SPE-169507-MS

Artificial Intelligence (AI) Assisted History Matching Alireza Shahkarami, Shahab D. Mohaghegh, Vida Gholami, Sayed Alireza Haghighat, West Virginia University

Copyright 2014, Society of Petroleum Engineers This paper was prepared for presentation at the SPE Western North American and Rocky Mountain Joint Regional Meetingheld in Denver, Colorado, USA, 16–18April 2014. 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

History matching is the process of adjusting uncertain reservoir parameters until an acceptable match with the measured

production data is obtained. Complexity and insufficient knowledge of reservoir characteristics makes this process time-

consuming with high computational cost. In the recent years, many efforts mainly referred as assisted history matching have

attempted to make this process faster; nevertheless, the degree of success of these techniques continues to be a subject for

debate.

This study aims to examine the application of a unique pattern recognition technology to improve the time and efforts required

for completing a successful history matching project. The pattern recognition capabilities of Artificial Intelligence and Data

Mining (AI&DM) are used to develop Surrogate Reservoir Model (SRM) for utilization as the engine to drive the history

matching process. SRM is an intelligent prototype of the full-field reservoir simulation model that runs in fractions of a

second. SRM is built using a handful of geological realizations.

In this study, a synthetic reservoir model of a heterogeneous oilfield with 24 production wells and 30 years of production

history was used as the ground truth (the subject and the goal of the history match). An SRM was created to accurately

represent this reservoir model. The history matching process for this field was performed using the SRM and by tuning static

data (Permeability). The result of this study demonstrates the capabilities of SRM for fast track and accurate reproduction of

the numerical model results. Speed and accuracy make SRM a fast and effective tool for assisted history matching.

Keywords: History Matching, Artificial Intelligence, Surrogate Reservoir Model (SRM), AI Assisted History Matching

2 SPE-169507-MS

1. Introduction  

The purpose of reservoir management is to develop strategies to maximize recovery. Reservoir simulation is usually used as a

decision making tool in this procedure. The common concern of reservoir simulation and modeling is accuracy. It is generally

believed that models with higher resolution (in both time and space) are more accurate. Since increase in resolution (time and

space) translates to increase in computational time, a well-known dichotomy arises. On one hand the model must satisfy the

accuracy requirements (high resolution), and on the other hand, it needs to be fast enough to become practical.

The new advancements in reservoir data acquisition have raised the complexity of the reservoir model and therefore the time

required to run it. At the same time typical reservoir modeling tasks such as sensitivity analysis, history matching, field

development optimization, and uncertainty assessment require large number of simulation runs. The challenge now is to keep

the complexity of the reservoir model while shortening its run-time.

The main objective of history matching is to improve and validate the reservoir simulation model by incorporating the

observed data into the characterization process, in order to obtain reliable production forecast. A simulation model which has

been tuned to match the past performance of a reservoir offers a higher degree of confidence to predict the future. Having a

trustworthy prediction of field performance has direct impact on technical and financial performance of operators.

History matching, by nature, is an ill-posed inverse problem. Correspondingly, classical history matching where reservoir

parameters are adjusted manually by trial-and-error makes this scenario more tedious and time-consuming. Assisted

(automated) history matching was proposed to decrease the amount of labor required during the manual history matching.

During last two decades there have been efforts to improve assisted history matching in a way that could be applicable in the

real world. But despite all the attempts, due to increasing rate of complexity and resolution in the reservoir models, there is

still hesitation about the practicality and potential of these methods to handle highly complicated real reservoir models. This

makes assisted history matching still a challenging research topic.

The novelty of the idea in this study is to examine a new application of pattern recognition technologies to improve the time

and efforts required for completing a successful history matching project. The pattern recognition capabilities of Artificial

Intelligence and Data Mining (AI&DM) are used to develop a Surrogate Reservoir Model (SRM) and use it as the engine to

drive the history matching process. SRM is a prototype of the full-field reservoir simulation model that runs in fraction of a

second. SRM is built using a small number of geological realizations. The geological realizations are used to create a spatio-

temporal database. The AI&DM techniques are utilized to derive the complicated relationship between different parameters in

SPE-169507-MS 3

the database. Clearly the relationship originates from the nonlinear behavior of fluid flow thorough the porous media. In this

study Artificial Neural Networks (ANNs) are the AI&DM tool in building the SRM. In order to develop the SRM, the spatio-

temporal database was used to build ANNs.

2. Literature  Review    

2.1. History  Matching  

The advancement of computational power pushed reservoir simulation as the main tool to model the behavior of fluid flow in

reservoir (Watts 1997). Nowadays, feedbacks from reservoir simulation models are used in almost all reservoir development

decisions. Simulating reservoirs easily and realistically makes them a primary and reasonable choice for oil and gas companies

in the development of new (green) fields. Similarly, they are used in developed (brown or mature) fields where production

forecasts are required to help make future investment decisions.

In general, most of the required input data for building a numerical reservoir model comes from samples in wellbore or near

wellbore (Fanchi 2006). Compared to the size of a reservoir, these data are inadequate and their sources represent a very

limited section of reservoir. Furthermore, the methods applied for preparing these data are treating them in a very local aspect.

However, these data and the techniques to attain them are the only options that provide input data for the reservoir simulation

model of the field under study. The main point is that a huge part of the reservoir remains unknown to the engineers and

geologists working on the simulation model. As a result, the initial data in a simulation model should be adjusted in order to be

matched with the available historical data and predict the future performance of reservoir. This tuning procedure is performed

during history matching process. History matching is a calibration process that includes adjusting the uncertain parameters of

reservoir model until the model reproduces the historical field performance as closely as possible.

History matching is an ill-posed inverse problem. The inverse problem is the opposite of forward or direct problem which the

model parameters are used to predict the data. While in inverse problem the observed data is used to conclude (adjust) the

model parameters. On the other hand, a problem is ill-poised (not well-posed) when there are multiple non-unique solutions

for a certain problem. History matching is an ill-posed problem because many possible combinations of reservoir parameters

can result in almost the same behavior of reservoir (match the history data).

There is no doubt that history matching is a complicated procedure. Many criteria could be named which affect the degree of

success in this process: the quality and quantity of available data, the specific characteristics of the reservoir under study, the

4 SPE-169507-MS

time and resources allocated to the study, and finally the experience and knowledge of the research group working on the

model. Consequently, each one of these criteria gives the history matching problem its most important characteristic which is

the non-uniqueness character of the results. There is no specific and unique method for history matching process. Each

reservoir has the particular specification and behavior.

Many efforts to improve manual history matching techniques have been made since the mid 1960’s to both speed up and

automate history match process (Kruger 1961) (Jacquard and Jain 1965) (Jahns 1966). Gradient optimization methods were

used for history matching in late 1960’s (Coats, Dempsey and Henderson 1968)(Slater and Durrer 1970). Chen et al. (1974)

tried to formulate history matching as an optimal control problem. Williams et al (1998) offered a structured approach to

perform history matching on a complex reservoir and based on their experience proposed multiple recommendations which

make the manual history matching easier. Bush and Carter (1996) showed that simple optimization techniques are not good

enough to address complex history matching problems. He and Chamber (1999) claimed that automatic history matching using

an object-based approach could provide acceptable results without the need to manually adjust the model. In the early 90’s,

using stochastic modeling to generate multiple realizations were started (Tyler, Svanes and Omdal 1993) (Palatnic, et al.

1993). Stochastic modeling, which provides many different geological realizations, increases the variation of the most

important input parameters, e.g. the geological properties influencing fluid flow. Sultan et al. (1994) and Ouenes et al. (1993)

used the Simulated Annealing Method (SAM) to automate history matching process. SAM was a non-gradient optimization

method capable of handling large number of parameters.

Gao et al. (2004) for the first time suggested the idea of combining the simultaneous perturbation stochastic approximation

(SPSA) method with a simulator to perform automatic history match of multiphase flow production data. Hajizadeh et al.

(2009) (2010) introduced a stochastic approach for automatic history matching based on a continuous Ant Colony

Optimization (ACO) algorithm. Other stochastic algorithms have been examined in this area. Evolutionary algorithms have

gained popularity as a standard optimization approach in history matching. These algorithms are generally inspired by the

evolution theory. There have been may examples of application of these algorithms in history matching (Schulze-Riegert et al.

2002) (Cheng et al. 2008)(Ferraro and Verga 2009) (Abdollahzadeh et al. 2012) (Christie et al. 2013).

However, high nonlinear behavior of the problem, large computational expenses and huge dimension of a real size field make

the history match process more difficult. Although significant computational and solver efficiencies have been gained over the

past four decades, ever-increasing size of geo-statistical earth models has continued to challenge the computational speed issue

(Kabir, Chien and Landa 2003).

SPE-169507-MS 5

2.2. Artificial  Neural  Networks    

Artificial neural network (ANN), usually called Neural Network (NN), is an algorithm that was originally motivated by the

goal of having machines that can mimic the brain. A neural network consists of an interconnected group of artificial neurons.

They are physical cellular systems capable of obtaining, storing information, and using experiential knowledge. Like human

brain, the ANN’s knowledge comes from examples that they encounter. In human neural system, learning process includes the

modifications to the synaptic connections between the neurons. In a similar way, ANNs adjust their structure based on output

and input information that flows through the network during the learning phase.

Data processing procedure in any typical neural network has two major steps: the learning and application step. At the first

step, a training database is needed to train the networks. This dataset includes an input vector and a known output vector. Each

one of the inputs and outputs are representing a node or neuron. In addition, there are one or more hidden layers. The objective

of the learning phase is to adjust the weights of the connections between different layers or nodes. After setting up the learning

samples, in an iterative approach a sample will be fed into the network and the resulting outputs will be compared with the

known outputs. If the result and the unknown output are not equal, changing the weights of the connections will be continued

until the difference is minimized. After acquiring the desired convergence for the networks in the learning process, the

validation dataset is applied to the network for the validating step (Hagan, Demuth and Beale 2002)(Haykin 1998). Figure 1

depicts the input, hidden and output layers and their connections. Since the advent of ANNs (McCulloch and Pitts 1943), they

have seen different stages of rise and fall; however nowadays ANNs enjoy huge popularity and interests in different fields.

Some applied applications of ANNs are listed in Table 1.

Shahab Mohaghegh is one of the pioneers in applying AI in petroleum engineering. He (Mohaghegh 1995) refers the main

advantage of ANN to the type of recognition ability and the difference of the mechanism that human brain processes

information compared to conventional digital computers. Computers are fast and accurate tools in performing prepared

instructions. On the other hand, human brain performance is tremendously slower but more efficient than computers at

computationally complicated jobs such as speech and other pattern recognition problems.

ANNs can be helpful tool to solve many conventional and unconventional problems in petroleum engineering. Although they

have a long history, their popularity in petroleum engineering started two decades ago (Ali 1994). Since this time, the

applications of ANNs in addressing conventional problems of petroleum industry have been widely studied. Table 2 concisely

lists different applications of ANNs in petroleum engineering.

6 SPE-169507-MS

Table  1-­‐  Application  of  ANNs  in  different  fields.  The  popularity  of  ANNs  has  seen  rise  and  fall  since  their  advent.  

Applications of ANNs in different fields Sales forecasting (Yip, Hines and Yu 1997) Industrial process control (Devadhas, Pushpakumar and Mary 2012) Customer research (Chattopadhyay, et al. 2012) Risk management (Sarcià, Cantone and Basili 2007) Credit evaluation (Baesens, et al. 2003) Energy cost prediction (Yalcintas and Akkurt 2005) Medical diagnosis (Amato, et al. 2013)(Lei and Xing-cheng 2010) Business applications (Li 1994) Financial applications (Tan 2004) Stock market prediction (Adebiyi, et al. 2012)

Table  2-­‐  A brief list of ANN applications in petroleum engineering.  

A brief list of ANN application in petroleum engineering Well log interpretation (Baldwin, Otte and Whealtley 1989)(Jong-Se and Jungwhan

2004)(Masoud 1998)

Well test data analysis (Al-Kaabi and Lee 1990)(Ershaghi, et al. 1993)(Athichanagorn and Horne 1995)(Sultanp and Al-Kaabi 2002)

Reservoir characterization (Mohaghegh., et al. 1995)(Ahmed, et al. 1997)(Singh, et al. 2008)

Seismic attributes calibration Seismic pattern recognition

Inversion of seismic waveforms

(David 1993)(Yang and Huang 1991) (Roth and Tarantoia 1992)

Prediction of PVT data (Briones, et al. 1994)(Gharbi and Elsharkawy 1997)(Osman, Abdel-Wahhab and Al-Marhoun 2001)(Oloso, et al. 2009)

Identifying fractures and faults (Key, et al. 1997)(Sadiq and Nashawi 2000)(Aminzadeh and deGroot 2005)

Detecting hydrocarbons and forecast formation damage

(Cheng-Dang, et al. 1994)(Aminzadeh and deGroot 2005)(Nikravesh, et al. 1996)(Kalam, Al-Alawi and Al-Mukheini 1996)

2.3. Artificial  Intelligence  (AI)  Assisted  History  Matching  

During the last decade, there have been attempts to find alternative methods to reduce the amount of CPU time needed to

execute a numerical full field model. AI methods are one of the most famous and efficient examples of these kinds of

techniques. Zangl et al. (2006) trained an ANN as a proxy model by using a limited number of simulation runs of a gas storage

model. Then they applied this proxy model to replace the numerical model in order to make hundreds and thousands of runs in

a very short time in an optimization loop. One of the objectives was to perform the history matching. The results were

acceptable and had considerably less computational expenses compared with numerical reservoir simulation outcomes. Cullick

SPE-169507-MS 7

et al. (2006) compared the performance of proxy models based on ANNs with reservoir simulator to perform history matching.

Their results support using ANNs as a substitute for numerical simulator over the trained parameter space. They tried to

challenge the limitation of proxy model in their work by decreasing the number of training realizations and increasing the

uncertain parameters.

The objective of Rodriguez et al. (2007) work was accelerating the history matching process by applying singular value

decomposition method. This method helped them to save 75 % of total CPU time. At the same time, they used an ANN in

order to reduce number of simulation runs and help to increase the accuracy of solution. Silva et al. (2006)(2008) presented the

application of global optimizers combined with ANNs to address the history matching problem. Their results supported the

potential of ANNs to reduce the computational effort in history matching process. Sampaio et al. (2009) used feed-forward

neural networks as nonlinear proxies of reservoir simulation to speed up history matching. The focus of their work was to

discuss the technical criteria that will lead implementation of ANN to be a successful experience. The points that they have

mentioned in their paper are crucial for the researchers who are interested in applying ANN in petroleum engineering

problems.

The aforementioned cases are some examples of ANN application. However what is worth mentioning is the approach used in

these examples through development and implementation of AI models, which is the same as the statistical methods. The

degree of success of using AI models based on this approach is highly uncertain and it could be as successful or disappointing

as the statistical techniques (Cullick, Johnson and Shi 2006)(Zubarev 2009). Particularly addressing application of AI in

petroleum engineering problems (such as history matching), it requires a comprehensive knowledge in both areas of petroleum

engineering and AI and DM to achieve success. This knowledge plays an important role in keeping the physics to solve the

problem. The fact of using physics is something that has been neglected in statistical methods (or applying AI techniques using

the same approach).

2.4. Surrogate  Reservoir  Models  

The main objective of this study is to speed up the history matching process. The focus of our work is based on a relatively

new technology known as Surrogate Reservoir Model (SRM). SRM has been introduced as a tool for addressing many time-

consuming operations performed with reservoir simulation models (Mohaghegh 2006). SRM is a replica of numerical

reservoir simulation model which is able to reproduce the results of simulation model with a high accuracy in real-time.

Basically SRMs are a collection of (at least) one or multiple neuro-fuzzy systems that are trained and validated using the

information from numerical simulation models. The required information to train the SRM is assimilated in the form of a

8 SPE-169507-MS

spatio-temporal database. Design of spatio-temporal database is a function of the objective of SRM.

The examples of Surrogate Reservoir Models in the industry to address time-consuming reservoir modeling are available in the

literature. Mohaghegh introduced this tool for the first time in 2006 to perform uncertainty analysis of a giant oilfield with 165

horizontal wells in the Middle East (Mohaghegh 2006). The efficiency of SRMs to reproduce the results of reservoir

simulators has been proved in several case studies (Mohaghegh et al. 2009)(Mohaghegh 2009)(Mohaghegh 2010)(Mohaghegh

et al. 2012b)(Mohaghegh et al. 2012)(Amini et al. 2012). In this study, SRM is being used, for the first time as a tool for

assisted history matching.

3. Methodology  

SRMs are developed based on representative spatio-temporal databases. Building this database is the first step of developing

AI-based reservoir models. The main objective of the database is to teach the ANN model the whole process of fluid flow

phenomena in the reservoir. In general, this database should meticulously provide static and dynamic information of the

reservoir. The quality and quantity of this database determines degree of success to develop a successful AI-based reservoir

model including an SRM (Mohaghegh 2011). Compared to the other steps of SRM development, preparing the database is

relatively the most tedious part, which needs a lot of thought process. However a good database guarantees the success of the

modeling.

In order to build this SRM different steps were required. Followings are steps involved to develop the SRM:

1) Pre-processing step includes model development and dataset generation:

a. Development of a heterogeneous reservoir model using a commercial simulator. Starting with the base case

of reservoir model a small number of informative realizations were created. These informative realizations

represent the geological uncertainties involved in the reservoir model.

b. Depending on the objective of developing SRM, the reservoir could be divided into different segments and

tiers. Segmenting the reservoir helps to emphasize on the sections which are more important, such as well

block and the grid blocks around the well.

c. Extracting different static and dynamic data from the numerical simulation models in order to build the

spatio-temporal database.

2) SRM Development:

SPE-169507-MS 9

a. Performing Key Performance Indicators (KPIs) to identify and rank the influence of different reservoir

characteristics on the reservoir performance. The ranked KPIs will be a guide to select ANN inputs.

b. Partitioning the spatio-temporal database into training, calibration and validation sets.

c. Designing Artificial Neural Network (ANN) architecture.

d. Training, calibrating and validating the ANNs.

e. Testing the created ANNs using a complete blind realization of the reservoir.

Figure 2 summarizes the steps to develop the SRM.

4. The  Reservoir  Model  

The reservoir model used in this study is a synthetic replica of a highly heterogeneous oil field, with 24 production wells and

30 years of production history. The base simulation model is a single porosity oil reservoir, which was constructed in CMG-

IMEXTM1. The reservoir has been divided to 4800 Non-Orthogonal grid blocks, 80 in X direction and 60 in Y direction. The

reservoir has a single layer and thickness values are variable in different gird blocks. The field is producing oil at initial

pressure of 13,789.5 kilopascals (2,000 psi) and bubble point pressure of 2,068.4 kilopascals (300 psi), therefore it is expected

that the candidate reservoir will be producing oil for a long time in an under-saturated condition. The model is synthetic and

does not represent a real field. Figure 3 shows three and two dimensional views of the reservoir structure. Figure 4 and 5

illustrate three and two dimensional views of porosity and grid thickness distributions.

The given permeability range for the base model is from 10 to 75 md (Figure 6). In addition, the geological information from

the field identifies a high permeable zone. 24 production wells have been drilled in the field and they produce oil for 30 years.

Minimum bottom-hole pressure (BHP) is set as the production constraint which varies through time. The wells produce for 30

years, starting in 2000/01/01. The available historical data include oil rate production for all the wells.

5. Training  Realizations  

In order to introduce the uncertainties involved in the reservoir simulation model to the SRM, a small number of simulation

runs should be made. In this study, ten different realizations of the base model were designed to develop the SRM. Using the

permeability map from base reservoir model, ten different permeability maps were generated. The range of permeability for

1  Computer  Modeling  Group  

10 SPE-169507-MS

the base model is from 10 to 70 md. Due to the uncertainty involved in reservoir properties, a range from 10 to 200 md was

considered to create the permeability distributions. Afterward, to create ten different cases of permeability values at well

location, an experimental method (Latin Hypercube) was used. Table 3 summarizes generated permeability values at the wells’

location.

Table  3-­‐  Permeability  (md)  values  designed  at  well  locations  for  generating  permeability  maps.  The  permeability  values  for  each  well  have  been  ranged  by  color,  which  red  and  blue  represent  minimum  and  maximum  value  respectively.    

6. Reservoir  Segmentation-­‐  Tiering  System  and  offset  wells  

In order to include the static data of adjacent grid blocks of a well in the spatio-temporal database, a tiering system was

generated. Another objective of this part is to summarize the information based on their influences on the wells’ production.

Obviously, if the Euclidian distance of grid blocks from the production well is considered, different grid blocks show different

behavior in terms of fluid flow. For example, the well grid block has the maximum influence on the production of a well.

Hence, this influence should be considered during developing the database. Furthermore, considering the impact of the

neighborhood wells’ production was interested (offset wells’ effects).

 

Run  1 Run  2 Run  3 Run  4 Run  5 Run  6 Run  7 Run  8 Run  9 Run  10Well-­‐1 44.6 21.6 21.0 38.7 60.5 67.1 31.3 66.4 44.2 89.7Well-­‐10 40.3 29.8 51.5 140.8 49.7 142.8 146.9 87.5 113.6 107.3Well-­‐11 41.7 85.8 32.6 83.8 138.6 39.0 122.6 117.7 97.1 33.0Well-­‐12 33.4 18.0 44.7 51.9 40.1 21.2 89.8 73.9 75.5 34.9Well-­‐13 64.3 41.3 64.3 61.0 74.9 69.2 54.7 60.9 118.4 104.9Well-­‐14 17.6 42.8 30.0 31.0 38.1 28.4 43.1 56.1 35.2 62.9Well-­‐15 18.9 44.9 37.5 47.4 55.8 32.7 92.0 93.1 91.2 59.6Well-­‐16 21.7 40.0 29.9 32.5 41.1 33.9 43.0 57.8 38.8 66.8Well-­‐17 78.1 45.0 27.7 44.6 84.1 102.4 93.8 143.9 158.9 152.5Well-­‐18 34.6 24.6 40.2 56.8 29.5 44.1 75.7 74.9 54.6 81.3Well-­‐19 76.8 60.3 95.6 38.9 54.0 81.7 107.5 172.6 49.3 61.4Well-­‐2 58.8 42.9 52.6 92.2 78.0 105.4 93.7 81.6 107.2 119.5Well-­‐20 41.2 27.3 14.4 53.9 70.7 27.4 18.9 37.4 88.0 21.9Well-­‐21 19.5 22.4 39.5 27.4 19.6 47.5 50.5 63.4 60.7 89.6Well-­‐22 30.0 36.0 31.9 42.4 46.1 43.3 63.6 61.3 70.1 57.4Well-­‐23 58.6 67.8 60.4 117.6 109.0 59.6 82.4 55.8 47.6 73.2Well-­‐24 29.2 31.6 21.5 44.0 28.2 57.5 17.5 77.4 69.4 27.8Well-­‐25 29.5 88.8 46.1 68.4 31.7 109.8 159.9 112.4 182.8 153.0Well-­‐3 67.0 38.5 76.5 55.4 72.5 53.2 36.8 43.1 123.5 94.0Well-­‐4 26.5 37.5 32.9 71.0 66.7 42.0 31.6 29.8 22.8 19.0Well-­‐5 43.2 30.2 31.7 15.9 26.4 66.3 60.4 86.2 83.2 72.5Well-­‐6 24.5 38.1 34.9 40.3 46.5 38.5 62.3 63.4 56.7 61.7Well-­‐7 41.6 15.9 30.7 65.1 39.2 20.6 44.5 49.6 50.4 57.0Well-­‐8 54.1 79.0 73.4 112.9 101.4 71.8 193.9 161.8 140.1 131.8

Permeabilty  @  Wells'  Location  for  10  Runs  applied  in  Training  partWell

SPE-169507-MS 11

7. SRM  Development  

7.1. Input  Selection  

At this step, the inputs to develop the spatio-temporal database are selected. As it was mentioned, building this database is the

most important step of developing an SRM. In building of this database, the objective of the reservoir modeling should be

considered (Amini et al. 2012)(Mohaghegh et al. 2012a). For instance, the objective of this study is using the SRM to estimate

the well parameters such as oil production. Therefore, the reservoir properties, which are affecting the objective of study, have

higher degree of importance.

The spatio-temporal database includes different types of data such as static and dynamic reservoir characteristics, operational

constraints, etc. Static data refer to the properties of reservoir that are not changing through the time such as permeability,

porosity, top and thickness. Similarly, the dynamic data address variable parameters that are altering over the time, such as oil

production rate, bottom-hole pressure, and production time.

For the tiers which have more than one grid block, the average of the property was calculated. This calculation was done just

for static properties. Figure 7 summarizes different types of data in the spatio-temporal database.

7.2. Building  the  Artificial  Neural  Networks  

After having the database ready, the next step is to create the ANNs. In order to generate ANNs, software called IDEATM2 was

used (Intelligent Solutions Inc. 2012). The inputs of ANNs are displayed in figure 7 and the output of the networks is annual

oil rate production. The training algorithm was Back Propagation (BP). BP is one of the most common training methods to

train the ANN and the time-based model development feature of this paradigm was appropriate for our study.

One novel pre-modeling analysis in SRM development is performing Key Performance Indicators (KPIs) analysis. This

feature provided in IDEATM identifies the most influential parameters in any given process prior to modeling. This feature

operates based on a pattern recognition and fuzzy logic engine. Figure 8 displays the results of KPI analysis in this study.

Training the ANNs is the following step. The training process includes three different processes: Training (learning),

Calibration and Validation (testing). Therefore, the database is partitioned into three categories: training or learning set,

calibration set and validation or verification set. The training set is part of data shown to the ANNs during the training process.

2  IDEATM  is  a  data-­‐driving  and  AI  modeling  software  developed  by  Intelligent  Solutions  Inc.  (ISI).  

12 SPE-169507-MS

The ANNs are adapted to this set to match the provided outputs (reservoir simulation results). On the other hand, the

calibration set is not used to adjust the outputs. This set is utilized to assure that any increase in accuracy over the training data

set will lead to an increase in accuracy over a data set that has not been shown to the ANNs before. This set of data is helpful

to find out when the training should be stopped. If the error trend over the training data set has a decreasing trend, but the same

error for the calibration set has different trend, the ANN is over-fitting and it is time to stop the training process. Finally, the

verification set is a part of database to verify the validity of the trained ANN. Obviously this data set has not been used to train

the ANN. It is worth mentioning that the elapsed time to perform the training process (learning, calibration and verification) is

negligible compared to the reservoir simulation run-time. The training, calibration and verification included 80%, 10% and

10% of the data in the database.

7.3. Validation  the  SRM  by  a  Blind  Realization  

The trained SRM is validated against a complete blind realization of the reservoir. Therefore, a new simulation run was made.

This realization has a permeability distribution which is completely different from the ten realizations used in training process.

However it should be noted that the permeability range should be in the range of values used in the training runs. Finally, the

trained SRM was applied to predict the oil rate from the blind realization inputs.

7.4. History  Matching  

The trained and validated SRM is ready to be used in the process of history matching. In order to accomplish the history

matching, permeability values at each defined tier have been adjusted. The oil rates predicted by the SRM are compared

against the real production rates. This procedure must be repeated until an acceptable match in each well is obtained.

The objective functions to compare the results are presented in Equation 1 and Equation 2. Equation 1 calculates the difference

between measured and actual data at the well level and Equation 2 includes the well level objective function in a global

objective function at the field level. In Equation 1, the subscripts and represent well and time respectively. is the

total number of measured data points (In this study is 30 corresponding to 30 years of annual oil rate existing for each

well). is the predicted production by SRM and is measured production data. is the scale calculated by

subtracting the maximum and minimum of measured production data for well . In the global objective function, is the

objective function for well , and is the total number of wells (24 wells in this study). In practice, it is also common to

consider that the quality and importance of measured data may be different for some specific wells. is the defined weight

SPE-169507-MS 13

for well . In this work, all the wells were considered equally important and the weight coefficient is one for all of them.

Equation  1:  Individual  well  objective  function  

Equation  2:  Global  (Field)  objective  function  

8. Results  

This section intends to present the results for one of the wells (well # 20) for different steps of developing and applying the

SRM. The results for all wells can be found in somewhere else (Shahkarami 2012). Figure 9 displays the results after the

training process; the chart portrays the oil rate profile for 30 years of production comparing SRM results with the simulator

outputs. The blue squares represent the SRM and the red line with stars shows the numerical simulator results. It is evident that

SRM can reproduce the simulator results accurately. Figure 10 shows the results of blind verification realization. As was

mentioned earlier, a blind realization was used for testing the SRM. The blind set consists of a realization, which has not been

seen by SRM in the training process. Therefore, this graph validates the potential of SRM to predict a realization performance

out of the training dataset and displays the robustness of the technique. Finally figure 11 is a snapshot of the history matching

(HM) results for this well. This graph is the comparison of the SRM outcome with the measured production data.

The distribution of matched values of permeability is shown in figure 12. The right side of this figure pictures some shots of

the matched permeability map, while the left side shots are the actual permeability distribution. Figure 13 demonstrates the

error distribution of the results after history matching process. Figure 14 is an error frequency distribution of these results, as

well.

9. Summary  and  Concluding  Remarks  

An SRM was created for a synthetic but highly heterogeneous oil field, with 24 production wells and 30 years of production

history. The goal was achieving a match of the production history by tuning permeability distribution. SRM was trained using

14 SPE-169507-MS

ten heterogeneous realizations and then validated by a blind simulation run. Finally, the full field model was substituted by the

trained SRM to perform the history match process.

SRM was able to accurately match the results of training realizations. Robustness of SRM to predict the behavior of a

realization which has not been seen by SRM during learning process (blind case) was further verified. Matching the actual data

was perfect and comparison between the variable history matched property and actual distribution supports the claim. The

pattern recognition characteristics of SRM make it possible to achieve the results in a fraction of second. Although the running

time for the case study of reservoir model used in this study is not the concern, the number of simulation runs to attain a

desired match is time and power consuming. In numerical reservoir simulator, by increasing the size and complexity of the

components the run-time can increase in orders of magnitude. Nevertheless due to pattern recognition capability of SRM this

technology, it will not be an issue for SRM.

The results of this study could be counted as a proof of concept for showing the potential of this novel technology (SRM) to

assist history matching process. Increasing the uncertain variables and implementing the technology on a more sophisticated

(and real life) case study is the goal of the authors to achieve in future.

 

SPE-169507-MS 15

Figure  1-­‐  An  artificial  neural  network  is  an  interconnected  group  of  nodes.  

Figure  2-­‐  Steps  to  develop  an  SRM.

16 SPE-169507-MS

 

Figure  3-­‐Three and two dimensional  top  views  of  simulation  model.  

Figure  4-­‐  Three and two dimensional  views  of  porosity  distribution.  

 

Figure  5-­‐  Three and two dimensional  views  of  thickness  map.  

SPE-169507-MS 17

Figure  6-­‐  Given  permeability  map  for  the  base  case.  

Figure  7-­‐  Different  types  of  data  in  the  spatio-­‐temporal  database.

IndexWell  NameRun  Number

ijkXYZ

TopPorosity

PermeabilityGrid  Thickness

TimeOperational  Constraint Bottom-­‐hole  pressure

Oil  Rate  at  tOil  Rate  at  a  time  step  behind  (t-­‐1)

Production  RateDynamic  Data

Well  Location

Identifier

Static  Reservoir  Property  (at  4  tiers  and  offset  wells)

Static  Data

18 SPE-169507-MS

 Figure  8-­‐  The  results  of  KPI  analysis.  Pre-­‐modeling  analysis  of  KPI  is  an  appropriate  guide  to  select  the  inputs  of  ANNs.  

Figure  9-­‐  Training  results  for  well  #  20.  

SPE-169507-MS 19

Figure  10-­‐  Blind  run  results  for  well  #  20.  

Figure  11-­‐  Comparison  of  the  matched  results  coming  from  SRM  with  actual  outputs  (simulator)  for  well  #  20.  

20 SPE-169507-MS

 

Figure  12-­‐  Comparison  of  matched  and  actual  Permeability  distributions.  

Figure  13-­‐  Error  distribution  for  the  history  matched  results.  

SPE-169507-MS 21

Figure  14-­‐  Error  frequency  distribution  for  the  history  match  results.  

22 SPE-169507-MS

Bibliography  

Abdollahzadeh,  A.  et  al.  2012.  On  Population  Diversity  Measures  of  the  Evolutionary  Algorithms  Used  in  History  Matching.  SPE  Europec/EAGE  Annual  Conference,  4-­‐7  June,  Copenhagen,  Denmark  

Adebiyi,  A.A.,  C.K.  Ayo,  M.O  Adebiyi,  and  O.S  Otokiti.  2012.  Stock  Price  Prediction  using  Neural  Network  with  Hybridized  Market  Indicators.  Journal  of  Emerging  Trends  in  Computing  and  Information  Sciences.  

Ahmed,  T.,  C.A.  Link,  K.W.  Porter,  C.J.  Wideman,  P.  Himmer,  and  J.  Braun.  1997.  Application  of  Neural  Network  Parameter  Prediction  in  Reservoir  Characterization  and  Simulation  -­‐  A  Case  History:  The  Rabbit  Hills  Field.  Latin  American  and  Caribbean  Petroleum  Engineering  Conference.  Rio  de  Janeiro,  Brazil.  

Ali,  J  K.  Neural  Networks:  A  New  Tool  for  the  Petroleum  Industry?.  1994.  European  Petroleum  Computer  Conference.  Aberdeen,  United  Kingdom.  

Al-­‐Kaabi,  A  U,  and  W  J  Lee.  1990.  An  Artificial  Neural  Network  Approach  To  Identify  the  Well  Test  Interpretation  Model:  Applications.  SPE  Annual  Technical  Conference  and  Exhibition.  New  Orleans,  Louisiana.  

Amato,  F.,  A.  López,  E  María,  P.  Vaňhara,  and  A.  Hampl.  2013.  Artificial  neural  networks  in  medical  diagnosis.  Journal  of  Applied  Biomedicine:  47-­‐58.  

Amini,  S.  et  al.  2012.  Uncertainty  Analysis  of  a  CO2  Sequestration  Project  Using  Surrogate  Reservoir  Modeling  Technique.  SPE  Western  Regional  Meeting.  Bakersfield,  California,  USA.  

Aminzadeh,  F.,  and  P.  deGroot.  2005.  A  Neural  Networks  Based  Seismic  Object  Detection  Technique.  SEG  Annual  Meeting.  Houston,  Texas.  

Athichanagorn,  S,  and  Horne,  R  N.  1995.Automatic  Parameter  Estimation  From  Well  Test  Data  Using  Artificial  Neural  Network.  SPE  Annual  Technical  Conference  and  Exhibition.  Dallas,  Texas.  

Baesens,  B.,  Setiono,  R.,  Mues,  C.,  and  Vanthienen,J.  2003.  Using  Neural  Network  Rule  Extraction  and  Decision  Tables  for  Credit-­‐Risk  Evaluation.  Management  Science:  312-­‐329.  

Baldwin,  J.  L.,  Otte,  D.N.  and  Whealtley,  C.  L.  1989.  Computer  Emulation  of  Human  Mental  Processes:  Application  of  Neural  Network  Simulators  to  Problems  in  Well  Log  Interpretation.  SPE  Annual  Technical  Conference  and  Exhibition.  San  Antonio,  Texas,  USA.  

Briones,  M  F,  G.A.  Rojas,  J.A.  Moreno,  and  E  R  Martinez.  "Application  of  Neural  Networks  in  the  Prediction  of  Reservoir  Hydrocarbon  Mixture  Composition  From  Production  Data."  SPE  Annual  Technical  Conference  and  Exhibition.  New  Orleans,  Louisiana:  Society  of  Petroleum  Engineers,  1994.  

Bush,  M.D.,  and  Carter,  J.N.  1996.Application  of  a  Modified  Genetic  Algorithm  to  Parameter  Estimation  in  Petroleum  Industry.Intelligent  Engineering  Systems  through  Artificial  Neural  Networks(6):  397.  

Chattopadhyay,  M.  et  al.  2012.  Application  of  artificial  neural  network  in  market  segmentation:  A  review  on  recent  trends.  Management  Science  Letters:  425-­‐438.  

Chen,  W.H.,  Gavalas,  G.cR.  ,  Seinfeld,  J.  H.  and  Wasserman,  M.  L.  1974.  A  New  Algorithm  for  Automatic  History  Matching.  SPE-­‐AIME  48th  Annual  Fall  Meeting.  Las  Vegas,  USA.  

SPE-169507-MS 23

Cheng,  H.  et  al.  2008.  A  Structured  Approach  for  Probabilistic-­‐Assisted  History  Matching  Using  Evolutionary  Algorithms:  Tengiz  Field  Applications.  SPE  Annual  Technical  Conference  and  Exhibition,  21-­‐24  September,  Denver,  Colorado,  USA.  

Cheng-­‐Dang,  Z.  et  al.  1994.  Direct  Identification  of  Hydrocarbon  From  Well  Logs:  A  Neural  Network  Interpretation  Approach.Petroleum  Society  of  Canada,  Annual  Technical  Meeting.  Calgary,  Alberta,  Canada.  

Christie,  M.  et  al.  2013.  An  Adaptive  Evolutionary  Algorithm  for  History-­‐Matching.  EAGE  Annual  Conference  &  Exhibition  incorporating  SPE  Europec,  10-­‐13  June,  London,  UK  

CMG,  Computer  Modelling  Group.  2012.  Computer  Modelling  Group  Manual.  

Coats,  K.,  Dempsey,  J.  and  Henderson,    J.  1968.  A  New  Technique  for  Determining  Reservoir  Description  from  Field  Performance  Data.  43rd  SPE  Annual  Fall  Meeting.  Houston,  Texas,  USA.  

Cullick,  A.S.,  Johnson,  D.and  Shi,  G.  2006.  Improved  and  More-­‐Rapid  History  Matching  With  a  Nonlinear  Proxy  and  Global  Optimization.  SPE  Annual  Technical  Conference  and  Exhibition.  San  Antonio,  Texas,  USA.  

David,  H.  J.  1993.  Seismic  Attribute  Calibration  Using  Neural  Networks.  SEG  Annual  Meeting.  Washington,  DC,  USA.  

Devadhas,  G.,  Pushpakumar,  S.  and  Mary,  D.M.  2012.  ANN  Based  MARC  Controller  Design  for  an  Industrial  Chemical  Process.    International  Conference  on  Computing,  Electronics  and  Electrical  Technologies.  

Ershaghi,  I.  et  al.  1993.  A  Robust  Neural  Network  Model  for  Pattern  Recognition  of  Pressure  Transient  Test  Data.  SPE  Annual  Technical  Conference  and  Exhibition.  Houston,  Texas,  USA.  

Fanchi,  John  R.  2006.  Principles  of  Applied  Reservoir  Simulation.  Elsevier  Science  and  Technology  Books,  Inc.  

Ferraro,  P.  and  Verga,  F.  2009.  Use  Of  Evolutionary  Algorithms  In  Single  And  Multi-­‐  Objective  Optimization  Techniques  For  Assisted  History  Matching.  Offshore  Mediterranean  Conference  and  Exhibition,  25-­‐27  March,  Ravenna,  Italy.  

Gao,  G.,  Li,  G.  and  Reynolds,  A.C.  2004.  A  Stochastic  Optimization  Algorithm  for  Automatic  History  Matching.Society  of  Petroleum  Engineers.  

Gharbi,  R.B.,  and  Elsharkawy,  A.M.  1997.Neural  Network  Model  for  Estimating  The  PVT  Properties  of  Middle  East  Crude  Oils.  Middle  East  Oil  Show  and  Conference.  Bahrain.  

Hagan,  M.  T.,  Demuth,  H.B.  and  Beale,  M.  H.  2002.  Neural  Network  Design.  Hagan  Publishing.  

Hajizadeh,  Y.  2010.  Ants  Can  Do  History  Matching.SPE  Annual  Technical  Conference  and  Exhibition.  Florence,  Italy.  

Hajizadeh,  Y.,  Christie,  M.  and  Demyanov,  V.  2009.  Ant  Colony  Optimization  for  History  Matching.SPE  EUROPEC/EAGE  Annual  Conference  and  Exhibition.  Amsterdam,  The  Netherlands.  

Haykin,  S.  1998.  Neural  Networks:  A  Comprehensive  Foundation.  Prentice  Hall.  

He,  N.,  and  Chambers,  K.T.  1999.Calibrate  Flow  Simulation  Models  With  Well-­‐Test  Data  to  Improve  History  Matching.  SPE  Annual  Technical  Conference  and  Exhibition.  

Intelligent  Solutions  Inc.  2012.  www.intelligentsolutionsinc.com  (accessed  2011).  

Jacquard,  P.,  and  Jain,  C.  1965.  Permeability  Distribution  From  Field  Pressure  Data.SPE:  281.  

Jahns,  H.O.  1966.  A  Rapid  Method  for  Obtaining  a  Two-­‐Dimensional  Reservoir  Description  From  Well  Pressure  Response  Data.SPE:  315.  

24 SPE-169507-MS

Jong-­‐Se,  L.,  and  Jungwhan,K.  2004.  Reservoir  Porosity  and  Permeability  Estimation  from  Well  Logs  using  Fuzzy  Logic  and  Neural  Networks.  SPE  Asia  Pacific  Oil  and  Gas  Conference  and  Exhibition.  Perth,  Australia.  

Kabir,  C.S.,  Chien,  M.C.H.  and  Landa,  J.L.  2003.  Experiences  with  automated  history  matching.  SPE.  

Kalam,  M.Z.,  Al-­‐Alawi,  S.M  and  Al-­‐Mukheini,  M.  1996.  Assessment  of  Formation  Damage  Using  Artificial  Neural  Networks.SPE  Formation  Damage  Control  Symposium.  Lafayette,  Louisiana,  USA.  

Key,  S.C.  et  al.  1997.  Fault  And  Fracture  Classification  Using  Artifical  Neural  Networks  -­‐  Case  Study  From  the  Ekofisk  Field.  SEG  Annual  Meeting.  Dallas,  Texas,  USA.  

Kruger,  W.  D.  1961.  Determining  Areal  Permeability  Distribution  by  Calculations.J.  Pet.  Tech.:691.  

Lei,  S.,  and  Xing-­‐cheng,  W.  2010.  Artificial  Neural  Networks:Current  Applications  in  Modern  Medicine.  International  Conference  on  Computer  and  Communication  Technologies  in  Agriculture  Engineering.    

Li,  E.  1994.  Artificial  neural  networks  and  their  business  applications.  Information  &  Management:  303-­‐313.  

Masoud,  N.  1998.  Neural  Network  Knowledge-­‐Based  Modeling  of  Rock  Properties  Based  on  Well  Log  Databases.  SPE  Western  Regional  Meeting.  Bakersfield,  California,  USA.  

McCulloch,  W.S.,  and  Pitts,  W.H.  1943.  A  logical  calculus  of  the  ideas  immanent  in  nervous  activity.  Bulletin  of  Mathematical  Biophysics  Vol.  5  :  115-­‐133.  

Mohaghegh,  S  D.  1995.  Neural  Network:  What  It  Can  Do  for  Petroleum  Engineers.    Journal  of  Petroleum  Technology.  

Mohaghegh.,  S  D.,  Arefi,  R.,  Ameri,  S.,  and  Rose,  D.  1995.  Design  and  Development  of  An  Artificial  Neural  Network  for  Estimation  of  Formation  Permeability.    SPE  Computer  Applications.  

Mohaghegh,  S  D.  2006.  Quantifying  Uncertainties  Associated  With  Reservoir  Simulation  Studies  Using  a  Surrogate  Reservoir  Model.  SPE  Annual  Technical  Conference  and  Exhibition.  San  Antonio,  Texas,  USA  

Mohaghegh,  S  D.  2009.  Artificial  Intelligence  and  Data  Mining:  Enabling  Technology  for  Smart  Fields.  SPE's  The  Way  Ahead  Journal  :  14-­‐19.  

Mohaghegh,  S  D.,  A.  Modavi,  H.  Hafez,  and  M.  Haajizadeh.  2009.  Development  of  Surrogate  Reservoir  Model  (SRM)  for  Fast  Track  Analysis  of  a  Complex  Reservoir.    International  Journal  of  Oil,  Gas  and  Coal  Technology  :  2-­‐23.  

Mohaghegh,  S  D.  2010.  Surrogate  Reservoir  Model.  European  Geological  Union  General  Assembly.  EGU  2010.  Vienna,  Austria.  

Mohaghegh,  S  D.  2011.  Reservoir  Simulation  and  Modeling  Based  on  Pattern  Recognition.    SPE  Digital  Energy  Conference  and  Exhibition.  Woodlands,  Texas,  USA.  

Mohaghegh,  S  D.  et  al.  2012a.  Application  of  Surrogate  Reservoir  Models  (SRM)  to  an  Onshore  Green  Field  in  Saudi  Arabia;  Case  Study.  North  Africa  Technical  Conference  and  Exhibition.  Cairo,  Egypt.  

Mohaghegh,    S  D.  et  al.  2012b.  Application  of  Well-­‐Base  Surrogate  Reservoir  Models  (SRMs)  to  Two  Offshore  Fields  in  Saudi  Arabia,  Case  Study.  SPE  Western  Regional  Meeting.  Bakersfield,  California,  USA.  

Mohaghegh,  S  D.,  Amini,  S.,  Gholami,  V.,  Gaskari,  R.  and  Bromhal,  G.  2012.  Grid-­‐Based  Surrogate  Reservoir  Modeling  (SRM)  for  Fast  Track  Analysis  of  Numerical  Reservoir  Simulation  Models  at  the  Gridblock  Level.  SPE  Western  Regional  Meeting.  Bakersfield,  California,  USA.  

SPE-169507-MS 25

Nikravesh,  M.,  A.R.  Kovscek,  R.M.  Johnston,  and  T.W.  Patzek.  1996.  Prediction  of  Formation  Damage  During  Fluid  Injection  into  Fractured,  Low  Permeability  Reservoirs  via  Neural  Networks.  SPE  Formation  Damage  Control  Symposium.  Lafayette,  Louisiana,  USA.  

Oloso,  Munirudeen  A.  et  al.  2009.  Prediction  of  Crude  Oil  Viscosity  and  Gas/Oil  Ratio  Curves  Using  Recent  Advances  to  Neural  Networks.  SPE/EAGE  Reservoir  Characterization  and  Simulation  Conference.  Abu  Dhabi,  UAE.  

Osman,  E.  A,  Abdel-­‐Wahhab,  O.  A.  and  A  Al-­‐Marhoun,  M.  2001.  Prediction  of  Oil  PVT  Properties  Using  Neural  Networks.  SPE  Middle  East  Oil  Show.  Bahrain.  

Ouenes,  A.,    et  al.  1993.  A  New  Algorithm  for  Automatic  History  Matching:  Application  of  Simulated  Annealing  Method  (SAM)  to  Reservoir  Inverse  Modeling.  Society  of  Petroleum  Engineers.  

Palatnic,  B.,  L.  Zakirov,  S.  Haugen,  and  J.  van  Roosmalen.  1993.  New  Approaches  to  Multiple  History  Matching.  Seventh  European  Symposium  on  Improved  Oil  Recovery.  Moscow,  Russia.  

Rodriguez,  Adolfo  A.,  Hector  Klie,  Mary  F.  Wheeler,  and  Rafael  Banchs.  2007.  Assessing  Multiple  Resolution  Scales  in  History  Matching  With  Metamodels.  SPE  Reservoir  Simulation  Symposium.  Houston,  Texas,  USA.  

Roth,  Gunter,  and  Albert  Tarantoia.  1992.  Inversion  of  Seismic  Waveforms  Using  Neural  Networks.  SEG  Annual  Meeting.  New  Orleans,  Louisiana,  USA.  

Sadiq,  T.,  and  I.S.  Nashawi.  2000.  Using  Neural  Networks  for  Prediction  of  Formation  Fracture  Gradie.  SPE/CIM  International  Conference  on  Horizontal  Well  Technology.  Calgary,  Alberta,  Canada.  

Sampaio,  T.P.,  V.J.  Filho,  M.  Ferreira,  and  A.  de  Sa  Neto.  2009.  An  Application  of  Feed  Forward  Neural  Network  as  Nonlinear  Proxies  for  Use  During  the  History  Matching  Phase.Latin  American  and  Caribbean  Petroleum  Engineering  Conference.  Cartagena  de  Indias,  Colombia.  

Sarcià,  S.,  G.  Cantone,  and  V.  Basili.  2007.  A  Statistical  Neural  Network  Framework  for  Risk  Management  Process  -­‐  From  the  Proposal  to  its  Preliminary  Validation  for  Efficiency.  Second  International  Conference  on  Software  and  Data  Technologies.  Barcelona,  Spain.  

Schulze-­‐Riegert,  et  al.  2002.  Evolutionary  algorithms  applied  to  historymatching  of  complex  reservoirs.  SPE  Reserv.  Evalu.  Eng.5(2),  163–173    

Silva,  P.  C.,  C.  Maschio,  and  D.  J.  Schiozer.  2008.  Application  of  Neural  Network  and  Global  Optimization  in  History  Matching.Journal  of  Canadian  Petroleum  Technology.  

Silva,  P.  C.,  C.  Maschio,  and  D.  J.  Schiozer.  2006.  Applications  of  the  Soft  Computing  in  the  Automated  History  Matching.  Canadian  International  Petroleum  Conference.  Calgary,  Alberta,  Canada.  

Singh,  Virendra  et  al.  2008.  Neural  Networks  And  Their  Applications  In  Lithostratigraphic  Interpretation  of  Seismic  Data  For  Reservoir  Characterization.  World  Petroleum  Congress.  Madrid,  Spain.  

Slater,  G.,  and  E.  Durrer.  1970.  Adjustment  of  Reservoir  Simulation  Models  to  Match  Field  Performance.    SPE  45th  Annul  Fall  Meeting.  Houston,  Texas,  USA.  

Shahkarami,  A.  2012.  Artificial  intelligence  assisted  history  matching:  proof  of  concept.  Thesis  (M.S.)-­‐West  Virginia  University.  

Sultan,  A.J.,  A.  Ouenes,  and  W.W.  Weiss.    1994.  Automatic  History  Matching  for  an  Integrated  Reservoir  Description  and  Improving  Oil  Recovery.  SPE  Permian  Basin  Oil  and  Gas  Recovery  Conference.  Midland,  Texas,  USA.  

26 SPE-169507-MS

Sultanp,  Mir  Asif,  and  Abdulaziz  U.  Al-­‐Kaabi.  2002.  Application  of  Neural  Network  to  the  Determination  of  Well-­‐Test  Interpretation  Model  for  Horizontal  Wells.  SPE  Asia  Pacific  Oil  and  Gas  Conference  and  Exhibition.  Melbourne,  Australia.  

Tan,  C.  N.  W.  2004.  An  Artificial  Neural  Networks  Primer  with  Financial  Applications  Examples  in  Financial  Distress  Predictions  and  Foreign  Exchange  Hybrid  Trading  System.  Published  in  internet  (http://www.smartquant.com/references/NeuralNetworks/neural28.pdf).  

Tyler,  K.J.,  Tarald  Svanes,  and  Sturle  Omdal.  1993.  Faster  History  Matching  and  Uncertainty  in  Predicted  Production  Profiles  With  Stochastic  Modeling.68th  Annual  Technical  Conference  and  Exhibition  of  the  Society  of  Petroleum  Engineers.  Houston,  Texas,  USA.  

Watts,  J.W.  1997.  Reservoir  Simulation:  Past,  Present,  and  Future.SPE  Computer  Applications  :  171-­‐176.  

Williams,  M.A.  et  al.  1998.  The  Stratigraphic  Method:  A  Structured  Approach  to  History  Matching  Complex  SimulationModels.  SPE  Reservoir  Evaluation  &  Engineering  Journal.  Vol  (1):  169-­‐176.  

Yalcintas,  M.,  and  S.  Akkurt.  2005.  Artificial  neural  networks  applications  in  building  energy  predictions  and  a  case  study  for  tropical  climates.    International  Journal  of  Energy  Research:  891–901.  

Yang,  H.Z.,  and  Kou-­‐Yuan  Huang.  1991.  Hybrid  Neural  Network  For  Seismic  Pattern  Recognition.  SEG  Annual  Meeting.  Houston,  Texas,  USA.  

Yip,  D.H.F.,  E.L.  Hines,  and  W.W.H.  Yu.  1997.  Application  of  artificial  neural  networks  in  sales  forecasting.  International  Conference  on  Neural  Networks.  Houston,  Texas,  USA.  

Zangl,  G.,  M  Giovannoli,  and  M  Stundner.  2006.  Application  of  Artificial  Intelligence  in  Gas  Storage  Management.  SPE  Europec/EAGE  Annual  Conference  and  Exhibition.  Vienna,  Austria.  

Zubarev,  D.I.  2009.  Pros  and  Cons  of  Applying  Proxy-­‐models  as  a  Substitute  for  Full  Reservoir  Simulations.SPE  Annual  Technical  Conference  and  Exhibition.  New  Orleans,  Lousiana,  USA.