SPE 88476
Reservoir Porosity and Permeability Estimation from Well Logs using Fuzzy Logic and
Neural Networks
Jong-Se Lim, SPE, Korea Maritime Univ., and Jungwhan Kim, SPE, KODECO Energy Co., Ltd.
Copyright 2004, Society of Petroleum Engineers Inc.
This paper was prepared for presentation at the SPE Asia Pacific Oil and Gas Conference and
Exhibition held in Perth, Australia, 18–20 October 2004.
This paper was selected for presentation by an SPE Program Committee following review of
information contained in a proposal submitted by the author(s). Contents of the paper, as
presented, have not been reviewed by the Society of Petroleum Engineers and are subject to
correction by the author(s). The material, as presented, does not necessarily reflect any
position of the Society of Petroleum Engineers, its officers, or members. Papers presented at
SPE meetings are subject to publication review by Editorial Committees of the Society of
Petroleum Engineers. Electronic reproduction, distribution, or storage of any part of this paper
for commercial purposes without the written consent of the Society of Petroleum Engineers is
prohibited. Permission to reproduce in print is restricted to a proposal of not more than 300
words; illustrations may not be copied. The proposal must contain conspicuous
acknowledgment of where and by whom the paper was presented. Write Librarian, SPE, P.O.
Box 833836, Richardson, TX 75083-3836, U.S.A., fax 01-972-952-9435.
Abstract
Petroleum reservoir characterization is a process for
quantitatively describing various reservoir properties in spatial
variability using all the available field data. Porosity and
permeability are the two fundamental reservoir properties
which relate to the amount of fluid contained in a reservoir
and its ability to flow. These properties have a significant
impact on petroleum fields operations and reservoir
management. In un-cored intervals and well of heterogeneous
formation, porosity and permeability estimation from
conventional well logs has a difficult and complex problem to
solve by statistical methods. This paper suggests an intelligent
technique using fuzzy logic and neural network to determine
reservoir properties from well logs. Fuzzy curve analysis
based on fuzzy logics is used for selecting the best related well
logs with core porosity and permeability data. Neural network
is used as a nonlinear regression method to develop
transformation between the selected well logs and core
measurements. The technique is demonstrated with an
application to the well data in offshore Korea. The results
show that the technique can make more accurate and reliable
reservoir properties estimation compared with conventional
computing methods. This intelligent technique can be utilized
a powerful tool for reservoir characterization from well logs in
oil and natural gas development projects.
Introduction
Reservoir characterization is a process of describing various
reservoir characteristics using all the available data to provide
reliable reservoir models for accurate reservoir performance
prediction. Reservoir characterization plays a crucial role in
modern reservoir management. The reservoir characteristics
include pore and grin size distributions, permeability, porosity,
facies distribution, and depositional environment. The types of
data to need for describing the characteristics are core data,
well logs, well tests, production data and seismic survey.
Especially well log data can provide valuable but indirect
information about mineralogy, texture, sedimentary structures
and fluid content of a reservoir. Generally, well logs appear to
be continuous information with intensive vertical resolutions.
Reservoir porosity and permeability are the two
fundamental rock properties which relate to the amount of
fluid contained in a reservoir and its ability to flow when
subjected to applied pressure gradients. These properties have
a significant impact on petroleum fields operations and
reservoir management. In un-cored intervals and well, the
reservoir description and characterization methods utilizing
well logs represent a significant technical as well as economic
advantage because well logs can provide a continuous record
over the entire well where coring is impossible.
However, porosity and permeability estimation from
conventional well logs in heterogeneous formation has a
difficult and complex problem to solve by conventional
statistical methods. This paper suggests an intelligent
technique for reservoir characterization using fuzzy logic and
neural network to determine reservoir properties from well
logs. Simple cross-plotting each input against the output may
give an indication of the quality of linear or multiple linear
regression models that could be formed. For more complicated
relationships found in many oil field problems, such simple
tools often do not provide adequate solutions. Fuzzy ranking
algorithm can be used to select inputs best suited for
predicting the desired output. Fuzzy curve analysis based on
fuzzy logics is used for selecting the best related input (well
logs) with output (core porosity and permeability).
Parametric methods like statistical regression require the
assumption and satisfaction of multi-normal behavior and
linearity. Therefore, neural network as a non-linear and non-
parametric tool is becoming increasingly popular in well log
analysis. Neural network is a computer model that attempts to
mimic simple biological learning processes and simulate
specific functions of human nervous system. Neural network
can be used as a nonlinear regression method to develop
transformation between the selected well logs and core
analysis data.
Fuzzy Curve Analysis
A global prioritizing technique called fuzzy ranking is used
to select well logs to correlate with core measurements. Fuzzy
ranking is a tool to select variables that are globally related. It
also can be used to select neural network inputs by filtering
2 SPE 88476
the noise in the dataset. The significant inputs to the neural
network are identified using fuzzy curves that can identify
relationships between an available parameter and variables in
noisy data sets1.
Consider a data pair (x, y) where x is the event and y is the
reactions. The problem is to predict y when x changes slightly,
in a neighborhood close to x. The fuzzy membership function
of (x, y) gives a local prediction of y according to the
information from only (x, y). The fuzzification of the data is
done with Gaussian function. Fuzzy membership function is
defined as Eq. (1).
  xi − x 2 
Fi ( x) = exp −    ⋅ yi (1)
  b  
Where b defines the shape of the fuzzy membership curves
and is about 10% of data set range. A fuzzy curve function is
used to rank noisy data. The fuzzy curve function gives a
global prediction y because it consists of the sum of the local
predictions (fuzzy membership functions). Fuzzy curve
function is defined as Eq. (2).
n
∑ F ( x) i Where y is the output variable, x is input variable, w and v are
FC ( x) = n
i =1
(2)
∑ F ( x) / y
i =1
i i
The two fuzzy curves resulting from defuzzification of the
fuzzified data in Fig. 1 are shown in Fig. 21. As seen in Fig. 2,
the random data set has a no-slope dashed best-fit line while
the random data set plus the x0.5 trend has a best-fit line that
has a range of about 0.85. The range of fuzzy curves can be
used to identify related variables in noisy data sets and rank
the input variables for further analysis. The selected well logs
then can serve as inputs to regression or neural network to
develop multivariate correlations with core measurements.
Neural Networks
Neural networks have been successfully used in a variety of
related petroleum engineering applications such as reservoir
characterization, optimal design of stimulation treatments, and
optimization of field operations2,3. The fundamental
processing element of a neural network is a neuron. Basically,
a biological neuron receives inputs from other sources,
combines them in some way, performs a generally nonlinear
operation on the result, and then outputs the result. A typical
neuron contains a cell body, dendrites, and an axon2. Fig. 3 is
a schematic diagram of a biological neuron. An artificial
neural network is a computer model that attempts to mimic
simple biological learning processes and simulate specific
functions of natural neurons in human nervous system. It
learns from examples or experiences, and is extremely useful
in solving pattern classification and mapping problem. The
training or learning phase is an essential starting point for use
of neural networks. This process requires training patterns
consisting of a number of input signals paired with target
signals. The inputs are presented to the network and the
corresponding outputs are calculated with the aim of
minimizing the model error, which is the total difference
between calculated outputs and target signals. The back
propagation algorithm utilizing the gradient descent method is
the most commonly used method to reduce model error. The
training process creates a set of parameters that can be used
for predicting property values in situations where the actual
output is unknown.
A typical back propagation neural network (BPNN)
contains of three layers: input, hidden, and output layers. Each
layer is made of a number of processing elements or neurons.
Each neuron is connected to every neuron in the preceding
layer by a simple weighted link. BPNN requires the use of
training patterns, and involves a forward propagation step
followed by a backward propagation step. The forward
propagation step sends input signals through the neurons at
each layer resulting in an output value. BPNN uses the
following mathematical function4,5:
 n2
 n1

y = f  w0 + ∑ w j f j  v0 j + ∑ vij xi  (3)
 j =1  i =1 
the connection weights, n1 is the dimension of the input vector
and n2 is the number of hidden neurons. The backward
propagation step calculates the error vector by comparing the
calculated outputs and the target values. New sets of
connection weights are iteratively calculated based on the
error values until a minimum overall error is obtained. Fig. 4
shows a schematic diagram of back propagation neural
network5.
The connection weights are analyzed after training. These
weights relate to the average contributions of each input log to
the network4:
n2
∑w
j =1
ij
Ci = n1 n 2
(4)
∑∑ w
k =1 j =1
kj
Where Ci is the average contribution of input variable i, wij is
the connection weight from input neuron i to hidden neuron j.
This intelligent computing technique can help engineers in
solving problems which have not been solved by traditional
and conventional computing methods. Neural networks do not
require the specification of a structural relationship between
the inputs and outputs unlike statistical regression analysis.
Neural networks are used as a nonlinear regression tool to
develop transformation between well logs and core analysis
data. Such a transformation can be used for estimating
porosity and permeability in un-cored intervals or wells.
Recent comparison studies have shown that BPNN models
SPE 88476
may be more accurate than conventional methods and
statistical regression for reservoir properties estimation2,4,5-8.
Application
The intelligent technique using fuzzy logic and neural network
is demonstrated with an application to the well data of Well A,
Block K in offshore Korea. 13.25m of core was recovered and
47 core porosity and permeability values were measured in
this well. Fig. 5 shows the histogram and descriptive statistics
for core measurements. The following 8 conventional well
logs were considered for analysis: neutron log (NPHI), sonic
log (DT), gamma ray log (GR), caliper log (CAL), laterolog
deep (LLD), laterolog shallow (LLS), density log (RHOB),
and spontaneous potential log (SP). The well log data are
shown in Fig. 6.
The first step is to determine the strength of relationships
between the variables for selecting the best related well logs
with core porosity and permeability data. We constructed the
cross plots between well logs and core measurements, but
found weak correlation based on correlation coefficients and
visual observations. Next, fuzzy curve analysis based on fuzzy
logic was utilized to analysis correlations between the
variables. Normalized data by the maximum-minimum
normalization equation were used for fuzzy curves generation.
Fig. 7 shows the fuzzy ranked porosity and permeability
curves for each well log. These fuzzy curves could identify
visual relationships between core measurements and well logs
from noisy data sets. Fuzzy curve analysis could help to select
the best related well logs with core analysis data as inputs for
regressions and neural networks. The ranges of fuzzy ranked
curves were used as the ranking criteria. The results of
analyzing porosity and permeability fuzzy curves are tabulated
in Table 1 and Table 2, respectively. We selected six well logs
(NPHI, CAL, LLD, LLS, RHOB, and SP) for porosity
estimation. NPHI, DT, GR, LLD, RHOB, and SP were chosen
for permeability model.
For a comparative study, both multiple variable regressions
and neural networks were applied to the selected well log data
and the computed results were compared with core measured
porosity and permeability. The neural networks were trained
by a training set with six well logs and core analysis data.
Using the same data, we developed the porosity and
permeability models by multiple variable regressions. The
ability of a regression model to predict the property extremes
is enhanced through a weighting scheme of the high and low
values. But because of this, the predictor can become unstable
and also statistically biased.
The contribution of each log for porosity model is shown
in Fig. 8. NPHI contributed the most to the neural network,
while LLD contributed the least amount. Multiple regressions’
correlation coefficient of porosity in Fig. 9 is 0.7640 while
neural network has a correlation coefficient of 0.9993.
Estimated reservoir porosity results from well logs by each
method are shown in Fig. 10. Fig. 11 presents the computed
porosity and core porosity versus depth. The regression model
gives the best results on the average while neural network
provided more accurate results compared with multiple
regressions. Fig. 11 shows the average contribution of each
well log data to neural network for permeability model. DT
was the most contributed log to the network. The correlation
3
coefficients for the permeability by regression and neural
network models compared with measured core data were
0.5654 and 0.9998, respectively (Fig. 12). Fig. 13 shows the
estimated permeability and core measured permeability versus
depth. Multiple regression under-estimates higher permeability
values while neural network shows better consistency in
following the actual trend in permeability variation. It was
shown in these results that neural network performs better than
multiple regression method in estimating reservoir porosity
and permeability from well logs.
Conclusions
In this study, the intelligent technique is used to estimate
reservoir porosity and permeability from conventional well
logs. Fuzzy curve analysis based on fuzzy logics can be used
for selecting the best related parameters with reservoir
properties. Excellent correlation coefficients have been
obtained for porosity and permeability using neural network
models.
The techniques using fuzzy logic and neural network can
make more accurate and reliable reservoir properties
estimation compared with conventional methods. This
intelligent technique can be utilized a powerful tool for
reservoir characterization from well logs in petroleum
industry.
References
1. Weiss, W.W., Weiss, J.W., and Weber, J.: “Data Mining at a
Regulatory Agency to Forecast Waterflood Recovery,” paper
SPE 71057 presented at the 2001 SPE Rocky Mountain
Petroleum Technology Conference held in Keystone, Colorado,
21-23 May.
2. Mohaghegh, S.: “Virtual-Intelligence Applications in Petroleum
Engineering: Part I -Artificial Neural Networks,” Journal of
Petroleum Technology (Sep. 2000) 52, 64-73.
3. Tamhane, D., Wong, P.M., Aminzadeh, F., and Nikravesh, M.
“Soft Computing for Intelligent Reservoir Characterization,”
paper SPE 59397 presented at the 2000 SPE Asia Pacific
Conference on Integrated Modelling for Asset Management held
in Japan, 25-26 April.
4. Wong, P.M., Henderson, D.J., and Brooks, L.J.: “Reservoir
Permeability Determination from Well Log Data using Artificial
Neural Networks: An Example from the Ravva Field, Offshore
India,” paper SPE 38034 presented at the 1997 SPE Asia Pacific
Oil and Gas Conference held in Kuala Lumpur, Malaysia, 14-16
April.
5. Lim, Jong-Se: “Reservoir Permeability Determination using
Artificial Neural Network,” Journal of the Korean Society for
Geosystem Engineering (2003) 40, 232-238.
6. Balan, B., Mohaghegh, S., and Ameri, S.: “State-Of-The-Art in
Permeability Determination From Well Log Data: Part 1-A
Comparative Study, Model Development,” paper SPE 30978
presented at the 1995 SPE Eastern Regional Conference &
Exhibition held in Morgantown, West Virginia, 17-21 Sep.
7. Soto B., R., Ardila, J.F., Ferneynes, H., and Bejarano, A.: “Use
of Neural Networks to Predict the Permeability and Porosity of
Zone “C” of the Cantagallo Field in Colombia,” paper SPE
38134 presented at the 1997 SPE Petroleum Computer
Conference held in Dallas, TX, 8-11 June.
8. Malki, H.A, Baldwin, J.L., and Kwari, M.A.: “Estimating
Permeability by Use of Neural Networks in Thinly Bedded
Shaly Gas Sands,” SPE Computer Application (April 1996) 8,
58-62.
4 SPE 88476

Table 1-Result of fuzzy curve analysis for core porosity

Range of fuzzy ranked

Well Logs porosity rank
Neutron log (NPHI) 0.698 4
Sonic log (DT) 0.203 8
Gamma ray log (GR) 0.286 7
Caliper log (CAL) 0.840 1
Laterolog deep (LLD) 0.812 3
Laterolog shallow (LLS) 0.825 2
Density log (RHOB) 0.529 5
Spontaneous potential log (SP) 0.436 6

Table 2-Result of fuzzy curve analysis for core permeability

Range of fuzzy ranked

Well Logs permeability rank
Neutron log (NPHI) 0.371 4
Sonic log (DT) 0.523 1
Gamma ray log (GR) 0.441 3
Caliper log (CAL) 0.221 8
Laterolog deep (LLD) 0.350 6
Laterolog shallow (LLS) 0.285 7
Density log (RHOB) 0.491 2
Spontaneous potential log (SP) 0.352 5

(a)

(b)

Fig. 1-Conventional cross plot of data sets

(a) A random data set (0-1), (b) A random data set plus a square root trend
SPE 88476 5

(b)

(a)

Fig. 2-Fuzzy curves generated from data sets

(a) A random data set (0-1), (b) A random data set plus a square root trend

Fig. 3-Schematic diagram of biological neuron

6 SPE 88476

Input Layer Hidden Layer Output Layer y

X V Z W Y

f ' ( NET Z ) f ' ( NET Y )

δZ δY E

d
α α
X X

∆V ∆W

Input Layer Hidden Layer Output Layer

' y'
X Z' ' Y'
V '
W

Fig. 4-Block diagram of back propagation neural network algorithm

Fig. 5-Histogram and descriptive statistics for core measurements

Fig. 6-Well log data of Well A, Block K in offshore Korea

SPE 88476 7

(a)
(a) (b)
(b)
1.0
1.0 1.0
1.0

0.8
0.8 0.8
0.8

Value

Value
RankedValue

RankedValue
0.6
0.6 0.6
0.6
FuzzyRanked

FuzzyRanked
0.4
0.4 0.4
0.4
Fuzzy

Fuzzy
0.2
0.2 0.2
0.2
porosity
porosity porosity
porosity
permeability
permeability permeability
permeability
0.0
0.0 0.0
0.0
0.0
0.0 0.2
0.2 0.4
0.4 0.6
0.6 0.8
0.8 1.0
1.0 0.0
0.0 0.2
0.2 0.4
0.4 0.6
0.6 0.8
0.8 1.0
1.0
Neutron
NeutronLog
Log Sonic
SonicLog
Log

(c)
(c) (d)
(d)
1.0
1.0 1.0
1.0

0.8
0.8 0.8
0.8
Value

Value
RankedValue

RankedValue
0.6
0.6 0.6
0.6
FuzzyRanked

FuzzyRanked

0.4
0.4 0.4
0.4
Fuzzy

Fuzzy

0.2
0.2 0.2
0.2
porosity
porosity porosity
porosity
permeability
permeability permeability
permeability
0.0
0.0 0.0
0.0
0.0
0.0 0.2
0.2 0.4
0.4 0.6
0.6 0.8
0.8 1.0
1.0 0.0
0.0 0.2
0.2 0.4
0.4 0.6
0.6 0.8
0.8 1.0
1.0
Gamma
GammaRay
RayLog
Log Caliper
CaliperLog
Log

(e)
(e) (f)
(f)
1.0
1.0 1.0
1.0

0.8
0.8 0.8
0.8
Value

Value
RankedValue

RankedValue

0.6
0.6 0.6
0.6
FuzzyRanked
FuzzyRanked

0.4
0.4 0.4
0.4
Fuzzy

Fuzzy

0.2
0.2 0.2
0.2
porosity
porosity porosity
porosity
permeability
permeability permeability
permeability
0.0
0.0 0.0
0.0
0.0
0.0 0.2
0.2 0.4
0.4 0.6
0.6 0.8
0.8 1.0
1.0 0.0
0.0 0.2
0.2 0.4
0.4 0.6
0.6 0.8
0.8 1.0
1.0
LaterologDeep
Laterolog Deep LaterologShallow
Laterolog Shallow

(g)
(g) (h)
(h)
1.0
1.0 1.0
1.0

0.8
0.8 0.8
0.8
Value

Value
RankedValue

RankedValue

0.6
0.6 0.6
0.6
FuzzyRanked

FuzzyRanked

0.4
0.4 0.4
0.4
Fuzzy

Fuzzy

0.2
0.2 0.2
0.2
porosity
porosity porosity
porosity
permeability
permeability permeability
permeability
0.0
0.0 0.0
0.0
0.0
0.0 0.2
0.2 0.4
0.4 0.6
0.6 0.8
0.8 1.0
1.0 0.0
0.0 0.2
0.2 0.4
0.4 0.6
0.6 0.8
0.8 1.0
1.0
Density
DensityLog SP
Log SPLog
Log

Fig. 7-Fuzzy ranked porosity and permeability curves for well logs
8 SPE 88476

SP log
11.9% Neutron log
25.4%

Density log
22.2%

Caliper log
15.1%
Laterolog
Laterolog Deep
Shallow
11.8%
13.5%
Fig. 8-Average contribution of each input well log data to neural network for porosity model

(a)
(a) (b)
(b)
0.20 0.20
0.20 0.20
Correlation coefficient = 0.7640 Correlation coefficient = 0.9993
Correlation coefficient = 0.7640 Correlation coefficient = 0.9993

0.15 0.15
0.15 0.15
Estimated porosity

Estimated porosity
Estimated porosity

Estimated porosity
0.10 0.10
0.10 0.10

0.05 0.05
0.05 0.05

0.00 0.00
0.00 0.00
0.00 0.05 0.10 0.15 0.20 0.00 0.05 0.10 0.15 0.20
0.00 0.05 0.10 0.15 0.20 0.00 0.05 0.10 0.15 0.20
Meas ured poros ity Meas ured poros ity
Meas ured poros ity Meas ured poros ity

Fig. 9-Cross plots of core porosity and estimated porosity (a) by multiple regressions (b) by neural network

(a) Porosity
Porosity (b) Porosity
Porosity
0.0 0.1 0.2 0.3 0.0 0.1 0.2 0.3
0.0 0.1 0.2 0.3 0.0 0.1 0.2 0.3
2347 2347
2347 2347

2349 2349
2349 2349

2351 2351
2351 2351

2353 2353
2353 2353
Depth(m)

Depth(m)
Depth(m)

Depth(m)

2355 2355
2355 2355

2357 2357
2357 2357

2359 2359
2359 2359

2361 2361
2361 2361

2363 2363
2363 2363
Core poros ity Es timated poros ity Core poros ity Es timated poros ity
Core poros ity Es timated poros ity Core poros ity Es timated poros ity

Fig. 10-Estimated reservoir porosity from well logs (a) by multiple regressions (b) by neural network
SPE 88476 9

SP log Neutron log

11.1% 13.5%
Density log
12.3%

Sonic log
24.2%
Laterolog Deep
16.1%

Gamma ray log

22.9%
Fig. 11-Average contribution of each input well log data to neural network for permeability model

(a)
(a) (b)
(b)
100 100
100 100
Correlation coefficient = 0.5654 Correlation coefficient = 0.9998
Correlation coefficient = 0.5654 Correlation coefficient = 0.9998

75 75
Estimated permeability(md)

Estimated permeability(md)
75 75
Estimated permeability(md)

Estimated permeability(md)
50 50
50 50

25 25
25 25

0 0
0 0
0 25 50 75 100 0 25 50 75 100
0 25 50 75 100 0 25 50 75 100
Meas ured permeability (md) Meas ured permeability (md)
Meas ured permeability (md) Meas ured permeability (md)

Fig. 12-Cross plots of core permeability and estimated permeability (a) by multiple regressions (b) by neural network

(a) Permeability(md)
Permeability(md) (b) Permeability(md)
Permeability(md)
0 40 80 120 0 40 80 120
0 40 80 120 0 40 80 120
2347 2347
2347 2347

2349 2349
2349 2349

2351 2351
2351 2351

2353 2353
2353 2353
Depth(m)

Depth(m)
Depth(m)

Depth(m)

2355 2355
2355 2355

2357 2357
2357 2357

2359 2359
2359 2359

2361 2361
2361 2361

2363 2363
2363 2363
Core permeability Es timated permeability Core permeability Es timated permeability
Core permeability Es timated permeability Core permeability Es timated permeability

Fig. 13-Estimated reservoir permeability from well logs (a) by multiple regressions (b) by neural network