Ensemble model of non-linear feature selection-based Extreme Learning Machine for improved natural gas reservoir characterization

被引:50
作者
Anifowose, Fatai Adesina [1 ]
Labadin, Jane [1 ]
Abdulraheem, Abdulazeez [2 ]
机构
[1] Univ Malaysia Sarawak, Fac Comp Sci & Informat Technol, Kota Samarahan 94300, Sarawak, Malaysia
[2] King Fahd Univ Petr & Minerals, Dept Petr Engn, Dhahran 31261, Saudi Arabia
关键词
Reservoir characterization; Porosity and permeability; Feature selection; Ensemble machine learning; Extreme Learning Machine; FUNCTIONAL NETWORKS; OIL; CLASSIFICATION; PERMEABILITY; PREDICTION;
D O I
10.1016/j.jngse.2015.02.012
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
The deluge of multi-dimensional data acquired from advanced data acquisition tools requires sophisticated algorithms to extract useful knowledge from such data. Traditionally, petroleum and natural gas engineers rely on "rules-of-thumb" in the selection of optimal features with much disregard to the hidden patterns in operational data. The traditional multivariate method of feature selection has become grossly inadequate as it is incapable of handling the non-linearity embedded in such natural phenomena. With the application of computational intelligence and its hybrid techniques in the petroleum industry, much improvement has been made. However, they are still incapable of handling more than one hypothesis at a time. Ensemble learning offers robust methodologies to handle the uncertainties in most complex industrial problems. This learning paradigm has not been well embraced in petroleum reservoir characterization despite the persistent quest for increased prediction accuracy. This paper proposes a novel ensemble model of Extreme Learning Machine (ELM) in the prediction of reservoir properties while utilizing the non-linear approximation capability of Functional Networks to select the optimal input features. Different instances of ELM were fed with features selected from different bootstrap samplings of the real-life field datasets. When benchmarked against existing techniques, our proposed ensemble model outperformed the multivariate regression-based feature selection, the conventional bagging and the Random Forest methods with higher correlation coefficient and lower prediction errors. This work confirms the huge potential in the capability of the new ensemble modeling paradigm to improve the prediction of reservoir properties. (C) 2015 Elsevier B.V. All rights reserved.
引用
收藏
页码:1561 / 1572
页数:12
相关论文
共 66 条
[21]   A minimax method for learning functional networks [J].
Castillo, E ;
Gutiírrez, JM ;
Cobo, A ;
Castillo, C .
NEURAL PROCESSING LETTERS, 2000, 11 (01) :39-49
[22]  
Castillo E., 2001, Connectionist Models of Neurons, Learning Processes, and Artificial Intelligence. 6th International Work-Conference on Artificial and Natural Neural Networks, IWANN 2001. Proceedings, Part I (Lecture Notes in Computer Science Vol. 2084), P316
[23]   Some applications of functional networks in statistics and engineering [J].
Castillo, E ;
Gutiérrez, JM ;
Hadi, AS ;
Lacruz, B .
TECHNOMETRICS, 2001, 43 (01) :10-24
[24]   Functional networks [J].
Castillo, E .
NEURAL PROCESSING LETTERS, 1998, 7 (03) :151-159
[25]  
Chandra A, 2006, J Math Model Algorithms, V5, P417, DOI [10.1007/s10852-005-9020-3, DOI 10.1007/S10852-005-9020-3]
[26]  
Chen D., 2004, P 45 ANN LOGG S NOOR
[27]  
Deng HT, 2011, LECT NOTES COMPUT SC, V6792, P293, DOI 10.1007/978-3-642-21738-8_38
[28]  
Dutta H., 2009, P IICAI, V9, P17
[29]   Functional networks as a new data mining predictive paradigm to predict permeability in a carbonate reservoir [J].
El-Sebakhy, Emad A. ;
Asparouhov, Ognian ;
Abdulraheem, Abdul-Azeez ;
Al-Majed, Abdul-Aziz ;
Wu, Donghui ;
Latinski, Kris ;
Raharja, Iputu .
EXPERT SYSTEMS WITH APPLICATIONS, 2012, 39 (12) :10359-10375
[30]   Forecasting PVT properties of crude oil systems based on support vector machines modeling scheme [J].
El-Sebakhy, Emad A. .
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING, 2009, 64 (1-4) :25-34