzzy data in geotechnical mod- stone rock-type classification using probabilistic neural
els. Adv Math Comput Geomech. https://doi.org/10.1007/ network. Geosci Front 7(2016):53–60. https://doi.org/10.
978-3-540-45079-5 1016/j.gsf.2014.10.005
Oberguggenberger M, Wolfgang F (2002) From probability to Pavani M (2014) Application of functional network in
Fuzzy sets: the struggle for meaning in geotechnical risk geotechnical engineering, M.Sc. thesis, National Institute
assessment. In: R Potter, H Klapperich, HF Schweiger of Technology, Rourkela
(eds), Probabilistics in geotechnics: technical and eco- Penumadu D, Rongda Z (2000) Modeling drained triaxial
nomic risk estimation, Verlag Gluckauf GmbH, Essen, compression behavior of sand using ANN. In: GeoDenver
pp 29–38 2000: Numerical methods in geotechnical engineering
Ojo EB, Matawal DS (2014) Application of artificial neural USA, pp 71–87, ASCE
network in monitoring seepage flow through Dadin Kowa Pereira C, Maranha IR, Brito A (2014) Advanced constitutive
dam, Gombe State Nigeria. In: Proceedings of the 8th model calibration using genetic algorithms: some aspects.
European conference on numerical methods in geotechni- In: Proceedings of the 8th European conference on
cal engineering, Delft, The Netherlands, pp 479–483, numerical methods in geotechnical engineering, Delft, The
Taylor & Francis Group Netherlands, pp 485–490, Taylor & Francis Group
Oommen T, Laurie GB (2008) A new approach to liquefaction Pezeshk S, Camp CV, Karprapu S (1996) Geophysical log
potential mapping using satellite remote sensing and sup- interpretation using neural network. J Comput Civil Eng
port vector machine algorithm. In: IGARSS 2008, 10(2):136–142
pp 51–54, IEEE Pham BT, Le HS, Tuan-Anh H, Duc-Manh N, Dieu TB (2018)
Ornek M (2014) Estimation of ultimate loads of eccentric-in- Prediction of shear strength of soft soil using machine
clined loaded strip footings rested on sandy soils. Neural learning methods. CATENA 166(2018):181–191. https://
Comput Appl 25:39–54. https://doi.org/10.1007/s00521- doi.org/10.1016/j.catena.2018.04.004
013-1444-5 Pieczarka K, Katarzyna P, Krzysztof L, Zygmunt O (2018) The
Ornek M, Mustafa L, Ahmet D, Abdulazim Y (2012) Prediction use of artificial intelligence methods for optimization of
of bearing capacity of circular footings on soft clay stabi- tractive properties on Silty Clay Loam. J Res Appl Agric
lized with granular soil. Soils Found 52(1):69–80. https:// Eng 63(1):63–68
doi.org/10.1016/j.sandf.2012.01.002 Pirnia P, François D, Javad M (2018) Machine learning algo-
Ozbeka A, Mehmet U, Aydin D (2013) Estimating uniaxial rithms for applications in geotechnical engineering. In:
compressive strength of rocks using genetic expression Geo Edmonton, pp 1–7
programming. J Rock Mech Geotechnica Eng

123
Geotech Geol Eng

Pramanik R, Dilip KB, Nirjhar D (2019) Fuzzy reliability advances in geo-environmental engineering, geomechan-
analysis for elastic settlement of surface footing. In: Geo- ics and geotechnics, and geohazards, advances in science,
Congress 2019 GSP 313, pp 183–192, ASCE technology and innovation, pp 165–167, 10.1007/978-3-
Prasad MA, Giridhar MVSS (2014) Fuzzy logic simulation for 030-01665-4_39
ground water recharge estimation using soil water balance Rashidian V, Hassanlourad M (2014) Application of an artificial
method. Res Revol III(2): 51–56 neural network for modeling the mechanical behavior of
Prayogo D, Yudas TTS (2018) Optimizing the prediction carbonate soils. Int J Geomech 14(1):142–150. https://doi.
accuracy of friction capacity of driven piles in cohesive soil org/10.1061/(ASCE)GM.1943-5622.0000299
using a novel self-tuning least squares support vector Ravandi EG, Reza R, Amir EFM, Esmaeil GR (2013) Appli-
machine. Adv Civil Eng. https://doi.org/10.1155/2018/ cation of numerical modeling and genetic programming to
6490169 estimate rock mass modulus of deformation. Int J Min Sci
Provenzano P (2003) A Fuzzy-neural network method for Technol 23(2013):733–737. https://doi.org/10.1016/j.
modeling uncertainties in soil-structure interaction prob- ijmst.2013.08.018
lems. Comput-Aided Civil Infrastruct Eng 18:391–411 Rezaeeian A, Mohammad D, Mohammad KJ (2018) Determi-
Puri N, Harsh DP, Ashwani J (2018) Prediction of geotechnical nation of optimum cross section of earth dams using Ant
parameters using machine learning techniques. Procedia colony optimization algorithm. Scientia Iranica. https://
Comput Sci 125(2018):509–517. https://doi.org/10.1016/j. doi.org/10.24200/sci.2018.21078
procs.2017.12.066 Rezaei M, Abbas M, Masoud M (2014) An intelligent approach
Qazi WH, Osman SBS, Muhammad BM (2016) Improvement of to predict unconfined compressive strength of rock sur-
correlation using artificial neural networks technique for rounding access tunnels in longwall coal mining. Neural
the prediction of resistivity against soil strength properties. Comput Appl 24:233–241. https://doi.org/10.1007/
Indian J Sci Technol 9(37):1–10. https://doi.org/10.17485/ s00521-012-1221-x
ijst/2016/v9i37/94351 Rezaei H, Ramli N, Ehsan M (2016) Bearing capacity of thin-
Qi C, Xiaolin T (2018) Slope stability prediction using inte- walled shallow foundations: an experimental and artificial
grated metaheuristic and machine learning approaches: a intelligence-based study. J Zhejiang Univ Sci A Appl Phys
comparative study. Comput Ind Eng. https://doi.org/10. Eng 17(4):273–285
1016/j.cie.2018.02.028 Rezania M, Javadi AA (2007) A new genetic programming
Qi C, Andy F, Guowei M, Xiaolin T, Xuhao D (2018) Com- model for predicting settlement of shallow foundations.
parative study of hybrid artificial intelligence approaches Can Geotech J 44(2007):1462–1473. https://doi.org/10.
for predicting hangingwall stability. J Comput Civil Eng 1139/T07-063
32(2):1–12. https://doi.org/10.1061/(ASCE)CP.1943- Ribeiro AJA, Beiro CA, Uchôa da S, Suelly de HAB (2012)
5487.0000737 Proposition of a geotechnical mapping based on rtificial
Rad HM, Vosoughi M, Sarrafi A (2014) Predicting the grouting neural networks for the town of Caucaia, Ceará, Brazil for
ability of sandy soils by artificial neural networks based on Paving Purposes. In: International journal of engineering
experimental tests. Civil Eng Infrastruct J 47(2):239–253 and technology IJET-IJENS, vol 12, no 05, pp 65–74
Rad HN, Iman B, Wan AWJ, Tahir MM, Loke KF (2019) Pre- Rim B, Emeriault F, Kastner R (2010) Artificial neural network
diction of flyrock in mine blasting: a new computational application for the prediction of ground surface movements
intelligence approach. Nat Resour Res. https://doi.org/10. induced by shield tunnelling. Can Geotech J
1007/s11053-019-09464-x 47(2010):1214–1233. https://doi.org/10.1139/T10-023
Ranasing MRATM, Jaksa MB (2016) Application of artificial Roy TK, Ambika K, Sudip KR (2012) Prediction of soaked CBR
intelligence techniques for rolling dynamic compaction. In: for subgrade layer by using artificial neural network model.
11th Australia and New Zealand Young geotechnical In: S Chakraborty, G Bhattacharya (eds) Proceedings of the
professionals conference (11YGPC), pp 41–47 international symposium on engineering under uncertainty:
Ranasinghe RATM, Jaksa MB, Kuo YL, Nejad FP (2017) safety assessment and management (ISEUSAM-2012),
Application of artificial neural networks for predicting the pp 1195–1206, https://doi.org/10.1007/978-81-322-0757-
impact of rolling dynamic compaction using dynamic cone 3_83
penetrometer test results. J Rock Mech Geotech Eng Saadata M, Manoj K, Monjezi M (2014) An ANN-based
9(2017):340–349. https://doi.org/10.1016/j.jrmge.2016. approach to predict blast-induced ground vibration ofGol-
11.011 E-Gohar iron ore mine, Iran. J Rock Mech Geotech Eng
Ranasinghe RATM, Jaksa MB, Nejad FP, Kuo YL (2018) 6:67–76. https://doi.org/10.1016/j.jrmge.2013.11.001
Genetic programming for predictions of effectiveness of Saadatpour M, Abbas A, Mohammad HA (2011) Fuzzy pattern
rolling dynamic compaction with dynamic cone pen- recognition method for assessing soil erosion. Environ
etrometer test results. J Rock Mech Geotech Eng. https:// Monit Assess 180:385–397. https://doi.org/10.1007/
doi.org/10.1016/j.jrmge.2018.10.007 s10661-010-1794-8
Rangel J, Ursula I-V, Ayala AG, Francisco C (2005) Tunnel Sabat AK (2015a) Prediction of maximum dry density and
stability analysis during construction using a neuro-fuzzy specific gravity of fly ash using support vector machine.
system. Int J Numer Anal Methods Geomech EJGE 20(2015):155–166
2005(29):1433–1456. https://doi.org/10.1002/nag.463 Sabat AK (2015b) Prediction of California bearing ratio of a
Rashidi M, Adel A, Biltayib MB (2019) Correlation between stabilized expansive soil using artificial neural network and
uniaxial compressive and shear strength data of limestone support vector machine. EJGE 20(2015):981–991
rocks by regression analysis and ANFIS model. In: Recent

123
Geotech Geol Eng

Sabbar AS, Amin C, Hamid N (2019) Prediction of liquefaction Samui P, Sitharam TG (2010) Site characterization model using
susceptibility of clean sandy soils using artificial intelli- artificial neural network and kriging. Int J Geomech
gence techniques. Indian Geotech J 49(1):58–69. https:// 10:171–180. https://doi.org/10.1061/ASCE1532-
doi.org/10.1007/s40098-017-0288-9 3641201010:5171
Saeidi H, Mansour N-B (2010) The effect of step load moving Samui P, Sitharam TG (2011a) Machine learning modelling for
on the surface of a cylindrical cavity using neural networks. predicting soil liquefaction susceptibility. Nat Hazards
Int Conf Recent Adv Geotech Earthq Eng Soil Dyn 52:1–8 Earth Syst Sci 11(2011):1–9. https://doi.org/10.5194/
Saha A (2014) Artificial Bee Colony (ABC) algorithm applied nhess-11-1-2011
to slope-stability in searching the critical surface. In: Samui P, Sitharam TG (2011) Determination of liquefaction
Geotechnique today-prediction, modelling and construc- susceptibility of soil based on field test and artificial
tion, Indian Geotechnical Society, pp 69–76 intelligence. In: International journal of earth sciences and
Saha S, Fan G, Xue L, Robert LL (2017) Prediction of soil-water engineering, Vol 04, No 02, pp 216–222, CAFET-
characteristic curve using artificial neural network INNOVA TECHNICAL SOCIETY
approach. PanAm Unsaturated Soils 2017 GSP 301, Samui P, Sarat KD, Sitharam TG (2009) Application of soft
pp 124–134, ASCE computing techniques to expansive soil characterization.
Sahoo R, Sarat KD (2016) Evaluation of liquefaction potential In: K Gopalakrishnan et al. (eds) Intelligent and soft
of soil based on standard penetration test using multivariate computing in infrastructure systems engineering, SCI, Vol
adaptive regression splines and multi-gene genetic pro- 259, pp 305–323, Springer
gramming. In: Indian Geotechnical Conference IGC2016, Samui P, Yıldırım D, Jagan J (2015) Site characterization using
Madras, Chennai, India GP, MARS and GPR. Handbook Genetic Programm Appl
Sakellariou MG, Ferentinou MD (2005) A study of slope sta- 13:345–357. https://doi.org/10.1007/978-3-319-20883-1_
bility prediction using neural networks. Geotech Geol Eng 13
23:419–445. https://doi.org/10.1007/s10706-004-8680-5 Santamarina JC (1987) Fuzzy sets and knowledge systems in
Salahudeen AB, Ijimdiya TS, Eberemu AO, Osinubi KJ (2018) geotechnical engineering, Ph. D. thesis, Purdue University
Artificial neural networks prediction of compaction char- Santamarina JC, Chameau JL (1987) Expert systems for
acteristics of black cotton soil stabilized with cement kiln geotechnical engineers. J Comput Civil Eng 1:241–252
dust. J Soft Comput Civil Eng 2–3(2018):50–71. https:// Santra P, Bhabani SD, Debashish C (2011) Delineation of
doi.org/10.22115/SCCE.2018.128634.1059 hydrologically similar units in a watershed based on fuzzy
Salehzadeh H, Ozouri A, Golestani AR (2011) Correlation classification of soil hydraulic properties. Hydrol Process
between cone and standard penetration tests. In: 5thSAS- 25(2011):64–79. https://doi.org/10.1002/hyp.7820
Tech 2011, Khavaran Higher-education Institute, Mash- Sanuade OA, Rasheed BA, Joel OA, Akindeji OF, Olayiwola
had, Iran GO (2017) Using artificial neural network to predict dry
Salehzadeh H, Amir H, Ashkan N (2014) OCR of clays by CPTu density of soil from thermal conductivity. In: RMZ–M&G,
data using EPR. EJGE 19:6585–6598 2017, Vol 64, pp 237–249, https://doi.org/10.1515/
Salem SS, Khalid E-Z (2010) Application of general regression rmzmag-2017-0012
neural networks (GRNNs) in assessing liquefaction sus- Saride S, Sitharam TG, Anand JP (2010) Prediction of settle-
ceptibility. Int Conf Recent Adv Geotech Earthq Eng Soil ments of geocell reinforced sand foundations. Geotechni-
Dyn 3:1–8 cal Special Publication No. 207, GeoShanghai 2010
Salimi A, Christian M, Singh TN, Prasnna J (2015) TBM per- International Conference, pp 328–337, ASCE
formance prediction in rock tunneling using various arti- Sariyar O, Ural DN (2010) Expert system approach for soil
ficial intelligence algorithms. In: 11th Iranian and 2nd structure interaction and land use. J Urban Plan Dev
Regional Tunnelling Conference ‘‘Tunnels and the Future’’ 136(2):135–138. https://doi.org/10.1061/ASCE0733-9488
Salimi A, Jamal R, Christian M, Andrea D (2016) Application of Sarkar G, Sumi S, Rajib B, Rokonuzzaman M (2015) Prediction
non-linear regression analysis and artificial intelligence of soil type and standard penetration test (SPT) value in
algorithms for performance prediction of hard rock TBMs. Khulna City, Bangladesh using general regression neural
Tunnel Undergr Space Technol 58(2016):236–246. https:// network. Quarter J Eng Geol Hydrogeol
doi.org/10.1016/j.tust.2016.05.009 48(2015):190–203. https://doi.org/10.1144/qjegh2014-108
Samui P (2008) Prediction of friction capacity of driven piles in Sarmadian F, Mehrjardi RT (2008) Modeling of some soil
clay using the support vector machine. Can Geotech J properties using artificial neural network and multivariate
45(2008):288–295. https://doi.org/10.1139/T07-072 regression in Gorgan Province, North of Iran. Global J
Samui P (2012) Application of statistical learning algorithms to Environ Res 2(1):30–35
ultimate bearing capacity of shallow foundation on cohe- Sasmal SK, Rabi NB (2018) Prediction of combined static and
sionless soil. Int J Numer Anal Meth Geomech cyclic loadinduced settlement of shallow strip footing on
36:100–110. https://doi.org/10.1002/nag.997 granular soil using artificial neural network. Int J Geotech
Samui P (2013) Slope stability analysis using multivariate Eng. https://doi.org/10.1080/19386362.2018.1557384
adaptive regression spline. Metaheuristics Water Geotech Sayadi A, Monjezi M, Talebi N, Khandelwal M (2013) A
Transp Eng 2013:327–342. https://doi.org/10.1016/B978- comparative study on the application of various artificial
0-12-398296-4.00014-3 neural networks to simultaneous prediction of rock frag-
Samui P (2014) Vector machine techniques for modeling of mentation and backbreak. J Rock Mech Geotech Eng
seismic liquefaction data. Ain Shams Eng J 5:355–360. 5(2013):318–324. https://doi.org/10.1016/j.jrmge.2013.
https://doi.org/10.1016/j.asej.2013.12.004 05.007

123
Geotech Geol Eng

Saygili G, Hanna AM, Ural D (2005) Neural network model for and Environmental Engineering University of Adelaide,
liquefaction potential in layered soils using Turkey and Research Report No. R 167
Taiwan earthquake data. In: GSP 133 earthquake engi- Shahin MA, Mark BJ, Holger RM (2001) Artificial neural net-
neering and soil dynamics, pp 1-15, ASCE work applications in geotechnical engineering, Australian
Senapati S (2013) Modelling of geotechnical structures using Geomechanics–March 2001, pp 49–62
multivariate adaptive regression spline (MARS) and Shahin MA, Maier HR, Jaksa MB (2002a) Predicting settlement
genetic programming (GP), M.Sc. thesis, National Institute of shallow foundations using neural networks. J Geotech
of Technology, Rourkela Geoenviron Eng 2002(128):785–793. https://doi.org/10.
Shahin MA (2010) Intelligent computing for modeling axial 1061/ASCE1090-02412002128:9785
capacity of pile foundations. Can Geotech J Shahin MA, Mark BJ, Holger RM (2002) Artificial neural net-
47(2010):230–243. https://doi.org/10.1139/T09-094 work–based settlement prediction formula for shallow
Shahin MA (2013a) Artificial intelligence in geotechnical foundations on granular soils, Australian Geomechanics–
engineering: applications, modeling aspects, and future September 2002, pp 45–52
directions. Metaheuristics Water Geotech Transp Eng Shahin MA, Maier HR, Jaksa MB (2003a) Settlement prediction
2013:169–204. https://doi.org/10.1016/B978-0-12- of shallow foundations on granular soils using B-spline
398296-4.00008-8 neurofuzzy models. Comput Geotech 30(2003):637–647.
Shahin MA (2013) Artificial intelligence for modeling load- https://doi.org/10.1016/j.compgeo.2003.09.004
settlement response of axially loaded (steel) driven piles. Shahin MA, Mark BJ, Holger RM (2003) Applications of arti-
In: 18th international conference on soil mechanics and ficial neural networks in foundation engineering, Aus-
geotechnical engineering, Paris 2013, pp 797–800 tralian Geomechanics
Shahin MA (2014a) Load–settlement modeling of axially loa- Shahin MA, Maier HR, Jaksa MB (2004) Data division for
ded drilled shafts using CPT-based recurrent neural net- developing neural networks applied to geotechnical engi-
works. Int J Geomech 14:1–7. https://doi.org/10.1061/ neering. J Comput Civil Eng 2004(18):105–114. https://
(ASCE)GM.1943-5622.0000370 doi.org/10.1061/*ASCE!0887-3801*2004!18:2*105!
Shahin MA (2014) Artificial intelligence for modeling load- Shahin MA, Jaksa MB, Maier HR (2005) Neural network based
settlement response of axially loaded bored piles. In: Pro- stochastic design charts for settlement prediction. Can
ceedings of the 8th European conference on numerical Geotech J 42(2005):110–120. https://doi.org/10.1139/T04-
methods in geotechnical engineering, Delft, The Nether- 096
lands, pp 491–495, Taylor & Francis Group Shahin MA, Mark BJ, Holger RM (2008) State of the art of
Shahin MA (2014c) Load–settlement modeling of axially loa- artificial neural networks in geotechnical engineering.
ded steel driven piles using CPT-based recurrent neural EJGE 13(2008):1–23
networks. Soils Found 54(3):515–522. https://doi.org/10. Shahin MA, Mark BJ, Holger RM (2009) Recent advances and
1016/j.sandf.2014.04.015 future challenges for artificial neural systems in geotech-
Shahin MA (2015a) Genetic programming for modelling of nical engineering applications. Adv Artif Neural Syst
geotechnical engineering systems. Handbook Genetic 308239:1–9. https://doi.org/10.1155/2009/308239
Program Appl 2:37–57. https://doi.org/10.1007/978-3- Shahnazari H, Shahin MA, Tutunchian MA (2014) Evolution-
319-20883-1_2 ary-based approaches for settlement prediction of shallow
Shahin MA (2015b) A review of artificial intelligence applica- foundations on cohesionless soils. Int J Civil Eng
tions in shallow foundations. Int J Geotech Eng 9(1):49–60. 12(1):55–64
https://doi.org/10.1179/1939787914Y.0000000058 Shahr-Babak MM, Mohammad JK, Kourosh Q (2016) Uplift
Shahin MA (2016) State-of-the-art review of some artificial capacity prediction of suction caisson in clay using a
intelligence applications in pile foundations. Geosci Front hybridintelligence method (GMDH-HS). Appl Ocean Res
7(2016):33–44. https://doi.org/10.1016/j.gsf.2014.10.002 59(2016):408–416. https://doi.org/10.1016/j.apor.2016.07.
Shahin MA, Indraratna B (2006) Modeling the mechanical 005
behavior of railway ballast using artificial neural networks. Shalmani AA, Mahmoud SS, Hossein A, Farid B (2010) Com-
Can Geotech J 43(2006):1144–1152. https://doi.org/10. parison of regression pedotransfer functions and artificial
1139/T06-077 neural networks for soil aggregate stability simulation.
Shahin MA, Jaksa MB (2005) Neural network prediction of World Appl Sci J 8(9):1065–1072
pullout capacity of marquee ground anchors. Comput Shang JQ, Ding W, Rowe RK, Josic L (2004) Detecting heavy
Geotech 32(2005):153–163. https://doi.org/10.1016/j. metal contamination in soil using complex permittivity and
compgeo.2005.02.003 artificial neural networks. Can Geotech J
Shahin MA, Mark BJ (2006) Pullout capacity of small ground 41(2004):1054–1067. https://doi.org/10.1139/T04-051
anchors by direct cone penetration test methods and neural Sharghi E, Vahid N, Nazanin B (2018) Earthfill dam seepage
networks. Can Geotech J 43(2006):626–637. https://doi. analysis using ensemble artificial intelligence based mod-
org/10.1139/T06-029 eling. J Hydroinf 66:1–14
Shahin MA, Mark BJ (2009) Intelligent computing for pre- Sharma LK, Vikram V, Singh TN (2017) Developing novel
dicting axial capacity of drilled shafts. Int Found Congress models using neural networks and fuzzy systems for the
Equip Expo. https://doi.org/10.1061/41022(336)4 prediction of strength of rocks from key geomechanical
Shahin MA, Jaksa MB, Maier HR (2000) Predicting the settle- properties. Measurement. https://doi.org/10.1016/j.
ment of shallow foundations on cohesionless soils using measurement.2017.01.043
back-propagation neural networks, Department of Civil

123
Geotech Geol Eng

Shatnawi A, Wassel ALB, Mutasim A-J, Bashar T (2019) Suman S, Partha NM, Sarat KD (2015) Prediction of seismic
Empirical formulas to predict the axial capacity of driven attenuation in rocks using artificial intelligence techniques.
piles using in-situ dynamic load testing data. Int J Mach In: 50th Indian geotechnical conference 17th–19th
Learn Comput 9(2):129–134. https://doi.org/10.18178/ December 2015, Pune, Maharashtra, India
ijmlc.2019.9.2.776 Suman S, Mahasakti M, Sarat KD (2016a) Prediction of maxi-
Sheng-Jun SHA, Hao X, Shu-Hua Z (2012) Constitutive model mum dry density and unconfined compressive strength of
identification of rock based on artificial intelligence. Adv cement stabilised soil using artificial intelligence tech-
Mater Res 368–373(2012):2509–2516. https://doi.org/10. niques. Int J Geosynth Ground Eng 2(11):1–11. https://doi.
4028/www.scientific.net/AMR.368-373.2509 org/10.1007/s40891-016-0051-9
Shin HS, Park IJ, Pande GN (2008) Generalization of field Suman S, Khan SZ, Das SK, Chand SK (2016b) Slope stability
measurement data based on a neural network. In: 12th analysis using artificial intelligence techniques. Nat
international association for computer methods and Hazards 2016(84):727–748. https://doi.org/10.1007/
advances in geomechanics (IACMAG), Goa, India, s11069-016-2454-2
pp 1730–1736 Suman S, Sarat KD, Ranajeet M (2016c) Prediction of friction
Shinoda M, Yoshihisa M (2018) PSO-based stability analysis of capacity of driven piles in clay usig artificial intelligence
unreinforced and reinforced soil slopes using non-circular techniques. Int J Geotech Eng. https://doi.org/10.1080/
slip surface. Acta Geotech. https://doi.org/10.1007/ 19386362.2016.1169009
s11440-018-0678-x Tabari H, Talaee PH, Patrick W (2015) Short-term forecasting
Shirzadi A, Dieu TB, Binh TP, Karim S, Kamran C, Ataollah K, of soil temperature using artificial neural network. Mete-
Himan S, Inge R (2017) Shallow landslide susceptibility orol Appl 22(2015):576–585. https://doi.org/10.1002/met.
assessment using a novel hybrid intelligence approach. 1489
Environ Earth Sci 76:60. https://doi.org/10.1007/s12665- Taha MR, Firoozi A (2012) Estimating the clay Cohesion by
016-6374-y means of artificial intelligence technique. J Asian Sci Res
Singh Gurdeepak G, Walia BS (2017) Performance evaluation 2(11):651–657
of nature-inspired algorithms for the design of bored pile Taha MR, Mohammad K, Ahmed E-S (2010) Slope stability
foundation by artificial neural networks. Neural Comput assessment using optimization techniques: an overview.
Appl 28(Suppl 1):S289–S298. https://doi.org/10.1007/ EJGE 15(2010):1901–1915
s00521-016-2345-1 Talaee PH, Majid H, Parviz F, Safar M, Hossein T (2012)
Singh R, Ashutosh K, Singh TN (2012) Estimation of elastic Numerical model and computational intelligence approa-
constant of rocks using an ANFIS approach. Appl Soft ches for estimating flow through Rockfill Dam. J Hydrol
Comput 12(2012):40–45. https://doi.org/10.1016/j.asoc. Eng 17:528–536. https://doi.org/10.1061/(ASCE)HE.
2011.09.010 1943-5584.0000446
Singh V, Samreen B, Anand KY, Sabih A (2019) Feasibility of Tarawneh B (2013) Pipe pile setup: database and prediction
artificial neural network in civil engineering. In: Interna- model using artificial neural network. Soils Found
tional journal of trend in scientific research and develop- 53(4):607–615. https://doi.org/10.1016/j.sandf.2013.06.
ment (IJTSRD), vol 3, no 3, pp 724-728, ISSN: 2456–6470 011
Sitharam TG, Shailendra K, Latha GM, Madhusudholl N (2003) Tarawneh B (2016) ‘‘Predicting standard penetration test
Intelligent Prediction of Elastic Properties of Jointed N-value from cone penetration test data using artificial
Rocks. J Rock Mech Tunnel Tech 9(1):11–34 neural networks. Geosci Front. https://doi.org/10.1016/j.
Sivrikaya O, Mahmut B (2009) Approaches to estimate gsf.2016.02.003
unconfined compressive strength of cohesive soils using Tarawneh B (2018) Gene expression programming model to
artificial neural networks. In: International symposium on predict driven pipe piles set-up. Int J Geotech Eng
innovations in intelligent systems and applications, Trab- 2018:1–8. https://doi.org/10.1080/19386362.2018.
zon, Turkey, pp 236–240 1460964
Solanki P, Musharraf Z, Ali E (2009) Regression and artificial Teh CI, Wong KS, Goh ATC, Jaritngam S (1997) Prediction of
neural network modeling of resilient modulus of subgrade pile capacity using neural networks. J Comput Civil Eng
soils for pavement design applications. In: K Gopalakr- 11(2):129–138
ishnan et al. (eds) intelligent and soft computing in Thomas S, Pillai GN, Kirat P, Zuhair M (2013) Prediction of
infrastructure systems engineering, SCI, vol 259, peak ground acceleration (PGA) using artificial neural
pp 269–304, Springer networks. In: International conferences on advances in
Sousa LR, Tiago M, Rita LS, Joaquim T (2017) The use of data computer science, AETACS, pp 270–276, Elsevier
mining techniques in rockburst risk assessment. Engi- Tinoco J (2012) Application of data mining techniques to jet
neering 3(2017):552–558. https://doi.org/10.1016/J.ENG. grouting columns design, Ph. D. thesis, University of
2017.04.002 Minho, Portugal
Sriram D (1984) A bibliography on knqwledge-based expert Tinoco J, Correia AG, Paulo C (2001) A data mining approach
systems in engineering, DRC-12-23-S4 for jet grouting uniaxial compressive strength prediction.
Sub-committee A2K053 (1999) Use of artificial neural networks In: 2009 World congress on nature and biologically
in geomechanical and pavement systems. In: Transporta- inspired computing (NaBIC 2009), pp 553–558, IEEE
tion research circular, Number E-C012, December 1999, Tinoco J, Correia AG, Cortez P (2011) Data mining approach
ISSN 0097-8515 for predicting jet grouting geomechanical parameters. In:

123
Geotech Geol Eng

Geotechnical Special Publication No. 223  ASCE 2011, Tsiaousi D, Thaleia T, Vasilis D, Jose U, Jacob C (2018)
pp 97–104, ASCE Machine learning applications for site characterization
Tinoco J, Correia AG, Paulo C (2011b) Application of data based on CPT data. Geotech Earthq Eng Soil Dyn
mining techniques in the estimation of the uniaxial com- 293:461–472
pressive strength of jet grouting columns over time. Constr Tsompanakis Y, Nikos DL, Prodromos NP, Evaggelos CG
Build Mater 25(2011):1257–1262. https://doi.org/10.1016/ (2009) Simulating the seismic response of embankments
j.conbuildmat.2010.09.027 via artificial neural networks. Adv Eng Softw 40:640–651.
Tinoco J, Correia AG, Paulo C (2011) Using data mining https://doi.org/10.1016/j.advengsoft.2008.11.005
techniques to predict deformability properties of jet Tumay MT, Murad YA-F, Zhongjie Z (2008) From theory to
grouting laboratory formulations over time. In: 15th Por- implementation of a CPT-based probabilistic and fuzzy
tuguese conference on artificial intelligence, EPIA 2011 soil classification. In: From research to practice in
Lisbon, Portugal, pp 491–505, https://doi.org/10.1007/ geotechnical engineering congress, pp 259–276, ASCE
978-3-642-24769-9, Springer Turan A, Sean DH, El Naggar MH (2008) Predicting the
Tinoco J, Correia AG, Paulo C (2011) Support vector machines dynamic properties of glyben using a modular neural net-
in mechanical properties prediction of jet grouting col- work (MNN). Can Geotech J 45(2008):1629–1638. https://
umns. Semana da Escola de Engenharia doi.org/10.1139/T08-054
Tinoco J, Alberto A, Paulo da V, Correia AG, Luı́s L (2016) A Turk G, Ogar J, Majes B (2001) Modelling soil behaviour in
data-driven approach for qu prediction of aboratory soil- uniaxial strain conditions by neural networks. Adv Eng
cement mixtures. In: The 3rd international conference on Softw 32(10–11):805–812. https://doi.org/10.1016/S0965-
transportation geotechnics (ICTG 2016), pp 566–573, 9978(01)00032-1
https://doi.org/10.1016/j.proeng.2016.06.073, Elsevier Ukritchon B, Suraparb K (2016) A practical method for the
Tinoco J, Correia AG, Paulo C, David T (2018) Artificial neural optimal design of continuous footing using Ant-Colony
networks for rock and soil cutting slopes stability condition optimization. Acta Geotechnica Slovenica 2:45–55
prediction. In: 2nd GeoMEast international congress and Ural DN, Mert T (2008) Slope stability during earthquakes: a
exhibition on sustainable civil infrastructures, Egypt, neural network application. In: Geocongress 2008: char-
pp 105–114, 10.1007/978-3-030-02032-3_10, Springer acterization, monitoring, and, modeling of geosystems,
Toll DG, Giolas A (1998) Representing geotechnical properties pp 878–885, ASCE
in a knowledge-based system. Adv Eng Softw Uyumaz A, Abdüsselam A, Mehmet O (2006) Fuzzy logic
29(7–9):627–636 model for equilibrium scour downstream of a Dam’s
Tolon M, Derin NU (2012) Geotechnical considerations for Vertical Gate. J Hydraul Eng 132:1069–1075. https://doi.
offshore wind turbines based on neural network. In: The org/10.1061/ASCE0733-9429
2012 world congress on advances in civil, environmental, Valliappan S, Pham TD (1993) Fuzzy finite element analysis of
and materials research (ACEM’ 12) Seoul, Korea, August a foundation on an elastic soil medium. Int J Numer Anal
26-30, 2012, pp 3265–3276 Methods Geomech 17:771–789
Touran A (1990) Expert system for compactor selection. Van den Adel JF, Al-Jibouri SH, Karim UFA, Mawdesley M
J Transp Eng 116(3):338–348 (2000) GROUNDSS: integrated foundation design expert
Tran H-H, Nhat-Duc H (2014) An artificial intelligence system. Comput Civil Build Eng 50:1180–1187
approach for groutability estimation based on autotuning Vergobbi P, Alain P, Geodia, Yves M, Gilles F (1992) Sagitaire:
support vector machine. J Constr Eng. https://doi.org/10. an artificial intelligence software dedicated to the
1155/2014/109184 geotechnical engineering of offshore structures. In: Off-
Tran KT, Michael MV, Rodrigo H, Peter L (2012) Estimating shore technology conference (OTC 6864), Houston, Texas,
static tip resistance of driven piles with bottom pile pp 471–478
instrumentation. Can Geotech J 49(2012):381–393. https:// Verma AK, Singh TN (2013) A neuro-fuzzy approach for pre-
doi.org/10.1139/T2012-001 diction of longitudinal wave velocity. Neural Comput Appl
Trivedi JS, Andeep N, Chakradhar I (2013) optimum utilization 22:1685–1693. https://doi.org/10.1007/s00521-012-0817-
of fly ash for stabilization of sub-grade soil using genetic 5
algorithm. Procedia Eng 51(2013):250–258. https://doi. Viloria JA, Alvaro V-B, Marı́a CP, Angel V (2016) Digital
org/10.1016/j.proeng.2013.01.034 modelling of landscape and soil in a mountainous region: a
Trivedi R, Singh TN, Raina AK (2014) Prediction of blast- neuro-fuzzy approach. Geomorphology
induced flyrock in Indian limestone mines using neural 253(2016):199–207. https://doi.org/10.1016/j.geomorph.
networks. J Rock Mech Geotech Eng 6(2014):447–454. 2015.10.007
https://doi.org/10.1016/j.jrmge.2014.07.003 Viswanathan R, Pijush S (2016) Determination of rock depth
Tsangaratos P, Andreas B (2014) Estimating landslide suscep- using artificial intelligence techniques. Geosci Front
tibility through a artificial neural network classifier. Nat 7(2016):61–66. https://doi.org/10.1016/j.gsf.2015.04.002
Hazards 74:1489–1516. https://doi.org/10.1007/s11069- Wanga Y, Xinyi Z, Baotian W (2013) LS-SVM and Monte
014-1245-x Carlo methods based reliability analysis for settlement of
Tsangaratos P, Benardos A (2013) Applying artificial neural soft clayey foundation. J Rock Mech Geotechn Eng
networks in slope stability related phenomena. Bull Geol 5(2013):312–317. https://doi.org/10.1016/j.jrmge.2012.
Soc Greece 47(4):1901–1911. https://doi.org/10.12681/ 06.003
bgsg.10945

123
Geotech Geol Eng

Wei L, Qing Z (2000) An AI integrated system for NATM in J. Korean Geosynthetics Society 17(4):277–292. https://
tunnel engineering. In: Computing in civil and building doi.org/10.12814/jkgss.2018.17.4.277
engineering, pp 1188–1195, ASCE Young-Su K, Kim B-T (2006) Use of artificial neural networks
Weihua F (2012) Back-analysis improved particle Swarm in the prediction of liquefaction resistance of sands.
optimization algorithm on mechanical parameters of divi- J Geotech Geoenviron Eng 132:1502–1504. https://doi.
sional geotechnical engineering material. Appl Mech org/10.1061/ASCE1090-02412006132:111502
Mater 182–183(2012):1647–1653. https://doi.org/10.4028/ Yousefpour N, Sogol F (2018) Application of machine learning
www.scientific.net/AMM.182-183.1647 in geotechnics. https://www.researchgate.net/publication/
Wislocki AP, Bentley SP (1991) An expert system for landslide 327338485_Application_of_Machine_Learning_in_
hazard and risk assessment. Comput Struct 40(1):169–172 Geotechnics
Wong KC, Poulos HG, Thorne CP (1989) Site classification by Zadhesh J, Fuad R, Faraydoun S, Hasel A, Hossein MN (2015)
expert systems. Comput Geotech 8:133–156 Consolidation grouting quality assessment using artificial
Xiao W-Q, Bo R (2009) Optimization methods for design of the neural network (ANN). Indian Geotech J 45(2):136–144.
stabilizing piles in landslide treatment. In: GeoHunan https://doi.org/10.1007/s40098-014-0116-4
international conference, pp 174–183, ASCE Zaman M, Pranshoo S, Ali E, Luther W (2010) Neural network
Xu W, Shao F (1998) Artificial neural network analysis for the modeling of resilient modulus using routine subgrade soil
evaluation of slope stability. In: Fourth European confer- properties. In: International journal of geomechanics, vol
ence on numerical methods in geotechnical engineering 10, no 1, pp 1–12, ISSN 1532-3641, ASCE
numge98 Udine, Italy, pp 665–672, Springer Zhang Z, Mehmet TT (1999) Statistical to Fuzzy approach
Xu L, Xuedong G, Lei N, Yongmei Q (2016) Back analysis on toward CPT soil classification. J Geotech Geoenviron Eng
mechanical parameters of interface between pile and soil 125(3):179–186
based on BP neural network. In: International journal of Zhang Z, Mehmet TT (2003) Non-traditional approaches in soil
earth sciences and engineering ISSN 0974-5904, vol 09, no classification derived from the cone penetration test. In:
06, pp 2802–2809 ASCE Special Publication No. 121 on probabilistic site
Xue X (2016) Prediction of slope stability based on hybrid PSO characterization at the national geotechnical experimenta-
and LSSVM. J Comput Civil Eng 04016041:1–10. https:// tion sites, pp 101–149, ISBN 0-7844-06693, ASCE
doi.org/10.1061/(ASCE)CP.1943-5487.0000607 Zhang Y, Gallipoli D, Augarde CE (2009a) Simulation-based
Yagiz S, Sezer EA, Gokceoglu (2012) Artificial neural networks calibration of geotechnical parameters using parallel
and nonlinear regression techniques to assess the influence hybrid moving boundary particle swarm optimization.
of slake durability cycles on the prediction of uniaxial Comput Geotech 36(4):604–615. https://doi.org/10.1016/j.
compressive trength and modulus of elasticity for carbon- compgeo.2008.09.005
ate rocks. Int J Numer Anal Meth Geomech 36:1636–1650. Zhang Y, Domenico G, Charles A (2009) Parallel hybrid par-
https://doi.org/10.1002/nag.1066 ticle swarm optimization and applications in geotechnical
Yagiz S, Ebrahim G, Amoussou CA (2018) Prediction of rock engineering. In: Advances in computation and intelligence.
brittleness using genetic algorithm and particle Swarm Heidelberg: Springer Berlin, pp 466–475, https://doi.org/
optimization techniques. Geotech Geol Eng 10.1007/978-3-642-04843-249
36:3767–3777. https://doi.org/10.1007/s10706-018-0570- Zhang Z, Zaobao L, Lifeng Z, Yu Z (2014) Development of an
3 adaptive relevance vector machine approach for slope
Yang Y, Rosenbaum MS (2002) The arti¢cial neural network as stability inference. Neural Comput Appl 25:2025–2035.
a tool for assessing geotechnical properties. Geotech https://doi.org/10.1007/s00521-014-1690-1
Geolog Eng 20: 149–168 Zhang L, Xianguo W, Wenying J, Simaan MA (2016a) Intelli-
Yang Y, Xuegang H, Xiaojie W, Qiongfang Z, Chen L (2012) gent approach to estimation of tunnel-induced ground
Application of Fuzzy cluster to geotechnical stratums settlement using wavelet packet and support vector
division. Adv Mater Res 378–379(2012):507–511. https:// machines. J Comput Civil Eng 04016053:1–14. https://doi.
doi.org/10.4028/www.scientific.net/AMR.378-379.507 org/10.1061/(ASCE)CP.1943-5487.0000621
Yasrebi SSH, Emami M (2008) Application of artificial neural Zhang L, Xianguo W, Yawei Q, Miroslaw JS, Wenli L (2016b)
networks (ANNs) in prediction and interpretation of pres- Towards a Fuzzy Bayesian network based approach for
suremeter test results. In: 12th international association for safety risk analysis of tunnel-induced pipeline damage.
computer methods and advances in geomechanics (IAC- Risk Anal 36(2):278–301. https://doi.org/10.1111/risa.
MAG), Goa, India, pp 1634–1638 12448
Yeh Y-C, Yau-Hwaug K, Deh-Shiu H (1993) Building KBES Zhao N (2014) The application of BP artificial neural network in
for diagnosing pc pile with artificial neural network. geotechnical engineering. Appl Mech Mater
J Comput Civil Eng 7(1):71–93. https://doi.org/10.1061/ 580–583(2014):823–826. https://doi.org/10.4028/www.
(ASCE)0887-3801(1993)7:1(71) scientific.net/AMM.580-583.823
Yin Z-Y, Yin-Fu J, Jack SS, Pierre-Yves H (2018) Optimization Zhao AJ, Xu BC, Yan CY, Ma DJ (2012) Predictive study on
techniques for identifying soil parameters in geotechnical ultimate bearing capacity of static pressure pipe pile based
engineering: comparative study and enhancement. Int J on grey support vector machine. In: Earth and Space 2012,
Numer Anal Methods Geomech 42:70–94. https://doi.org/ pp 1187–1195, ASCE
10.1002/nag.2714 Zhao H, Ming Z, Changxing Z (2016) Reliability-based opti-
Yoo C, Haider SA, Qaisar A, Jaewon Y (2018) Artificial intel- mization of geotechnical engineering using the artificial
ligence (AI)-based deep excavation designed program. Bee Colony algorithm. KSCE J Civil Eng

123
Geotech Geol Eng

20(5):1728–1736. https://doi.org/10.1007/s12205-015- rock masses using artificial neural networks: application


0117-6 and supplementary studies. Environ Earth Sci
Zhou M-M, Ahmed M, Günther M (2015) Modeling and opti- 2015(73):3417–3431. https://doi.org/10.1007/s12665-014-
mization of ground freezing in tunneling. In: ITA WTC 3630-x
2015 Congress and 41st General Assembly, 2015, Lacroma Zounemat-Kermani M (2013) Hydrometeorological parameters
Valamar Congress Center, Dubrovnik, Croatia in prediction of soil temperature by means of artificial
Zhu J-H, Musharraf MZ, Scott AA (1998) Modeling of soil neural network: case study in Wyoming. J Hydrol Eng
behavior with a recurrent neural network. Can Geotech J 18:707–718. https://doi.org/10.1061/(ASCE)HE.1943-
35:858–872 5584.0000666
Zhu C, Hongbo Z, Ming Z (2014) Back analysis of geome-
chanical parameters in underground engineering using
Publisher’s Note Springer Nature remains neutral with
artificial Bee Colony. Sci World J. https://doi.org/10.1155/
regard to jurisdictional claims in published maps and
2014/693812
institutional affiliations.
Ziaee SA, Ehsan S, Amir HA, Danial MS (2015) Explicit for-
mulation of bearing capacity of shallow foundations on

123

You might also like