See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/319159054

Dry unit weight of compacted soils prediction using GMDH-type neural

network

Article  in  European Physical Journal Plus · August 2017

DOI: 10.1140/epjp/i2017-11623-5

CITATIONS READS

19 951

4 authors:

M. Hassanlourad Alireza Ardakani

Imam Khomeini International University Imam Khomeini International University
29 PUBLICATIONS   296 CITATIONS    40 PUBLICATIONS   218 CITATIONS   

SEE PROFILE SEE PROFILE

Afshin Kordnaeij Hossein Molaabasi

Imam Khomeini International University Gonbad Kavous University
21 PUBLICATIONS   339 CITATIONS    60 PUBLICATIONS   640 CITATIONS   

SEE PROFILE SEE PROFILE

Some of the authors of this publication are also working on these related projects:

‫ رﻓﺘﺎر ﺳﺘﻮﻧﻬﺎی داﻧﻬﺎی ﻣﺤﺼﻮرﺷﺪه ﺑﺎ ژﺋﻮﺳﻨﺘﺘﯿﮏ در ﺧﺎک ﻣﺎﺳﻪ اﻟﯿﺪار ﺗﺤﺖ آزﻣﺎﯾﺶ ﺑﺮش ﻣﺴﺘﻘﯿﻢ‬View project

Risk assessment of underground structures View project

All content following this page was uploaded by Alireza Ardakani on 21 August 2017.

The user has requested enhancement of the downloaded file.

 European Journal of Environmental and Civil Engineering

ISSN: 1964-8189 (Print) 2116-7214 (Online) Journal homepage: http://www.tandfonline.com/loi/tece20

Soil compaction parameters prediction using

GMDH-type neural network and genetic algorithm

Alireza Ardakani & Afshin Kordnaeij

To cite this article: Alireza Ardakani & Afshin Kordnaeij (2017): Soil compaction parameters
prediction using GMDH-type neural network and genetic algorithm, European Journal of
Environmental and Civil Engineering

To link to this article: http://dx.doi.org/10.1080/19648189.2017.1304269

Published online: 23 Mar 2017.

Submit your article to this journal

View related articles

View Crossmark data

Full Terms & Conditions of access and use can be found at

http://www.tandfonline.com/action/journalInformation?journalCode=tece20

Download by: [5.210.106.119] Date: 23 March 2017, At: 05:25

European Journal of Environmental and Civil Engineering, 2017
http://dx.doi.org/10.1080/19648189.2017.1304269

Soil compaction parameters prediction using GMDH-type neural

network and genetic algorithm
Alireza Ardakani and Afshin Kordnaeij
Department of Civil Engineering, Imam Khomeini International University, Qazvin, Iran

ABSTRACT ARTICLE HISTORY

The maximum dry density (γd,max) and optimum moisture content (ωopt) Received 11 September 2015
determined from the results of the Proctorr test are very important for Accepted 21 February 2017
geotechnical engineering and earth structures. As the Proctor test is
KEYWORDS
relatively time consuming and laborious, in present research Group Method Compaction parameters;
of Data Handling (GMDH) type neural network (NN) is used to estimate the maximum dry density;
compaction parameters (γd,max and ωopt) of soils indirectly from more simply optimum moisture content;
determined index properties such as liquid limit (LL), plastic limit (PL) and fine- proctor test; group method
grained content (FC) as well as sand content (SC). A database containing 212 of data handling
data-sets were used for the training and testing of the models. A comparison
was carried out between the experimentally measured compaction
parameters with the predictions in order to evaluate the performance of
the GMDH method. The results demonstrate that generalised GMDH-type NN
has a great ability for prediction of the γd,max and ωopt. At the end, sensitivity
analysis of the obtained model has been carried out to study the influence
of input parameters on model outputs, and shows that the LL and PL are the
most influential parameters on the compaction parameters.

1. Introduction
Soil compaction occurs when soil particles are pressed together, reducing the pore space between
them. This increases the weight of solids per unit volume of soil. Generally, compaction increases the
strength characteristics of the soil, reduces its compressibility and permeability.
The maximum dry density (γd,max) and optimum moisture content (ωopt) of soils are determined using
standard Proctor test (Proctor, 1933). These compaction parameters are very important for geotechni-
cal engineering and earth structures such as earth dams, bridge abutments, highway embankments
and the fills behind retaining walls. Soil is compacted in the project site according to the compaction
parameters determined in the laboratory. For a wide variety of earth structures, the minimum accept-
able dry density (γd) is usually specified at 95 percent of the γd,max for the standard Proctor compaction
(ASTM D698, 2003).
Soil type is an important factor that affects the soil compaction (Das, 2010). The compaction pro-
cess has significant differences for cohesive soil vs. cohesionless soils. The shapes and the positions
of the compaction curves change as the texture of the soils varies from coarse to fine (Terzaghi, Peck,
& Mesri, 1996). The major difference is that the cohesive soils are typically very moisture-dependent
and cohesionless soils are not (Rout, 2009). As standard Proctor test is time consuming and laborious,
several researchers have tried to find prediction models which can predict approximately the values of

CONTACT  Afshin Kordnaeij  Afshin_geotec@yahoo.com, A.Kordnaeij@edu.ikiu.ac.ir

© 2017 Informa UK Limited, trading as Taylor & Francis Group
2    A. ARDAKANI AND A. KORDNAEIJ

Table 1. Some correlations for compaction parameters.

Equation Equation number Reference
𝛾d,max (KPa):
𝛾d,max = 23.94 − 0.2 PL − 0.078 LL (Iraqi soils) (1) AI-Khafaji (1993)
𝛾d,max = 22.27 − 0.19 PL − 0.029 LL (US soils) (2) AI-Khafaji (1993)
γd,max = 0.23(93.3 – PL) (3) Sridharan and Nagaraj (2005)
𝛾d,max = −0.1008 LL + 21.16 (4) Gunayin (2009)
𝛾d,max = −0.2283 PL + 21.88 (5) Gunayin (2009)

𝜔opt (%):    
𝜔opt = 0.24 LL + 0.63 PL − 3.13 (Iraqi soils) (6) AI-Khafaji (1993)
𝜔opt = 0.14LL + 0.54PL (US soils) (7) AI-Khafaji (1993)
𝜔opt = 0.92PL (8) Sridharan and Nagaraj (2005)
𝜔opt = 0.8442 PL + 0.1076 (9) Gunayin (2009)
𝜔opt = 0.3802 LL + 2.4513 (10) Gunayin (2009)
𝜔opt = 0.323 LL + 0.157 PL (11) Gunayin (2009)

γd,max and ωopt from more simply determined index properties of natural soil. Table 1 presents several
types of empirical correlations in this field.
Almost all of the empirical correlations for the compaction parameters prediction have been estab-
lished based on regression analysis. Many factors may affect the compaction parameters (γd,max and
ωopt). Hence any statistical method using for the estimation of the γd,max and ωopt may contain some
deviation. Computational intelligence (CI) techniques can be considered as efficient methods. They
determine the structure of a prediction model by automatically learning from data. CI has different
well-known branches such as support vector machines (SVM), artificial neural network (ANN), fuzzy
inference system (FIS), etc. These methods have been used to model complex relationships between
input and output data-sets in geotechnical engineering (Edincliler, Cabalar, & Cevik, 2013; Kalantary &
Kordnaeij, 2012; Kang, Li, Wang, & Li, 2016; Žlender, Jelušič, & Boumezerane, 2012). Despite the good
performance of these CI methods, they are considered black-box models and are not capable of gener-
ating practical prediction equations. This is a fundamental disadvantage that limits their practicability
(Mohammadzadeh, Bolouri Bazaz, & Alavi, 2014). In order to overcome this disadvantage, Group Method
of Data Handling (GMDH) type NN has been used in this article.
The GMDH-type NN is a powerful identification technique and can be used to model complex sys-
tems, where unknown relationships exist between variables, without having specific knowledge of
processes as other NNs. GMDH is aimed at identifying the functional structure of a model hidden in
the empirical data (Ivakhnenko, 1971).
In recent years, genetic algorithms have been used in a feed forward GMDH-type NN for each
neuron searching its optimal set of connection with the preceding layer. Over the last few years, the
GMDH-type NN optimised by genetic algorithms have been applied to many geotechnical engineer-
ing problems and have demonstrated some degree of success (Ardalan, Eslami, & Nariman-Zadeh,
2009; Kalantary, Ardalan, & Nariman-Zadeh, 2009; Mola-Abasi, Eslami, & Tabatabaeishorijeh, 2013).
Therefore, this approach can be used in empirical correlation of the compaction parameters as a step
forward in comparison with statistical approaches and investigate the effect of input parameters on
the model output.
Present study aims to develop a GMDH-type NN for the prediction of γd,max and ωopt based on various
soil index parameters such as liquid limit (LL), plastic limit (PL) and fine-grained content (FC) as well as
sand content (SC), without carrying out Proctor tests.
The rest of this paper is organised as: Review of the GMDH-type NN model and application of genetic
algorithms in the topology design of GMDH-type NN, database compilation, evaluation of the compac-
tion parameters using GMDH model, carrying out the sensitivity analysis of the obtained model and
finally, the conclusion of the paper.
 EUROPEAN JOURNAL OF ENVIRONMENTAL AND CIVIL ENGINEERING   3

2.  Review of GMDH-type neural network Model

Group method of data handling (GMDH) type NN is a self-organising approach by which gradually com-
plicated models are generated based on the evaluation of their performances on a set of multi-input
single-output data pairs (Xi, yi) (i = 1, 2, …, M). The main idea of GMDH is to build an analytical function
in a feed forward network based on a quadratic node transfer function whose coefficients are obtained
using regression technique. Using the GMDH algorithm, a model can be represented as a set of neurons
in which different pairs in each layer are connected through a quadratic polynomial and thus produce
new neurons in the next layer. Such representation can be used to map inputs to outputs. The formal
definition of the identification problem is to find a function f̂ that can be approximately used instead
of the actual one, f in order to predict output ŷ for a given input vector X = (x1 , x2 , x3 , … , xn ) as close as
possible to its actual output y. Therefore, given M observation of multi-input-single-output data pairs
(Farlow, 1984):
( )
yi = f xi1 , xi2 , xi3 , … , xin (i = 1, 2, 3, … , M) (12)
It is now possible to train a (GMDH-type of artificial
) neural network to predict the output values ŷ i for
any given input vector X = xi1 , xi2 , xi3 , … , xin , that is:
( )
yi = ̂f xi1 , xi2 , xi3 , … , xin
̂ (i = 1, 2, 3, … , M) (13)

The problem is now to determine a GMDH-type of artificial neural network so that the square of the
differences between the observed and predicted output is minimised as follow:

∑
M
( )
[̂f xi1 , xi2 , xi3 , … , xin − yi ]2 → min (14)
i=1

The general connection between input and output variables can be expressed by a complicated discrete
form of the Volterra functional series, known as the Kolmogorov–Gabor polynomial. Hence:

∑
n
∑
n
∑
n
∑
n
∑
n
∑
n
y = a0 + ai xi + aij xi xj + aijk xi xj xk + … (15)
i=1 i=1 j=1 i=1 j=1 k=1

This full form of mathematical description can be represented by a system of partial quadratic polyno-
mials consisting of only two variables (neurons) in the form of:
( )
y = G xi , xj = a0 + a1 xi + a2 xj + a3 xi xj + a4 xi2 + a5 xj2
̂ (16)

By this means, the partial quadratic description is recursively used in a network of connected neurons
to build the general mathematical relation between inputs and output given in Equation (15). The coef-
ficients ai in Equation (16) are calculated using regression techniques so that the difference between
the observed output, y and the calculated one, ŷ for each pair of xi, xj as input variables is minimised
(Jamali, Nariman-zadeh, Darvizeh, Masoumi, & Hamrang, 2009). Apparently, a tree of polynomials is
constructed using the quadratic form given in Equation (16) whose coefficients are obtained in a least
squares scheme. In this way, the coefficients of each quadratic function Gi are obtained to fit optimally
the output in the whole set of input–output data pairs, that is:
∑M � �
i=1 (yi − Gi xi , xj )2
E= → min (17)
M

In the basic form of the GMDH algorithm, all the possibilities of two independent variables out of the
total n input variables are taken in order to construct the regression polynomial in the form of Equation
4    A. ARDAKANI AND A. KORDNAEIJ

(16) that
( ) best fits the dependent observations (yi , i = 1, 2, … , M) in a least squares sense. Consequently,
n
= n(n−2)
2
neurons will be built up in the first hidden layer of the feed forward network from
2
{( ) }
M) for different
the observations yi , xip , xiq ; (i = 1, 2, 3, … ,{( ) } … , n}. In other words, it
p, q ∈ {1, 2, 3,
is now possible to construct M data triples yi , xip , xiq ; (i = 1, 2, 3, … , M) from observations using
p, q ∈ {1, 2, 3, … , n} in the form of:

⎡ x1p x1q ⋮ y1 ⎤
⎢ x2p x2q ⋮ y2 ⎥
⎢ ⎥
⎢ …… ⋮ … ⎥
⎢ ⎥
⎣ xMp xMq ⋮ yM ⎦

Using the quadratic sub-expression in the form of Equation (16) for each row of M data triples, the
following matrix equation can be readily obtained as:
Aa = Y (18)

a = {a0 , a1 , a2 , a3 , a4 , a5 } (19)

Y = {y1 , y2 , y3 , … , yM }T (20)
It can be readily seen that:

⎡ 1 x1p x1q x1p x1q 2

x1p 2
x1q ⎤
⎢ 1 x2p x2q x2p x2q 2
x2p 2
x2q ⎥
A=⎢ ⎥ (21)
⎢ … … … … … … ⎥
⎢ ⎥
⎣ 1 xMp xMq xMq xMq 2
xMp 2
xMq ⎦

The least squares technique from multiple regression analysis leads to solution of the normal equations,
in the form of:
( )−1
a = AT A AT Y (22)

This determines the vector of the best coefficients of the quadratic Equation (16) for the whole set of M
data triples. Notice that this procedure is repeated for each neuron of the next hidden layer according
to the connectivity topology of the network. However, such a solution directly from normal equations
is rather susceptible to round off errors and, more importantly, to the singularity of these equations.
There are two main concepts involved within GMDH-type of artificial neural network design, namely,
the parametric and the structural identification problems. Nariman-Zadeh, Darvizeh, and Ahmad-Zadeh
(2003) present hybrid genetic algorithm (GA) and singular value decomposition (SVD) method to opti-
mally design such polynomial neural network.

3.  Application of GA in the topology design of GMDH-type neural network

Stochastic methods are commonly used in the training of neural network in terms of associated weights
or coefficients and have successfully performed better than traditional gradient-based techniques
(Atashkari, Nariman-Zadeh, Gölcü, Khalkhali, & Jamali, 2007). The literature shows a wide range of
evolutionary design approaches either for architectures or connection weights separately, in addition
to efforts for them simultaneously (Yao, 1999).
In the most GMDH-type NN, neurons in each layer are only connected to neuron in its adjacent layer
as it was the case in Methods I and II previously reported in Nariman-Zadeh et al. (2003). Taking this
 EUROPEAN JOURNAL OF ENVIRONMENTAL AND CIVIL ENGINEERING   5

a ab
abbc
b bc
abbcadad
c ad
d

Figure 1. A GS-GMDH network structure of a chromosome (Ardalan et al., 2009).

advantage, it was possible to present a simple encoding scheme for the genotype of each individual in
the population. The encoding schemes in general structure GMDH-type NN (GS-GMDH) must, however,
demonstrate the ability of representing different length and size of such neural networks. In Figure 1,
neuron ad in the first hidden layer is connected to the output layer by directly going through the sec-
ond hidden layer. Therefore, it is now very easy to notice that the name of output neuron (network’s
output) includes ad twice as abbcadad. In other words, a virtual neuron named adad has been con-
structed in the second hidden layer and used with abbc in the same layer to make the output neuron
abbcadad as shown in the Figure 1. Such repetition occurs whenever a neuron passes some adjacent
hidden layers and connects to another neuron in the next 2nd, or 3rd, or 4th, or … following hidden
layer. In this encoding scheme, the number of repetition of that neuron depends on the number of
passed hidden layers, ̃ n, and is calculated as 2̃n. It is easy to realise that a chromosome such as abab
bcbc, unlike chromosome abab acbc for example, is not a valid one in GS-GMDH network and has to be
simply re-written as abbc (Jamali et al., 2009).
The genetic operators of crossover and mutation can now be implemented to produce two offspring
from two parents. The natural roulette wheel selection method is used for choosing two parents pro-
ducing two offspring. The incorporation of genetic algorithm into the design of such GMDH type neural
network starts by representing each network as a string of concatenated sub-strings of alphabetical
digits. The fitness, Φ, of each entire string of symbolic digits which represents a GMDH-type NN model
is evaluated in the following form:
Φ = 1∕E (23)
Where E is the mean square of error given by Equation (17), which is minimised through the evolutionary
process by maximising the fitness, Φ. The evolutionary process starts by a random generation of an
initial population of symbolic strings, each as a candidate solution. Then, using the genetic operations
of roulette wheel selection, crossover and mutation the entire population of symbolic strings improve
gradually. In this way, GMDH-type NN models with progressively increasing fitness, Φ, are produced
until no further significant improvement is achievable (Atashkari et al., 2007).
The flowchart of proposed method is given in Appendix A.

4.  Database compilation

In the present study, the data (212 data) published by AI-Khafaj (1993), Günaydın (2009), Sridharan &
Nagaraj (2005) and Kolay and Baser (2014) for different soil types (CH, CI, CL, GC, GM, MH, MI, ML, SC, SM)
are used. Physical properties of soil samples are given in Table 2. The data include a very wide range of
soils as indicated by the wide range of index properties. In the database, the compaction parameters
were assumed to be affected by liquid limit (LL), plastic limit (PL), fine-grained content (FC) and sand
content (SC) as summarised in Table 2.
To visualise the distribution of the samples, the data are presented by frequency histograms (Figure 2).
As we can observe from Figure 2, the distributions of the predictor variables are not uniform. The
derived models provide better predictions for the cases where the frequencies of the variables
are higher.
6    A. ARDAKANI AND A. KORDNAEIJ

Table 2. Descriptive statistics of variables.

Variable Minimum Average Maximum
LL (%) 23.00 41.13 73.50
PL (%) 10.00 21.77 51.90
FC (%) 13.00 67.34 100
SC (%) 0 25.75 75.30
𝛾d,max (KPa) 11.10 17.04 21.58
𝜔opt (%) 7.60 18.16 44.40

60 80

70
50
60
40
50
Frequency

Frequency
30 40

30
20
20
10
10

0 0
20 30 40 50 60 70 80 10 20 30 40 50 60
LL (%) PL (%)

40

40

30
30
Frequency

Frequency

20
20

10
10

0 0
0 20 40 60 80 100 0 15 30 45 60 75
FC (%) SC (%)

80 100

80
60

60
Frequency

Frequency

40
40

20
20

0 0
10 12 14 16 18 20 22 5 10 15 20 25 30 35 40 45
γd,max (KPa) ωopt (%)

Figure 2. Histograms of the variables used for the model development.

 EUROPEAN JOURNAL OF ENVIRONMENTAL AND CIVIL ENGINEERING   7

5.  Evaluation of the compaction parameters using GMDH

The main goal of this research is to develop a polynomial function of input geotechnical parameters
to estimate the compaction parameters as outputs. In order to validate the prediction ability of the
evolved GMDH-type NN, data-set has been divided randomly into two separate data-sets as the training
data-set and the testing data-set. The testing data-set tries to obtain a more generalised model while
it is not incorporated in the training procedure. According to an accepted rule, training and testing
data-sets must be similar in terms of their statistical properties such as mean and standard deviation
(Tokar & Johnson, 1999).
In present research, among 212 data-sets, 32 randomly collected data-sets were used in the testing
stage and 180 data-sets were used in the training stage (Table 3). Four parameters LL, PL, FC and SC were
used for the GMDH models as the input variables and γd,max and ωopt as the output variables.
Various parameters involved in the GMDH predictive such as population size, number of generations,
number of hidden layers, crossover probability and mutation probability. The parameters selection
will affect the model generalisation capability of GMDH. To genetically design such GMDH-type NN, a
population of 100 individuals with a crossover probability of 0.95 and mutation probability of 0.01 has
been used in 300 generations for the population size of which no further improvement has been made.
A number of hidden layers may be tried to achieve the best relative fit. In this article, it was decided
to opt for a single layer to avoid over-fitting as well as obtaining a simpler correlation. It is noteworthy
that the inherent inaccuracies of test data and the uncertainties associated with experimentation,
prohibits an exact fit and only the general trend is determinable. The structure of the evolved GMDH-
type NN is shown in Figure 3. The corresponding polynomial representation of such model to predict
γd,max is as follows:
𝛾d,max = 10.68 − 1.376 Y1 + 1.065 Y2 − 0.1027 Y12 − 0.1802 Y22 + 0.3232 Y1 .Y2 (24a)

Y2 = 19.8 − 0.15 PL + 0.005 SC − 0.0006 PL2 + 0.0004 SC 2 + 0.0005 PL.SC (24b)

Y1 = 22.2 − 0.02 LL − 0.066 FC − 0.0012 LL2 + 0.0002 FC 2 + 0.00043 LL.FC (24c)

The polynomial representation of GMDH model for ωopt is as follows:

𝜔opt = −4.9 + 1.333 Y1 + 0.17 Y2 + 0.0043 Y12 + 0.032 Y22 − 0.049 Y1 .Y2 (25a)

Table 3. Descriptive statistics of variables used in the GMDH.

  Train (180 data-set) Test (32 data-set)
Maximum Average Minimum Maximum Average Minimum
Input LL (%) 23 41.37 73.50 23.1 39.79 73.50
PL (%) 10.00 21.85 51.90 13 21.29 45.2
FC (%) 13 68.16 100 15 62.71 99.10
SC (%) 0 25.40 75.30 0.90 27.73 69.09
Output γd,max(KPa) 11.10 17.03 21.58 12.20 17.08 19.95
𝜔opt (%) 7.60 18.17 44.40 9.30 18.12 39.70

Y1

Y2

Figure 3. Evolved structure of generalised GMDH neural network to predict compaction parameters (Yi).
8    A. ARDAKANI AND A. KORDNAEIJ

a b
22 50
Training Training
Testing Testing
20
40
(KPa)

(%)
18

opt
d,max

Estimated ω
30
16
Estimated γ

14 20

12
10

12 14 16 18 20 22 10 20 30 40 50
Measured γ (KPa) Measured ω (%)
d,max opt

Figure 4. The measured compaction parameters obtained from the Proctor test vs. the GMDH estimated values.

Table 4. Statistical results for GMDH.

Model R RMSE MAD MAPE
𝛾d,max        
GMDH model (training) 0.90 0.60 0.46 2.70
GMDH model (testing) 0.93 0.63 0.46 2.68
𝜔opt        
GMDH model (training) 0.91 1.81 1.37 7.53
GMDH model (testing) 0.96 1.79 1.42 7.84

Y2 = 15.4 + 0.02 PL − 0.143 SC + 0.0115 PL2 + 0.0007 SC 2 − 0.001 PL.SC (25b)

Y1 = 9.3 − 0.16 LL + 0.104 FC + 0.0062 LL2 + 0.00009 FC 2 − 0.0011 LL.FC (25c)

Figure 4 shows scattergram for the estimated γd,max and ωopt from the application of the GMDH model
and the measured values from the Proctor test obtained through the training and testing process. The
models show very good correlation for both the training and testing data and the proposed equation
results in points closely located around the 1:1 line.
Correlation coefficient (R), root mean squared error (RMSE), mean absolute deviation (MAD) and
mean absolute percent error (MAPE) were used to evaluate the performance of the equations, which
are defined as follows:
∑M ̄ ̄
1 (hi − hi )(ti − ti )
R= � (26)
∑M ̄ 2 ∑M (t − t̄ )2
1 (hi − hi ) 1 i i

√
√
√1 ∑M
RMSE = √ (h − ti )2 (27)
M 1 i

∑M �
h − ti ��
MAD = 1 � i (28)
M
 EUROPEAN JOURNAL OF ENVIRONMENTAL AND CIVIL ENGINEERING   9

Table 5. Statistical results for the empirical formulas and GMDH models.
Equation Equation number R RMSE MAD MAPE
𝛾d,max (KPa):          
𝛾d,max = 23.94 − 0.2PL − 0.078LL (Iraqi soils) (1) 0.77 1.28 0.99 5.79
𝛾d,max = 22.27 − 0.19PL − 0.029LL (US soils) (2) 0.74 0.97 0.76 4.47
γd,max = 0.23(93.3 – PL) (3) 0.70 1.19 0.89 5.20
𝛾d,max = −0.1008LL + 21.16 (4) 0.76 0.91 0.69 4.05
𝛾d,max = −0.2283PL + 21.88 (5) 0.70 1.04 0.82 4.80
γd,max (GMDH model) (24) 0.90 0.60 0.46 2.70
𝜔opt (%):  
𝜔opt = 0.24LL + 0.63PL − 3.13 (Iraqi soils) (6) 0.80 3.97 3.18 17.52
𝜔opt = 0.14LL + 0.54PL (US soils) (7) 0.79 2.95 2.42 13.34
𝜔opt = 0.92PL (8) 0.74 3.87 2.99 16.50
𝜔opt = 0.8442PL + 0.1076 (9) 0.74 3.27 2.66 14.62
𝜔opt = 0.3802LL + 2.4513 (10) 0.76 3.03 2.21 12.18
𝜔opt = 0.323LL + 0.157PL (11) 0.79 3.22 2.40 13.20
ωopt (GMDH model) (25) 0.92 1.81 1.38 7.58

100

80

60
SCF

40
AI-Khafaji (1993), Eq (1)
AI-Khafaji (1993), Eq (2)
Sridharan and Nagaraj
20 (2005), Eq (3)
Gunayin (2009), Eq (4)
Gunayin (2009), Eq (5)
GMDH
0
-20 -10 0 10 20
Er (%)

Figure 5. Scaled relative errors of the estimated γd,max.

∑M �
h − ti ��
MAPE = 1∑� Mi × 100 (29)
1 hi

where M denotes the total number of data, the hi and ti are the actual and predicted output values for
the ith outputs, respectively. h̄ i and t̄i are, respectively, the average of the actual and predicted outputs.
The lower the RMSE, MAD and MAPE values the better the model performance. Under ideal conditions
an accurate and precise method gives R of 1.0, RMSE, MAPE and MAD of 0.
In Table 4, the predictability of the GMDH model is statistically given. It is clearly evident that the
evolved GMDH-type NN in terms of simple polynomial equations could successfully model and predict
the output of testing data that has not been used during the training process.
In Table 5, the predictability of the GMDH models for all data-set are statistically compared with the
empirical equations. It can be seen that the least disparities of these parameters are achieved by the
GMDH approach. Therefore, the developed ANN models are more efficient than the existing empirical
10    A. ARDAKANI AND A. KORDNAEIJ

100

80

60

SCF

40 AI-Khafaji (1993), Eq (6)

AI-Khafaji (1993), Eq (7)
Sridharan and Nagaraj
(2005), Eq (8)
Gunayin (2009), Eq (9)
20
Gunayin (2009), Eq (10)
Gunayin (2009), Eq (11)
GMDH
0
-40 -20 0 20 40 60 80
E (%)
r

Figure 6. Scaled relative errors of the estimated ωopt.

formulas. A graphic representation of the comparative accuracy of the correlations and the proposed
methods are shown by plotting the Scaled relative error, (Er) vs. Scaled cumulative frequency (SCF).
(ti − hi )
Er (%) = × 100 (30)
hi
As is seen in Figures 5 and 6, broader ranges of prediction are given by all of the previously proposed
equations in comparison to suggested equations. The proposed GMDH models to predict both com-
paction parameters are more accurate in comparison with all of the other empirical correlations.

6.  Sensitivity analysis

Because the polynomial model produced by the evolved GMDH-type neural network is in the form of
complex equations and thus the effect of input parameters on the model output is not clearly evident,
the sensitivity analysis of the obtained model is carried out to evaluate the input parameters influence
on the model output.
To perform the analysis, the cosine amplitude method can be utilised. This method is illustrated in
the following equation (Momeni, Nazir, Jahed Armaghani, & Maizir, 2014):
∑n
k=1 (mik × mjk )
Rij = � (31)
∑n 2 ∑n 2
k=1 mik k=1 mjk

Where mi and mj are input and output parameters respectively. Rij, which ranges between 0 and 1, shows
the strength of the relation between each input parameter and the model output. In other words, if
the target variable has no relation with the input, then the Rij value is zero, while the value of Rij closer
to 1 indicates the further influence of the input parameter. The obtained strength of relations for the
problem in hand is shown in Figure 7. As displayed in this figure, the LL and PL are the most influential
parameters on the model outputs (γd,max and ωopt).
Figure 8 shows the effect of changing or error in measuring the input parameters (inaccuracies)
on the proposed models to predict the compaction parameters. Various constant change rates (–10
to 10%) are selected in the study. For every input neuron, mean absolute percent error (MAPE) in the
 EUROPEAN JOURNAL OF ENVIRONMENTAL AND CIVIL ENGINEERING   11

γd,max ωopt
1

0.95

0.90

0.85
Rij
0.80

0.75

0.70
LL PL FC SC
Input parameter

Figure 7. Influence of each input parameter on the model output.

γd,max ωopt
3.1
LL PL FC SC LL PL SC FC
8.5

2.9
MAPE (%)

MAPE (%)

2.8

2.7 7.58

-10 -5 0 5 10 -10 -5 0 5 10
Change in input (%) Change in input (%)

Figure 8. Effect of the change in the input parameters on the output MAPE.

outputs, as a result of change in the input neuron, is observed. It can be noticed from the Figure 8 that
the developed model to predict γd,max is considerably influenced by changing or error in measuring
LL value and the MAPE increases greatly by changing it. For example 10% error in measuring LL in the
laboratory may cause about 3% error (MAPE ≈ 3) in predicting γd,max by proposed model. Then it requires
more accuracy to measure this parameter in laboratory. As seen in Figure 8, the proposed model to
predict ωopt is notably affected by changing all three parameters LL, PL and FC. For example 10% error
in determining each of these parameters (LL, PL or FC) in the laboratory may cause about 8% error
(MAPE ≈ 8) for prediction of ωopt by derived model. Therefore, by increasing the accuracy in determining
each of these parameters in laboratory, the ωopt predicted by the model will be more accurate.

7. Conclusions
In present study, an attempt has been made to predict the compaction parameters of soils by neural
network simulations using a database consisting of 212 soil samples. Using the same database the
12    A. ARDAKANI AND A. KORDNAEIJ

predictability of the proposed models is statistically given. Furthermore, the sensitivity analyses of the
obtained models were used to study the influence of input parameters on models outputs. The results
indicate that:

• The results obtained from GMDH-type neural network in this study agreed well with the measured
γd,max and ωopt. Therefore, reliable predicting capabilities were obtained.
• The proposed GMDH models to predict the compaction parameters are more accurate in compar-
ison with all of the other empirical correlations.
• The sensitivity analysis shows that the LL and PL of soil are the most influential parameters on the
model outputs (γd,max and ωopt).
• The proposed models to predict γd,max is considerably influenced by error in measuring LL value
and the mean absolute percent error (MAPE) increases greatly by changing it. Then it needs more
accuracy to measure this parameter in laboratory.
• The proposed model to predict ωopt is considerably influenced by error in measuring LL, PL and
FC. Then for more accurate prediction of ωopt by proposed GMDH model, it needs more accuracy
to measure each of these parameters in laboratory.

It may thus be concluded that all predictions based on empirical approaches require the determi-
nation of input parameters, which are prone to uncertainties and inaccuracies. Therefore, a correlation
based on all of the soil parameters can be more useful to limit these uncertainties.

Nomenclature

Plastic Limit (%) PL

Root mean square error RMSE
Correlation coefficient R
Sand content SC
Scaled cumulative frequency SCF
Predicted output ti
Average of the predicted outputs t̄i
Input variable X
Vector of output’s value from observation Y
Output parameter Yi
Actual output y
Predicted output ŷ
Optimum water content ωopt
Dry density γd
Maximum dry density γd,max
Vector of unknown coefficients of the quadratic polynomial equation a
Coefficients of the quadratic polynomial equation ai
Mean square error E
Scaled relative error Er
Fine-grained content FC
Quadratic function Gi
Actual output hi
Average of the actual outputs h̄ i
Number of the value considered in cumulative probability P i
Liquid Limit (%) LL
Total numbers of data-sets M
Mean absolute deviation MAD
Mean absolute percent error MAPE
Input parameter mi
Output parameter mj
Total numbers of input variables n

Disclosure statement
No potential conflict of interest was reported by the authors.
 EUROPEAN JOURNAL OF ENVIRONMENTAL AND CIVIL ENGINEERING   13

References
Al-Khafaji, A. N. (1993). Estimation of soil compaction parameters by means of Atterberg limits. Quarterly Journal of
Engineering Geology and Hydrogeology, 26, 359–368. doi:10.1144/GSL.QJEGH.1993.026.004.10
Ardalan, H., Eslami, A., & Nariman-Zadeh, N. (2009). Piles shaft capacity from CPT and CPTu data by polynomial neural
networks and genetic algorithms. Computers and Geotechnics, 36, 616–625. doi:10.1016/j.compgeo.2008.09.003
ASTM D698. (2003). Standard test methods for laboratory compaction characteristics of soil using standard effort. West
Conshohocken, PA: American Society for Testing and Materials (ASTM) International.
Atashkari, K., Nariman-Zadeh, N., Gölcü, M., Khalkhali, A., & Jamali, A. (2007). Modelling and multi-objective optimization
of a variable valve-timing spark-ignition engine using polynomial neural networks and evolutionary algorithms. Energy
Conversion and Management, 48, 1029–1041. doi:10.1016/j.enconman.2006.07.007
Das, B. M. (2010). Principles of geotechnical engineering (7th ed.). Stamford, CT: Cenage Learning.
Edincliler, A., Cabalar, A. F., & Cevik, A. (2013). Modelling dynamic behaviour of sand–waste tires mixtures using Neural
Networks and Neuro-Fuzzy. European Journal of Environmental and Civil Engineering, 17, 720–741. doi:10.1080/19648
189.2013.814552
Farlow, S. J. (1984). Self-organizing method in modelling: GMDH type algorithm (Vol. 54). New York, NY: CRC Press/Marcel
Dekker.
Günaydın, O. (2009). Estimation of soil compaction parameters by using statistical analyses and artificial neural networks.
Environmental Geology, 57, 203–215. doi:10.1007/s00254-008-1300-6
Ivakhnenko, A. G. (1971). Polynomial theory of complex systems. Systems, man and cybernetics. IEEE Transactions on, SMC
-1, 364–378. doi:10.1109/TSMC.1971.4308320
Jamali, A., Nariman-zadeh, N., Darvizeh, A., Masoumi, A., & Hamrang, S. (2009). Multi-objective evolutionary optimization
of polynomial neural networks for modelling and prediction of explosive cutting process. Engineering Applications of
Artificial Intelligence, 22, 676–687. doi:10.1016/j.engappai.2008.11.005
Kalantary, F., Ardalan, H., & Nariman-Zadeh, N. (2009). An investigation on the Su–NSPT correlation using GMDH type neural
networks and genetic algorithms. Engineering Geology, 104, 144–155. doi:10.1016/j.enggeo.2008.09.006
Kalantary, F., & Kordnaeij, A. (2012). Prediction of compression index using artificial neural network. Scientific Research and
Essays, 7, 2835–2848. doi:10.5897/SRE12.297
Kang, F., Li, J. S., Wang, Y., & Li, J. (2016). Extreme learning machine-based surrogate model for analyzing system reliability
of soil slopes. European Journal of Environmental and Civil Engineering, 1–22. doi:10.1080/19648189.2016.1169225
Kolay, E., & Baser, T. (2014). Estimating of the dry unit weight of compacted soils using general linear model and multi-layer
perceptron neural networks. Applied Soft Computing, 18, 223–231. doi:10.1016/j.asoc.2014.01.033
Mohammadzadeh, S. D., Bolouri Bazaz, J., & Alavi, A. M. (2014). An evolutionary computational approach for formulation
of compression index of fine-grained soils. Engineering Applications of Artificial Intelligence, 33, 58–68. doi:10.1016/j.
engappai.2014.03.012
Mola-Abasi, H., Eslami, A., & Tabatabaeishorijeh, P. (2013). Shear wave velocity by polynomial neural networks and genetic
algorithms based on geotechnical soil properties. Arabian Journal for Science and Engineering, 38, 829–838. doi:10.1007/
s13369-012-0525-6
Momeni, M., Nazir, R., Jahed Armaghani, D., & Maizir, H. (2014). Prediction of pile bearing capacity using a hybrid genetic
algorithm-based ANN. Measurement, 57, 122–131. doi:10.1016/j.measurement.2014.08.007
Nariman-Zadeh, N., Darvizeh, A., & Ahmad-Zadeh, G. R. (2003). Hybrid genetic design of GMDH-type neural networks using
singular value decomposition for modelling and prediction of the explosive cutting process. Proceedings of the Institution
of Mechanical Engineers, Part B: Journal of Engineering Manufacture, 217, 779–790. doi:10.1243/09544050360673161
Proctor, R. R. (1933). Fundamental principles of soil compaction. Engineering News Record, 111, 245–248.
Rout, S. K. (2009). Prediction of relative density of sand with particular reference to compaction energy (Doctoral dissertation),
National Institute of Technology, Rourkela.
Sridharan, A., & Nagaraj, H. B. (2005). Plastic limit and compaction characteristics of finegrained soils. Proceedings of the
Institution of Civil Engineers - Ground Improvement, 9, 17–22.
Terzaghi, K., Peck, R. B., & Mesri, G. (1996). Soil mechanics in engineering practice. John Wiley and Sons, New York.
Tokar, S. A., & Johnson, P. A. (1999). Rainfall-runoff modeling using artificial neural networks. Journal of Hydrologic Engineering,
4, 232–239. doi:10.1061/(ASCE)1084-0699(1999)4:3(232)
Yao, X. (1999). Evolving artificial neural networks. Proceedings of the IEEE, 87, 1423–1447. doi:10.1109/5.784219
Žlender, B., Jelušič, P., & Boumezerane, D. (2012). Planning geotechnical investigation using ANFIS. Geotechnical and
Geological Engineering, 30, 975–989. doi:10.1007/s10706-012-9520-7
14    A. ARDAKANI AND A. KORDNAEIJ

Appendix A. The flowchart of proposed method

Figure A1. The flowchart of proposed method.

View publication stats