SPE-195072-MS

Applications of Artificial Neural Networks in the Petroleum Industry: A

Review

Husam H. Alkinani, Abo Taleb T. Al-Hameedi, Shari Dunn-Norman, and Ralph E. Flori, Missouri University of
Science and Technology; Mortadha T. Alsaba, Australian College of Kuwait; Ahmed S. Amer, Newpark Technology
Center/ Newpark Drilling Fluids

Copyright 2019, Society of Petroleum Engineers

This paper was prepared for presentation at the SPE Middle East Oil and Gas Show and Conference held in Manama, Bahrain, 18-21 March 2019.

This paper was selected for presentation by an SPE program committee following review of information contained in an abstract submitted by the author(s). Contents
of the paper have not been reviewed by the Society of Petroleum Engineers and are subject to correction by the author(s). The material does not necessarily reflect
any position of the Society of Petroleum Engineers, its officers, or members. Electronic reproduction, distribution, or storage of any part of this paper without the written
consent of the Society of Petroleum Engineers is prohibited. Permission to reproduce in print is restricted to an abstract of not more than 300 words; illustrations may
not be copied. The abstract must contain conspicuous acknowledgment of SPE copyright.

Abstract
Oil/gas exploration, drilling, production, and reservoir management are challenging these days since most
oil and gas conventional sources are already discovered and have been producing for many years. That is
why petroleum engineers are trying to use advanced tools such as artificial neural networks (ANNs) to help
to make the decision to reduce non-productive time and cost.
A good number of papers about the applications of ANNs in the petroleum literature were reviewed
and summarized in tables. The applications were classified into four groups; applications of ANNs in
explorations, drilling, production, and reservoir engineering. A good number of applications in the literature
of petroleum engineering were tabulated. Also, a formalized methodology to apply the ANNs for any
petroleum application was presented and accomplished by a flowchart that can serve as a practical reference
to apply the ANNs for any petroleum application. The method was broken down into steps that can be
followed easily. The availability of huge data sets in the petroleum industry gives the opportunity to use these
data to make better decisions and predict future outcomes. This paper will provide a review of applications
of ANNs in petroleum engineering as well as a clear methodology on how to apply the ANNs for any
petroleum application.

Background
The first neural networks research was by McCulloch and Pitts (1943). Rosenblatt (1957) invented the
perceptron and proved that a perceptron would develop a weight vector that separates the classes. Rosenblatt
(1957) believed that structures of more layers can overcome the limitations of the simple perceptron.
However, there weren't any learning algorithms that can determine the weights for a given calculation
(Mohaghegh, 2000). Few years after, Widrow (1962) developed a network called Adeline. Minsky and
Papert (1969) showed that the single layer perceptron can't elementary calculations problems. After that,
the neural network's research stopped for 20 years (Hertz et al., 1991). Then, Hopfield (1982) proposed
new algorithms, such as backpropagation, that brought life for the neural network's research. Since then,
the neural networks applications has gone viral (Mohaghegh, 2000).
2 SPE-195072-MS

Neural Network Structure

An artificial neural network is "an information-processing system that has certain performance
characteristics in common with biological neural network" (Mohaghegh, 2000). All organisms are made up
from cells. Neurons are the basic building blocks of the nervous system. A typical biological neuron consists
of a cell body, an axon, and dendrites as shown in Figure 1. Information in the cell body enters through the
dendrites. The cell body then provides an output which travels through the axon then to another receiving
neuron, the output from the first neuron becomes an input for the second neuron and so on (Mohaghegh,
2000).

Figure 1—Two Bipolar Neurons (After Mohaghegh, 2000)

The human brain contains 10-500 billion neurons (Rumelhart and McClelland, 1986). These neurons
are divided into sections, each section contains about 500 neural networks (Stubbs, 1988). Each neural
network contains about 100,000 neurons where these neurons are connected to thousands of other neurons
(Mohaghegh, 2000). This structure is behind human's complex behavior. A simple task such as moving
hands, walking, or catching a cup of coffee, requires very complex calculations that sophisticated computer
can't perform but the human brain is able to do them. Although computers are faster than human brains
(human brain cycle is 10 to 100 milliseconds while computer chips cycle is in nanoseconds), the human
brain can still much more perform complex activities than computer due to the sophisticated structures of
the neurons.
Artificial neural networks (ANNs) are a simulation for the biological process explained above. ANNs
are developed based on mathematical models with the following assumptions (Mohaghegh, 2000):
1. The information is processed through elements called neurons.
2. There are connections links between the neurons that let the information to pass through.
3. Each connection links have their own weights.
4. Once the inputs received by the neurons, the neurons will apply an action function to determine the
outputs.
Figure 2 is a schematic of an artificial neuron, the outputs from other neurons are multiplied by the
connection links weights and enter the neuron. The inputs then are summed and the activation function of
the neuron is applied which leads to an output. Thus, a neuron has multiple inputs and only one output. An
artificial neural network consists of one input layer, one or more hidden layers, and one output layer. The
input and output layers are obviously for inputs and outputs. The hidden layer is responsible for extraction
SPE-195072-MS 3

the features from the data (Mohaghegh, 2000). ANNs can be simple three layers as shown in Figure 3, or
ANNs can be more complicated as shown in Figure 4.

Figure 2—Schematic of Artificial Neuron (After Mohaghegh, 2000)

Figure 3—Example of a Simple Neural Network

Figure 4—Example of a Complex Neural Network

4 SPE-195072-MS

How to Successfully Apply ANNs to Any Petroleum Applications

In this section, a methodology of how to successfully apply ANNs to any petroleum applications will be
presented. The focus will be on supervised ANNs since most petroleum applications are based on supervised
training algorithms (Mohaghegh, 2000). Figure 5 shows a summary flowchart for how to successfully apply
ANNs in the petroleum industry.

Figure 5—Flowchart for How to Successfully Apply ANNs in the Petroleum Industry

Input Data Selection and Data Collection

Depending on the application, the input data for ANNs will be different. Inputs can be chosen based on
experimental tests, modeling, simulation, sensitivity analysis, expert opinion, statistical analysis and etc.
Once the input data are chosen, data collection is the next step. Since most applications of oil and gas
industry are supervised, this means data for inputs and outputs should be obtained.

Selection of Training, Testing, and Verification Data

Typically, data are divided into three sections; training, testing, and verification sets. The training data
used to develop the ANN model, the desired output is used to help the network adjust the weights of each
input. The error will backpropagate in the network and adjust the weights until calibration is reached, this
method is called feedforward backpropagation algorithm. It should be noted that the network should not be
overstrained since the network won't be efficient. Testing sets are used to measure the network generalization
and to stop the training when generalization stops improving (Demuth et al., 2007). Finally, the verification
set (data not used to create the network) will be used to evaluate the performance of the network.

Data Normalization
Sometimes, if the input or the output data are too small or too large; therefore, scaling of the data should be
performed (Saeedi et al., 2007; Zabihi et al., 2011). One method of normalizing data to have values between
-1 and 1 is shown in Equation 1 (Demuth et al., 2007).

Eq. 1

Where Xi is the original value of the parameter, is the normalized value of Xi, Xmax and Xmin are the
maximum and the minimum values of Xi, respectively.

Determining the Number of Hidden Layers and Training Function

It is important to evaluate the optimum number of hidden layers and the number of neurons in each hidden
layers. To find the optimum number of hidden layers, iteration should be performed until obtaining the
optimum number of hidden layers. Typically, to obtain the number of neurons in each hidden layer, the
total average absolute deviation (TAAD) or mean square of error (MSE) (or any form of error calculations)
should be calculated such that starting with one neuron until reaching a number of neurons that have the
lowest error.
After evaluating the optimum number of hidden layers and the number of neurons in each hidden
layer, the training function should be chosen so that the error is minimized. Examples of training function
SPE-195072-MS 5

that can be tested are Variable Learning Rate Backpropagation (GDX), Resilient Backpropagation (RP),
Fletcher-Powell Conjugate Gradient (CGF), Scaled Conjugate Gradient (SCG), Levenberg-Marquardt
(LM), Levenberg-Marquardt with Bayesian Regularization (BR), Quasi-Newton (BFG), and One Step
Secant (OS) (Demuth et al., 2007).

Application of Artificial Neural Networks in the Petroleum Industry

ANNs have been used to solve complicated problems in the petroleum industry. ANNs should not be
used to solve mathematical problems or problems that can be modeled analytically since the purpose of
neural networks is to solve complicated problems that can't be solved in conventional modeling tools
due to the complexity of the problem. After reading a good number of papers and case histories in the
petroleum literature, the decision was made to classify the applications into four categories: applications
for exploration, drilling, production, and reservoir.

Exploration
This section gives examples of the applications of ANNs in exploration. This mainly consists of applications
of ANNs of seismic data as shown in Table 1.

Table 1—Application of ANNs in Exploration

Author(s) Application Notes

Used ANNs to extract structural lineaments

Guo et al. (1992) Feature recognition
and lithologic information from seismic data

Used ANNs to successfully identify the

Hansen (1993) Primary reflection identifications
primary reflection from seismic data

Karrenbach et al. (2000) Seismic data processing Used ANNs for seismic data processing

Used ANNs for petro-seismic characterization

Fogg (2000) Petro-seismic characterization
of a 96,000 trace 3D seismic migrated volume

Used ANNs to predict hydrocarbon and

Xiangjun et al. (2000) Hydrocarbon prediction
presented a case history from DaQing field

Sun et al. (2000); Amplitude variation Used ANNs to solve the interpretation problem associated with
Russell et al. (2002) with offset (AVO) AVO since it is hard to distinguish between wet sand and gas sand

Aminzadeh & deGroot (2005) Object detection Used ANNs to detect several seismic objects using seismic data

Parameters determinations Used ANNs to detect line pattern of the direct wave and
Huang et al. (2006)
and seismic pattern detection hyperbola pattern of reflection wave in a seismogram

Kononov et al. (2007) Travel time computation Used ANNs to compute travel times for a complete 3D volume model.

Used ANNs to for velocity picking in the time-

Huang & Yang (2008) Seismic velocity picking
velocity semblance image of seismic data

Used ANNs to detect gas from absorption

Clifford & Aminzadeh (2011) Gas detection
attributes and amplitude in Grand Bay field

Aminzadeh et al. (2011) Micro-seismic Used ANNs to autopick micro-seismic earthquake data

Used ANNs to map high frackability and high

Verma et al. (2012) Mapping
total organic content zones in the Barnett Shale

Amplitude variation with angle Used ANNs to predict AVA to help to evaluate the
Hami-Eddine et al. (2015)
of incidence (AVA) prediction comparative risk between prospects for ranking purposes.

Used ANNs to identify the unconventional

Refunjol et al. (2016) Identifying unconventional potential
potential using seismic inversion in the Eagle Ford

Used ANNs to improve resolution and clarity of seismic data in

Improve resolution and
Ross (2017) the tight sand that has lower porosity, higher bulk density, and
clarity of seismic data
velocity. Also, used a practical example form the Permian Basin
6 SPE-195072-MS

Author(s) Application Notes

Depositional environment Used ANNs to instigate depositional environments and

Ogiesoba & Ambrose (2017)
investigation hydrocarbon sweet-spot distribution in Serbin field in Texas

Canning et al. (2017) Seismic data enhancement Used ANNs for enhancing the frequency spectrum of seismic data

Drilling
ANNs have been utilized in drilling engineering for a long time. Table 2 shows some applications of ANNs
in drilling engineering.

Table 2—Applications of ANNs in Drilling

Author(s) Application Notes

Used ANNs to determine the grade (state

Arehart (1990) Drill bit diagnosis
of wear) of the drill bit while drilling

Used ANNs to model the dynamic behavior of the

Dashevskiy et al. (1999) Real-time drilling dynamic
non-linear, multi0inputs/outputs drilling system

Bilgesu et al. (2001) Drill bit selection Used ANNs to select the "best" bit based on some inputs

Used ANNs to predict bed heights in

Ozbaoglu et al. (2002) Bed height for horizontal wells
horizontal or highly-inclined wellbores

Used ANNs to detect bit bounce that can be used as a proactive approach
Vassallo et al. (2004) Bit bounce detection
to prevent anomalous drilling conditions such as bit whirl and stick-slip

Fruhwirth et al. (2006); Drilling hydraulics Used ANNs to optimize and predict
Wang and Salehi (2015) optimization and prediction drilling hydraulics with a practical example

Moran et al. (2010); Al- Rate of penetration

Used ANNs to predict ROP so that the drill time can be estimated better
AbdulJabbar et al. (2018a) (ROP) prediction

Gidh et al. (2012) Bit wear prediction Used ANNs to predict/ manage bit wear to improve ROP

Used ANNs to predict troubles during the drilling

Lind & Kabirova (2014) Drilling troubles prediction
process using a database on drilling parameters

Used ANNs to predict wellbore instability with case

Okpo et al. (2016) Wellbore instability
history from the Niger Delta oil field in Nigeria

Prediction of mud weight

Ahmadi et al. (2016) Collected data from the literature
at wellbore conditions

; Elkatatny et al. (2016);

Abdelgawad et al. (2018); Drilling fluid rheological properties Used ANNs to predict drilling fluid rheological properties
Al-Azani et al. (2018)

Used multiple artificial intelligence methods

Cristofaro et al. (2017) Mud losses
to find the best treatment for mud losses

Used ANNs to develop a methodology for automatic

Drilling reports
Hoffmann et al. (2018) of sentences written in drilling reports into three tables:
sentence classifications
Events, Symptom, and Action. used data of 303 wells

Li et al. (2018) Lost circulation Used ANNs to predict the risk level of lost circulation while drilling

Formation top
Al-AbdulJabbar et al. (2018b) Used ANNs to predict formation tops while drilling
prediction while drilling

Equivalent circulation
Elzenary et al. (2018) Used ANNs to predict ECD while drilling
density (ECD) prediction

Production
ANNs have been applied in many applications of petroleum production engineering. Table 3 shows some
applications of ANNs in petroleum production engineering.
SPE-195072-MS 7

Table 3—Applications of ANN in Production

Author(s) Application Notes

Thomas & Pointe (1995) Conductive fracture identification Used ANNs to identify conductive fractures

Used ANNs to identify fracture restimulation

Denney (2000) Fracturing restimulation candidates
candidates with case history from Red Oak field

Used ANNs to obtain real-time, well specific,

Faga, & Oyeneyin (2000) Gravel-pack design
grain size distribution for gravel-pack completion.

Developed ANN model to forecast the

Al-Fattah & Startzman (2001) Natural gas production prediction
United States gas production to the Year 2020

Used ANNs to predict casing collapse issues due to reservoir

Salehi et al. (2009) Casing collapse due to production compaction, poroelastic effects, and corrosion. Also,
used an example from a large carbonate oil field in Iran

Adeyemi, & Sulaimon (2012) Wax formation prediction Used ANNs to predict the wax formation

Moradi et al. (2013) Wax disappearance temperature Used experimental and real data of wax precipitation

Costa et al. (2014) History matching Built a reservoir simulation model and used ANN for history matching

Yanfang and Salehi (2014) Re-fracture candidate selection Used real field data from Zhongyuan oilfield

Application of Used "Unified Model" to generate the data

Al-Naser et al. (2016)
multiphase flow patterns and used experimental data for testing

Ghahfarokhi et al. (2018) Prediction of gas production Used ANNs to predict gas production in the Marcellus Shale

Khan et al. (2018) Oil rate prediction Used ANNs to predict the optimum production rate

Luo et al. (2018) Production optimization Used ANNs to optimize the production in the Bakken Shale

Used ANNs to minimize the error in predicting

Nande (2018) Hydraulic fracturing
closure pressure for hydraulic fracturing analysis

Used ANNs to optimize the completion and to protect

Nieto et al. (2018) Completion optimization
parent well in the Montney formation in British Columbia

Used ANNs to optimize well spacing

Pankaj (2018) Well spacing and well stacking
and well tacking in the Permian Basin

Sidaoui et al. (2018) Carbonate acidizing Used ANNs to predict the optimum injection rate of carbonate acidizing

Flowing bottom hole

Tariq (2018) Used ANNs to predict flowing bottom hole pressure
pressure prediction

Al-Dogail et al (2018); Used ANNs to predict inflow performance

Inflow performance (IPR) prediction
Basfar et al. (2018) of gas field and for vertical oil well

Reservoir
There are many applications of ANNs in reservoir engineering. Table 4 shows a summary of the main
applications of ANNs in reservoir engineering.

Table 4—Applications of ANNs in Reservoir

Author(s) Application Notes

An & Moon (1993);

Reservoir characterization Used ANNs for reservoir characterization
Long et al. (2016)

Yang & Kim (1996) Rock properties Used accelerated ANNs to find rock properties

Used ANNs to find the optimum relationship between pressure,

Denney (2001) Reservoir monitoring
saturation, and seismic data. The model was applied to the Statfjord field

Alcocer & Rodrigues (2001) Fluid properties Used ANNs to estimate fluid properties using nuclear magnetic resonance

Used ANNs to analyzed pressure transient

Denney (2003) Well testing
data from an anisotropic faulted reservoir
8 SPE-195072-MS

Author(s) Application Notes

Uncertainties in Used ANNs in Monte Carlo simulations to eliminate to

Denney (2006)
reservoir performance generate the probability distribution of possible outcomes.

Used ANNs to predict formation porosity

Elshafei & Hamada (2007) porosity and water saturation
and water saturation from well logs

Ayoub et al. (2007) Viscosity correlations Used ANNs to evaluate the below bubble point viscosity correlations

Al-Bulushi et al (2007); Used ANNs to predict water saturation for

Water saturation prediction
Khan et al. (2018) sandstone reservoirs using conventional well logs

Used ANNs to estimate gas/oil ratio (GOR)

Hegeman et al. (2009) Downhole fluid analysis
from real-time downhole fluid samples

Zabihi et al. (2011) Permeability damage prediction Used experimental data of Berea sandstone cores

Kohli & Arora (2014) Permeability prediction Used ANNs to predict permeability from well logs

Ma and Gomez (2015) Predictions of hydrocarbon resource Used real field data with some statistical methods and ANN

Drilling system Used multiple artificial intelligence techniques-

Bello et al. (2016)
design and operation including ANNs- to design drilling and operation systems

Used ANNs to successfully synthesize

Li et al. (2018) Geomechanical characterization
compressional and shear travel time logs

Used ANNs to perform N-dimensional

Dang et al. (2018) EOR
interpolation of relative permeability

Used ANNs to correlate between static and dynamic

Rashidi et al (2018) Elastic modulus modulus of limestone formations. Also, used an
example from two formations Asmari and Sarvak in Iran

Hadi & Nygaard (2018) Shear wave estimation Used ANNs to predict shear wave in carbonate reservoirs

Rashidi & Asadi,(2018) Pore pressure estimation Used ANNs to predict formation pore pressure from drilling data

Used ANNs to develop a screening tool for

Hamam & Ertekin (2018) CO2 injection
CO2 injection in naturally fractured reservoirs.

Hasan et al. (2018) Temperature distribution Used ANNs to predict thermal distribution in thermal EOR methods

Conclusions
ANNs are very useful tool which can be used to solve problems that are hard to be modeled analytically.
ANNs have been applied to many petroleum applications and have shown a reasonable accuracy. After
reviewing a good number of papers about the applications of ANNs in the petroleum industry, the following
conclusions were made:

• Due to the availability of huge historical data in the petroleum industry, this data can be used for
predictions of future outcomes to help to make better decisions. Future predictions are always
challenging, due to the large uncertainties in the future. ANNs can be used for future prediction
or real-time predictions with a good accuracy so that the decision makers can prepare to solve the
problems ahead of time.
• Some petroleum engineering problems are hard to be solved analytically. Thus, ANNs can be used
to solve such problems with a good accuracy.
• Many application of ANNs from the literature were summarized in this paper. Also, the applications
were divided and tabulated into four categories; applications for exploration, drilling, production,
and reservoir.
• Practical guidelines have been developed that when used with the accompanying flow chart will
serve as a quick reference guide to apply the ANNs for any petroleum application. This paper
provides a clear methodology on how to successfully apply the DTA which can serve as a reference
for any future ANNs applications in the petroleum industry.
SPE-195072-MS 9

References
Abdelgawad, K., Elkatatny, S., Mousa, T., Mahmoud, M., & Patil, S. (2018, August 16). Real Time Determination of
Rheological Properties of Spud Drilling Fluids Using a Hybrid Artificial Intelligence Technique. Society of Petroleum
Engineers. doi:10.2118/192257-MS.
Adeyemi, B. J., & Sulaimon, A. A. (2012, January 1). Predicting Wax Formation Using Artificial Neural Network. Society
of Petroleum Engineers. doi:10.2118/163026-MS.
Al-AbdulJabbar, A., Elkatatny, S., Mahmoud, M., & Abdulraheem, A. (2018a, August 16). Predicting Rate of Penetration
Using Artificial Intelligence Techniques. Society of Petroleum Engineers. doi:10.2118/192343-MS.
Al-AbdulJabbar, A., Elkatatny, S., Mahmoud, M., & Abdulraheem, A. (2018b, August 16). Predicting Formation Tops
While Drilling Using Artificial Intelligence. Society of Petroleum Engineers. doi:10.2118/192345-MS.
Al-Azani, K., Elkatatny, S., Abdulraheem, A., Mahmoud, M., & Al-Shehri, D. (2018, August 16). Real Time Prediction
of the Rheological Properties of Oil-Based Drilling Fluids Using Artificial Neural Networks. Society of Petroleum
Engineers. doi:10.2118/192199-MS.
Al-Bulushi, N., Araujo, M., Kraaijveld, M., & Jing, X. D. (2007, January 1). Predicting Water Saturation Using Artificial
Neural Networks (ANNs). Society of Petrophysicists and Well-Log Analysts.
Alcocer, Y., & Rodrigues, P. (2001, January 1). Neural Networks Models for Estimation of Fluid Properties. Society of
Petroleum Engineers. doi:10.2118/69624-MS.
AL-Dogail, A. S., Baarimah, S. O., & Basfar, S. A. (2018, August 16). Prediction of Inflow Performance Relationship of
a Gas Field Using Artificial Intelligence Techniques. Society of Petroleum Engineers. doi:10.2118/192273-MS.
Al-Fattah, S. M., & Startzman, R. A. (2001, January 1). Predicting Natural Gas Production Using Artificial Neural
Network. Society of Petroleum Engineers. doi:10.2118/68593-MS.
Aminzadeh, F., & deGroot, P. (2005, January 1). A Neural Networks Based Seismic Object Detection Technique. Society
of Exploration Geophysicists.
Aminzadeh, F., Maity, D., Tafti, T. A., & Brouwer, F. (2011, January 1). Artificial Neural Network Based Autopicker For
Micro-earthquake Data. Society of Exploration Geophysicists.
An, P., & Moon, W. M. (1993, January 1). Reservoir Characterization Using Feedforward Neural Networks. Society of
Exploration Geophysicists.
Arehart, R. A. (1990, July 1). Drill-Bit Diagnosis With Neural Networks. Society of Petroleum Engineers.
doi:10.2118/19558-PA.
Ayoub, M. A., Raja, A. I., & Almarhoun, M. (2007, January 1). Evaluation Of Below Bubble Point Viscosity Correlations
& Construction of a New Neural Network Model. Society of Petroleum Engineers. doi:10.2118/108439-MS.
B. Widrow, "Generalization and Information Storage in Networks of Adaline ‘Neurons’," in Self-Organizing Systems,
symposium proceedings, M.C. Yovitz, G.T. Jacobi, and G. Goldstein, eds., pp.435–461, Spartan Books, Washington,
DC, 1962.
Basfar, S., Baarimah, S. O., Elkatany, S., AL-Ameri, W., Zidan, K., & AL-dogail Ala. (2018, August 16). Using Artificial
Intelligence to Predict IPR for Vertical Oil Well in Solution Gas Derive Reservoirs: A New Approach. Society of
Petroleum Engineers. doi:10.2118/192203-MS.
Bello, O., Teodoriu, C., Yaqoob, T., Oppelt, J., Holzmann, J., & Obiwanne, A. (2016, August 2). Application of Artificial
Intelligence Techniques in Drilling System Design and Operations: A State of the Art Review and Future Research
Pathways. Society of Petroleum Engineers. doi:10.2118/184320-MS.
Bilgesu, H. I., Al-Rashidi, A. F., Aminian, K., & Ameri, S. (2001, January 1). An Unconventional Approach for Drill-Bit
Selection. Society of Petroleum Engineers. doi:10.2118/68089-MS.
Canning, A., Moulière-Reiser, D., Weiss, Y., Malkin, A., Phillip, E., Grinberg, N., Yehezkel, V. (2017, October 23). Neural
networks approach to spectral enhancement. Society of Exploration Geophysicists.
Clifford, A., & Aminzadeh, F. (2011, January 1). Gas Detection From Absorption Attributes And Amplitude Versus Offset
With Artificial Neural Networks In Grand Bay Field. Society of Exploration Geophysicists.
Dang, C., Nghiem, L., Fedutenko, E., Gorucu, E., Yang, C., & Mirzabozorg, A. (2018, September 17). Application
of Artificial Intelligence for Mechanistic Modeling and Probabilistic Forecasting of Hybrid Low Salinity Chemical
Flooding. Society of Petroleum Engineers. doi:10.2118/191474-MS.
Dashevskiy, D., Dubinsky, V., & Macpherson, J. D. (1999, January 1). Application of Neural Networks for Predictive
Control in Drilling Dynamics. Society of Petroleum Engineers. doi:10.2118/56442-MS.
Demuth, H., Beale, M., Hagan, M., 2007. Neural Network Toolbox 5 User's Guide. The MathWorks Inc., USA.
Denney, D. (2000, February 1). Artificial Neural Networks Identify Restimulation Candidates. Society of Petroleum
Engineers. doi:10.2118/0200-0044-JPT.
Denney, D. (2001, August 1). Neural Network for Time-Lapse Seismic Reservoir Monitoring. Society of Petroleum
Engineers. doi:10.2118/0801-0044-JPT.
10 SPE-195072-MS

Denney, D. (2003, February 1). Characterizing Partially Sealing Faults - An Artificial Neural Network Approach. Society
of Petroleum Engineers. doi:10.2118/0203-0068-JPT.
Denney, D. (2006, June 1). Treating Uncertainties in Reservoir-Performance Prediction With Neural Networks. Society
of Petroleum Engineers. doi:10.2118/0606-0069-JPT.
Elshafei, M., & Hamada, G. M. (2007, January 1). Neural Network Identification of Hydrocarbon Potential of Shaly Sand
Reservoirs. Society of Petroleum Engineers. doi:10.2118/110959-MS.
Elzenary, M., Elkatatny, S., Abdelgawad, K. Z., Abdulraheem, A., Mahmoud, M., & Al-Shehri, D. (2018, August 16).
New Technology to Evaluate Equivalent Circulating Density While Drilling Using Artificial Intelligence. Society of
Petroleum Engineers. doi:10.2118/192282-MS.
Faga, A. T., & Oyeneyin, B. M. (2000, January 1). Application of Neural Networks for Improved Gravel-Pack Design.
Society of Petroleum Engineers. doi:10.2118/58722-MS.
Fogg, A. N. (2000, January 1). Petro-seismic Classification Using Neural Networks: UK Onshore. Society of Exploration
Geophysicists.
Fruhwirth, R. K., Thonhauser, G., & Mathis, W. (2006, January 1). Hybrid Simulation Using Neural Networks To Predict
Drilling Hydraulics in Real Time. Society of Petroleum Engineers. doi:10.2118/103217-MS.
Ghahfarokhi, P. K., Carr, T., Bhattacharya, S., Elliott, J., Shahkarami, A., & Martin, K. (2018, August 9). A Fiber-Optic
Assisted Multilayer Perceptron Reservoir Production Modeling: A Machine Learning Approach in Prediction of Gas
Production From the Marcellus Shale. Unconventional Resources Technology Conference.
Gholamreza Moradi, Majid Mohadesi, Mohammad Reza Moradi, Prediction of wax disappearance temperature using
artificial neural networks, Journal of Petroleum Science and Engineering, Volume 108, 2013, Pages 74–81, ISSN
0920-4105, http://dx.doi.org/10.1016/j.petrol.2013.06.003.
Gidh, Y. K., Purwanto, A., & Ibrahim, H. (2012, January 1). Artificial Neural Network Drilling Parameter Optimization
System Improves ROP by Predicting/Managing Bit Wear. Society of Petroleum Engineers. doi:10.2118/149801-MS.
Guo, Y., Hansen, R. O., & Harthill, N. (1992, January 1). Artificial Intelligence I Neural Networks In Geophysics. Society
of Exploration Geophysicists.
Hadi, F. A., & Nygaard, R. (2018, August 21). Shear Wave Prediction in Carbonate Reservoirs: Can Artificial Neural
Network Outperform Regression Analysis? American Rock Mechanics Association.
Hamam, H., & Ertekin, T. (2018, August 16). A Generalized Varying Oil Compositions and Relative Permeability
Screening Tool for Continuous Carbon Dioxide Injection in Naturally Fractured Reservoirs. Society of Petroleum
Engineers. doi:10.2118/192194-MS.
Hami-Eddine, K., Klein, P., & de Ribet, B. (2015, December 17). Predicting Reliability of AVA Effects Using Neural
Networks. Society of Exploration Geophysicists.
Hansen, K. V. (1993, January 1). Neural Networks For Primary Reflection Identification. Society of Exploration
Geophysicists.
Hassan, A., Elkatatny, S., Mahmoud, M., Abdulraheem, A., & Hossain, E. (2018, August 16). New Technique to Estimate
Temperature Distribution During Thermal EOR Operations. Society of Petroleum Engineers. doi:10.2118/192350-
MS.
Hegeman, P. S., Dong, C., Varotsis, N., & Gaganis, V. (2009, February 1). Application of Artificial Neural Networks to
Downhole Fluid Analysis. Society of Petroleum Engineers. doi:10.2118/123423-PA.
Hertz, J., Krogh, A., & Palmer, R. G. (1991). Introduction to the theory of neural computation. Reading, California:
Addison-Wesley.
Hoffimann, J., Mao, Y., Wesley, A., & Taylor, A. (2018, September 17). Sequence Mining and Pattern Analysis in Drilling
Reports with Deep Natural Language Processing. Society of Petroleum Engineers. doi:10.2118/191505-MS.
Hopfield, J. (1982). Neural Networks and Physical Systems with Emergent Collective Computational Abilities.
Proceedings of the National Academy of Sciences of the United States of America, 79(8), 2554–2558. Retrieved from
http://www.jstor.org/stable/12175.
Huang, K.-Y., & Yang, J.-R. (2015, December 17). Seismic Velocity Picking using Hopfield Neural Network. Society of
Exploration Geophysicists.
Huang, K.-Y., Pissarenko, J.-D., Chen, K.-J., Lai, H.-L., & Don, A.-J. (2006, January 1). Neural Network For Parameters
Determination And Seismic Pattern Detection. Society of Exploration Geophysicists.
Karrenbach, M., Essenreiter, R., & Treitel, S. (2000, January 1). Multiple Attenuation With Attribute-based Neural
Networks. Society of Exploration Geophysicists.
Khan, M. R., Tariq, Z., & Abdulraheem, A. (2018, August 16). Machine Learning Derived Correlation to Determine
Water Saturation in Complex Lithologies. Society of Petroleum Engineers. doi:10.2118/192307-MS.
Khan, M. R., Tariq, Z., & Abdulraheem, A. (2018, August 16). Utilizing State of the Art Computational Intelligence to
Estimate Oil Flow Rate in Artificial Lift Wells. Society of Petroleum Engineers. doi:10.2118/192321-MS.
SPE-195072-MS 11

Kohli, A., & Arora, P. (2014, January 19). Application of Artificial Neural Networks for Well Logs. International
Petroleum Technology Conference. doi:10.2523/IPTC-17475-MS
Kononov, A., Gisolf, D., & Verschuur, E. (2007, January 1). Application of Neural Networks to Travel-times Computation.
Society of Exploration Geophysicists.
Leite Cristofaro, R. A., Longhin, G. A., Waldmann, A. A., de Sá, C. H. M., Vadinal, R. B., Gonzaga, K. A., & Martins, A.
L. (2017, October 24). Artificial Intelligence Strategy Minimizes Lost Circulation Non-Productive Time in Brazilian
Deep Water Pre-Salt. Offshore Technology Conference. doi:10.4043/28034-MS.
Li, H., He, J., & Misra, S. (2018, September 17). Data-Driven In-Situ Geomechanical Characterization in Shale
Reservoirs. Society of Petroleum Engineers. doi:10.2118/191400-MS.
Li, Z., Chen, M., Jin, Y., Lu, Y., Wang, H., Geng, Z., & Wei, S. (2018, August 21). Study on Intelligent Prediction for Risk
Level of Lost Circulation While Drilling Based on Machine Learning. American Rock Mechanics Association.
Lind, Y. B., & Kabirova, A. R. (2014, October 14). Artificial Neural Networks in Drilling Troubles Prediction. Society
of Petroleum Engineers. doi:10.2118/171274-MS.
Long, W., Chai, D., & Aminzadeh, F. (2016, May 23). Pseudo Density Log Generation Using Artificial Neural Network.
Society of Petroleum Engineers. doi:10.2118/180439-MS.
Luís Augusto Nagasaki Costa, Célio Maschio, Denis José Schiozer, Application of artificial neural networks in a history
matching process, Journal of Petroleum Science and Engineering, Volume 123, 2014, Pages 30–45, ISSN 0920-4105,
http://dx.doi.org/10.1016/j.petrol.2014.06.004.
Luo, G., Tian, Y., Bychina, M., & Ehlig-Economides, C. (2018, August 9). Production Optimization Using Machine
Learning in Bakken Shale. Unconventional Resources Technology Conference.
McCulloch, W.S. & Pitts, W. Bulletin of Mathematical Biophysics (1943) 5: 115. doi.org/10.1007/BF02478259
Minsky, M., & Papert, S. (1969). Perceptrons. An introduction to computational geometry. Cambridge,MA: MIT press.
Mohaghegh, S. (2000, September 1). Virtual-Intelligence Applications in Petroleum Engineering: Part 1—Artificial
Neural Networks. Society of Petroleum Engineers. doi:10.2118/58046-JPT
Mohammad Ali Ahmadi, Seyed Reza Shadizadeh, Kalpit Shah, Alireza Bahadori, An accurate model to predict drilling
fluid density at wellbore conditions, Egyptian Journal of Petroleum, Volume 27, Issue 1, 2018, Pages 1–10, ISSN
1110-0621, http://dx.doi.org/10.1016/j.ejpe.2016.12.002.
Moran, D. P., Ibrahim, H. F., Purwanto, A., & Osmond, J. (2010, January 1). Sophisticated ROP Prediction Technology
Based on Neural Network Delivers Accurate Drill Time Results. Society of Petroleum Engineers. doi:10.2118/132010-
MS.
Mustafa Al-Naser, Moustafa Elshafei, Abdelsalam Al-Sarkhi, Artificial neural network application for multiphase flow
patterns detection: A new approach, Journal of Petroleum Science and Engineering, Volume 145, 2016, Pages
548–564, ISSN 0920-4105, http://dx.doi.org/10.1016/j.petrol.2016.06.029.
Nande, S. (2018, September 17). Application of Machine Learning for Closure Pressure Determination. Society of
Petroleum Engineers. doi:10.2118/194042-STU.
Nieto, J., Janega, G., Batlai, B., & Martinez, H. (2018, August 9). An Integrated Approach to Optimizing Completions
and Protecting Parent Wells in the Montney Formation, N.E.B.C. Unconventional Resources Technology Conference.
Ogiesoba, O., & Ambrose, W. (2017, October 23). Seismic attributes investigation of depositional environments and
hydrocarbon sweet-spot distribution in Serbin field, Taylor group, central Texas. Society of Exploration Geophysicists.
Okpo, E. E., Dosunmu, A., & Odagme, B. S. (2016, August 2). Artificial Neural Network Model for Predicting Wellbore
Instability. Society of Petroleum Engineers. doi:10.2118/184371-MS.
Ozbayoglu, E. M., Miska, S. Z., Reed, T., & Takach, N. (2002, January 1). Analysis of Bed Height in Horizontal and Highly-
Inclined Wellbores by Using Artificial Neuraletworks. Society of Petroleum Engineers. doi:10.2118/78939-MS.
Pankaj, P. (2018, August 9). Characterizing Well Spacing, Well Stacking, and Well Completion Optimization in the
Permian Basin: An Improved and Efficient Workflow Using Cloud-Based Computing. Unconventional Resources
Technology Conference.
Rashidi, M., & Asadi, A. (2018, August 21). An Artificial Intelligence Approach in Estimation of Formation Pore Pressure
by Critical Drilling Data. American Rock Mechanics Association.
Rashidi, M., Hajipour, M., & Asadi, A. (2018, August 21). Correlation Between Static and Dynamic Elastic Modulus of
Limestone Formations Using Artificial Neural Networks. American Rock Mechanics Association.
Refunjol, X., Infante, L., & Bernaez, A. (2016, January 1). Identifying unconventional potential using seismic inversion
and neural networks: An Eagle Ford Shale study. Society of Exploration Geophysicists.
Reza Zabihi, Mahin Schaffie, Hossein Nezamabadi-pour, Mohammad Ranjbar, Artificial neural network for permeability
damage prediction due to sulfate scaling, Journal of Petroleum Science and Engineering, Volume 78, Issues 3–
4,2011,Pages 575–581,ISSN 0920-4105, http://dx.doi.org/10.1016/j.petrol.2011.08.007.
Rosenblatt, F. "The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain."
Psychological Review, vol. 65, no. 6, 1958, pp. 386–408., doi:10.1037/h0042519.
12 SPE-195072-MS

Ross, C. (2017, October 23). Improving resolution and clarity with neural networks. Society of Exploration Geophysicists.
Rumelhart, D. E., & McClelland, J. L. (1986). Parallel distributed processing: Explorations in the microstructure of
cognition: Vol. 1 Foundations. Cambridge, Massachusetts: The Mit Press.
Russell, B., Ross, C., & Lines, L. (2002, January 1). Neural Networks And AVO. Society of Exploration Geophysicists.
Saeed Salehi, Geir Hareland, Keivan Khademi Dehkordi, Mehdi Ganji, Mahmoud Abdollahi,Casing collapse
risk assessment and depth prediction with a neural network system approach, Journal of Petroleum Science
and Engineering, Volume 69, Issues 1–2,2009, Pages 156–162, ISSN 0920-4105, http://dx.doi.org/10.1016/
j.petrol.2009.08.011.
Saeedi, A., Camarda, K. V., & Liang, J.-T. (2007, November 1). Using Neural Networks for Candidate Selection and Well
Performance Prediction in Water-Shutoff Treatments Using Polymer Gels - A Field-Case Study. Society of Petroleum
Engineers. doi:10.2118/101028-PA.
Salaheldin Elkatatny, Zeeshan Tariq, Mohamed Mahmoud, Real time prediction of drilling fluid rheological properties
using Artificial Neural Networks visible mathematical model (white box), Journal of Petroleum Science and
Engineering, Volume 146, 2016, Pages 1202–1210, ISSN 0920-4105, http://dx.doi.org/10.1016/j.petrol.2016.08.021.
Sidaoui, Z., Abdulraheem, A., & Abbad, M. (2018, August 16). Prediction of Optimum Injection Rate for Carbonate
Acidizing Using Machine Learning. Society of Petroleum Engineers. doi:10.2118/192344-MS.
Stubbs, D. Neurocomputers. MD Computing. (1988); 5(3):14–53.
Sun, Q., Castagna, J., & Liu, Z. (2000, January 1). AVO Inversion By Artificial Neural Networks (ANN). Society of
Exploration Geophysicists.
Tariq, Z. (2018, August 16). An Automated Flowing Bottom-Hole Pressure Prediction for a Vertical Well Having
Multiphase Flow Using Computational Intelligence Techniques. Society of Petroleum Engineers. doi:10.2118/192184-
MS.
Thomas, A. L., & La Pointe, P. R. (1995, January 1). Conductive fracture identification using neural networks. American
Rock Mechanics Association.
Vassallo, M., Bernasconi, G., & Rampa, V. (2004, January 1). Bit Bounce Detection Using Neural Networks. Society of
Exploration Geophysicists.
Verma, S., Roy, A., Perez, R., & Marfurt, K. J. (2012, November 4). Mapping High Frackability and High TOC Zones in
The Barnett Shale: Supervised Probabilistic Neural Network vs. Unsupervised Multi-Attribute Kohonen SOM. Society
of Exploration Geophysicists.
Wang Yanfang, Saeed Salehi, Refracture candidate selection using hybrid simulation with neural network and data analysis
techniques, Journal of Petroleum Science and Engineering, Volume 123, 2014, Pages 138–146, ISSN 0920-4105,
http://dx.doi.org/10.1016/j.petrol.2014.07.036.
Wang, Y., & Salehi, S. (2015, March 3). Drilling Hydraulics Optimization Using Neural Networks. Society of Petroleum
Engineers. doi:10.2118/173420-MS.
Xiangjun, Z., Youming, L., & Hong, L. (2000, January 1). Hydrocarbon Prediction Using Dual Neural Network. Society
of Exploration Geophysicists.
Y. Zee Ma, Ernest Gomez, Uses and abuses in applying neural networks for predictions in hydrocarbon resource
evaluation, Journal of Petroleum Science and Engineering, Volume 133, 2015, Pages 66–75, ISSN 0920-4105, http://
dx.doi.org/10.1016/j.petrol.2015.05.006.
Yang, H.-S., & Kim, N.-S. (1996, January 1). Determination of Rock Properties By Accelerated Neural Network. American
Rock Mechanics Association.