Excess Water Production Diagnosis in Oil Fields Using Ensemble Classifiers

Excessive water production in oil fields is a challenging problem affecting oil production and entailing high handling and disposing costs as well as environmental issues. Accurate and timely diagnosis of the water production problem will significantly increase the success of the remedial actions taken. The traditional approaches in production data analysis by means of empirical techniques for proper diagnosis of water production mechanisms are still debatable. This paper presents a novel approach in water production problem identification using data mining techniques for production data analysis. The data used in this approach are water-oil ratio and some reservoir knowledge. New parameters used to identify two common types of water production mechanisms, i.e. water coning and channeling, are developed, and tree based ensemble classifiers are used for diagnosis. Our results demonstrate the applicability of this technique in successful diagnosis of water production problems.

[1]  J. Friedman.  Special Invited Paper-Additive logistic regression: A statistical view of boosting , 2000 .

[2]  J. Myers,et al.  Design and Construction of Pilot Wetlands for Produced-Water Treatment , 2003 .

[3]  D. Edwards.  Data Mining: Concepts, Models, Methods, and Algorithms , 2003 .

[4]  Iraj Ershaghi,et al.  A Method for Pattern Recognition of WOR Plots in Waterflood Management , 2005 .

[5]  D. Elcock,et al.  A white paper describing produced water from production of crude oil, natural gas, and coal bed methane. , 2004 .

[6]  F. HELLINGA,et al.  WATER CONTROL , 1952 .

[7]  Kolawole Babajide Ayeni,et al.  Empirical modeling and simulation of edgewater cusping and coning , 2008 .

[8]  Kurt Hornik,et al.  Open-source machine learning: R meets Weka , 2009, Comput. Stat..

[9]  Tarek Ahmed,et al.  Reservoir Engineering Handbook , 2002 .

[10]  Masoud Nikravesh,et al.  Past, present and future intelligent reservoir characterization trends , 2001 .

[11]  Alejandro Armellini,et al.  Encyclopedia of information technology curriculum integration - Edited by Lawrence A Tomei , 2011, Br. J. Educ. Technol..

[12]  Rodney R. Reynolds,et al.  Produced Water and Associated Issues , 2003 .

[13]  W. Shannon,et al.  Combining classification trees using MLE. , 1999, Statistics in medicine.

[14]  John A. Veil,et al.  Produced water volumes and management practices in the United States. , 2009 .

[15]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

[16]  M. Armenta.  Mechanisms and control of water inflow to wells in gas reservoirs with bottom water drive , 2003 .

[17]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[18]  L. Mattar,et al.  Production Data Analysis — Future Practices for Analysis and Interpretation , 2007 .

[19]  Li Li,et al.  A New Model for Predicting Water Cut in Oil Reservoirs , 2011 .

[20]  Phillip C. Harris,et al.  Data Mining Identifies Production Drivers in a Complex High-Temperature Gas Reservoir , 2009 .

[21]  Sanjoy Dasgupta,et al.  Adaptive Control Processes , 2010, Encyclopedia of Machine Learning and Data Mining.

[22]  Ritu Gupta,et al.  Transforming Data into Knowledge Using Data Mining Techniques: Application in Excess Water Production Problem Diagnosis in Oil Wells , 2010 .

[23]  Masoud Nikravesh,et al.  Mining and fusion of petroleum data with fuzzy logic and neural network agents , 2001 .

[24]  C. L. Boney,et al.  Production Data Analysis and Forecasting Using a Comprehensive Analysis System , 1999 .

[25]  S. I. Ozkaya,et al.  Using Probabilistic Decision Trees to Detect Fracture Corridors From Dynamic Data in Mature Oil Fields , 2008 .

[26]  R. D. Sydansk,et al.  A Strategy for Attacking Excess Water Production , 2003 .

[27]  M. Al Wadhahi,et al.  Diagnosis of Excessive Water Production in Horizontal Wells Using WOR Plots , 2008 .

[28]  R. Amin,et al.  A Method for Enhancing the RPM Performance in Matrix Reservoir , 2008 .

[29]  Eric Bauer,et al.  An Empirical Comparison of Voting Classification Algorithms: Bagging, Boosting, and Variants , 1999, Machine Learning.

[30]  H. Chipman,et al.  Bayesian CART Model Search , 1998 .

[31]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[32]  Alpana Bhatt,et al.  Reservoir Properties from Well Logs using neural Networks , 2002 .

[33]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[34]  Dilhan Ilk,et al.  Production-Data Analysis—Challenges, Pitfalls, Diagnostics , 2010 .

[35]  S. I. Chou,et al.  Development of Optimal Water Control Strategies , 1994 .

[36]  Eric R. Ziegel,et al.  The Elements of Statistical Learning , 2003, Technometrics.

[37]  Ronen Feldman,et al.  The Data Mining and Knowledge Discovery Handbook , 2005 .

[38]  Pedro M. Domingos.  Knowledge Acquisition from Examples Via Multiple Models , 1997 .

[39]  A. Kabir,et al.  Chemical Water & Gas Shutoff Technology - An Overview , 2001 .

[40]  Jose Luis Ortiz-volcan,et al.  A Reliability-Based Systemic Method for Water-Production Analysis, Diagnosis, and Solution Design , 2010 .

[41]  A. Joseph,et al.  A Review of Water Shutoff Treatment Strategies in Oil Fields , 2010 .

[42]  Bhavin Patel,et al.  A Proposed Method for Planning the Best Response to Kicks Taken During Managed Pressure Drilling Operations , 2011 .

[43]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[44]  David Hinkley,et al.  Bootstrap Methods: Another Look at the Jackknife , 2008 .

[45]  Ritu Gupta,et al.  A novel approach in extracting predictive information from water-oil ratio for enhanced water production mechanism diagnosis , 2010 .

[46]  Randall S. Seright,et al.  IMPROVED METHODS FOR WATER SHUTOFF , 1998 .

[47]  Subhash C. Bagui,et al.  Combining Pattern Classifiers: Methods and Algorithms , 2005, Technometrics.

[48]  Mohamed Y. Soliman,et al.  Integration of Technology Supports Preventive Conformance Reservoir Techniques , 2000 .

[49]  L. Dake.  Fundamentals of Reservoir Engineering , 1983 .

[50]  Yoav Freund,et al.  A Short Introduction to Boosting , 1999 .

[51]  Arie Ben-David,et al.  A lot of randomness is hiding in accuracy , 2007, Eng. Appl. Artif. Intell..

[52]  Tracy Love,et al.  Problem Diagnosis, Treatment Design, and Implementation Process Improves Waterflood Conformance , 1998 .

[53]  Eibe Frank,et al.  Logistic Model Trees , 2003, Machine Learning.

[54]  Tamás D. Gedeon,et al.  Intelligent Well Log Data Analysis: A Comparison Study , 2002, FSKD.

[55]  Adrian F. M. Smith,et al.  A Bayesian CART algorithm , 1998 .

[56]  Ildar Batyrshin,et al.  New Insights and Applications of Soft Computing on Analysis of Water Production From Oil Reservoirs , 2007 .

[57]  金田 重郎,et al.  C4.5: Programs for Machine Learning (書評) , 1995 .

[58]  Shahab D. Mohaghegh,et al.  A New Method for Production Data Analysis To Identify New Opportunities in Mature Fields: Methodology and Application , 2005 .

[59]  Andrei Popa,et al.  A Data Mining Approach to Unlock Potential from an Old Heavy Oil Field , 2011 .

[60]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[61]  Andrew P. Bradley,et al.  The use of the area under the ROC curve in the evaluation of machine learning algorithms , 1997, Pattern Recognit..

[62]  Pedro Alberto Zegarra,et al.  Water Control in Heavy-Oil Mature Field, Block 1AB , 2007 .

[63]  Zara Khatib,et al.  Water to Value - Produced Water Management for Sustainable Field Development of Mature and Green Fields , 2003 .

[64]  L. Breiman,et al.  BORN AGAIN TREES , 1996 .

[65]  Kagan Tumer,et al.  Classifier ensembles: Select real-world applications , 2008, Inf. Fusion.

[66]  Sungzoon Cho,et al.  Multiple permeability predictions using an observational learning algorithm , 2000 .

[67]  K. Chan,et al.  Water Control Diagnostic Plots , 1995 .