Investigating the effect of correlation-based feature selection on the performance of support vector machines in reservoir characterization

Abstract Permeability is an important property of hydrocarbon reservoir as crude oil lies underneath rock formations with lower permeability and its accurate estimation is paramount to successful oil and gas exploration. In this work, we investigate the effect of feature selection on the generalization performance and predictive capability of support vector machine (SVM) in predicting the permeability of carbonate reservoirs. The feature selection was based on estimating the correlation between the target attribute and each of the available predictors. SVM has been improved through the feature selection approach employed. The uniqueness of this approach is the fact that it employs fewer dataset in improving the performance of the SVM model. The effect of the approach has been investigated using real-industrial datasets obtained during petroleum exploration from five distinct oil wells located in a Middle Eastern oil and gas field. The results from this approach are very promising and suggest a way to improve on the performance of this algorithm and many other computational intelligence methods through systematic selection of the best features thereby reducing the number of features employed.

[1]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[2]  Andrew McCallum,et al.  Efficient clustering of high-dimensional data sets with application to reference matching , 2000, KDD '00.

[3]  Xiaoou Li,et al.  Support vector machine classification for large data sets via minimum enclosing ball clustering , 2008, Neurocomputing.

[4]  Michael D. Tusiani,et al.  LNG: A Nontechnical Guide , 2007 .

[5]  Tom Gedeon,et al.  A STATE-OF-THE-ART REVIEW OF NEURAL NETWORKS FOR PERMEABILITY PREDICTION , 2000 .

[6]  Federico Girosi,et al.  Training support vector machines: an application to face detection , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[7]  Ali Selamat,et al.  Predicting correlations properties of crude oil systems using type-2 fuzzy logic systems , 2011, Expert Syst. Appl..

[8]  Xiaoou Li,et al.  Fast Support Vector Machine Classification for Large Data Sets , 2014, Int. J. Comput. Intell. Syst..

[9]  Wasfi G. Al-Khatib,et al.  Identification of Question and Non-Question Segments in Arabic Monologues Using Prosodic Features: Novel Type-2 Fuzzy Logic and Sensitivity-Based Linear Learning Approaches , 2013 .

[10]  Walter Rose,et al.  Some Theoretical Considerations Related To The Quantitative Evaluation Of The Physical Characteristics Of Reservoir Rock From Electrical Log Data , 1950 .

[11]  P. H. Nelson,et al.  Permeability Prediction From Well Logs Using Multiple Regression , 1986 .

[12]  Feng Li,et al.  An Efficient Hierarchical Clustering Method for Large Datasets with Map-Reduce , 2009, 2009 International Conference on Parallel and Distributed Computing, Applications and Technologies.

[13]  Ali Selamat,et al.  Improved sensitivity based linear learning method for permeability prediction of carbonate reservoir using interval type-2 fuzzy logic system , 2014, Appl. Soft Comput..

[14]  W. D. Carrier Goodbye, Hazen; Hello, Kozeny-Carman , 2003 .

[15]  Tixier Maurice Pierre Evaluation of permeability from electric-log resistivity gradient , 1949 .

[16]  Ali Selamat,et al.  A hybrid model through the fusion of type-2 fuzzy logic systems and extreme learning machines for modelling permeability prediction , 2014, Inf. Fusion.

[17]  Masoud Nikravesh,et al.  Soft Computing for Reservoir Characterization and Modeling , 2010 .

[18]  Morteza Ahmadi,et al.  Design of neural networks using genetic algorithm for the permeability estimation of the reservoir , 2007 .

[19]  Hossain Arif,et al.  IDENTIFICATION OF ERYTHEMATO-SQUAMOUS SKIN DISEASES USING EXTREME LEARNING MACHINE AND ARTIFICIAL NEURAL NETWORK , 2013, SOCO 2013.

[20]  G. R. Coates,et al.  Permeability estimation; The various sources and their interrelationships , 1991 .

[21]  Sunday O. Olatunji,et al.  Performance Comparison of SVM and ANN in Predicting Compressive Strength of Concrete , 2014 .

[22]  Sunday O. Olatunji,et al.  Estimation of Superconducting Transition Temperature TC for Superconductors of the Doped MgB2 System from the Crystal Lattice Parameters Using Support Vector Regression , 2015 .

[23]  Alexandros Labrinidis,et al.  Challenges and Opportunities with Big Data , 2012, Proc. VLDB Endow..

[24]  David R. Lamb,et al.  Statistics and research in physical education , 1970 .

[25]  Jason W. Osborne,et al.  The power of outliers (and why researchers should ALWAYS check for them) , 2004 .

[26]  Kathleen M. MacQueen,et al.  Handbook for Team-Based Qualitative Research , 2007 .

[27]  Kabiru O. Akande,et al.  Support Vector Machines Approach for Estimating Work Function of Semiconductors: Addressing the Limitation of Metallic Plasma Model , 2014 .

[28]  Sylvain J. Pirson,et al.  Handbook of well log analysis : for oil and gas formation evaluation , 1963 .

[29]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[30]  Djebbar Tiab,et al.  Application of artificial intelligence to characterize naturally fractured zones in Hassi Messaoud Oil Field, Algeria , 2005 .

[31]  D. Stoneking Improving the manufacturability of electronic designs , 1999 .