Data mining and well logging interpretation: application to a conglomerate reservoir
Shi Ning1,2, Li Hong-Qi1,2, and Luo Wei-Ping1,2
1. Geophysics and Information Engineering College, China University of Petroleum, Beijing 102249, China.
2.Beijing Key Laboratory of Petroleum Data Mining, China University of Petroleum, Beijing 102249, China.
Abstract：
Data mining is the process of extracting implicit but potentially useful information from incomplete, noisy, and fuzzy data. Data mining offers excellent nonlinear modeling and self-organized learning, and it can play a vital role in the interpretation of well logging data of complex reservoirs. We used data mining to identify the lithologies in a complex reservoir. The reservoir lithologies served as the classification task target and were identified using feature extraction, feature selection, and modeling of data streams. We used independent component analysis to extract information from well curves. We then used the branch-and-bound algorithm to look for the optimal feature subsets and eliminate redundant information. Finally, we used the C5.0 decision-tree algorithm to set up disaggregated models of the well logging curves. The modeling and actual logging data were in good agreement, showing the usefulness of data mining methods in complex reservoirs.
Shi Ning,Li Hong-Qi,Luo Wei-Ping. Data mining and well logging interpretation: application to a conglomerate reservoir[J]. APPLIED GEOPHYSICS, 2015, 12(2): 263-272.
[1]
Acar, M. A.,Tolun, M. R., and Elbasi, E., 2014, An application of data mining and knowledge discovery process in the field of natural gas exploration: Proceedings on Application of Information and Communication Technologies (AICT), 8th IEEE International Conference, 1−6.
[2]
Al-Bazzaz, W. H., and Al-Mehanna, Y. W., Gupta, A., et al. 2007, Permeability modeling using neural-network approach for complex Mauddud-Burgan carbonate reservoir: SPE Middle East Oil and Gas Show and Conference, 11−14.
[3]
Aminzadeh, F., 2005, Applications of AI and soft computing for challenging problems in the oil industry: Journal of Petroleum Science and Engineering, 47(1−2), 5−14.
[4]
Bian, Z. Q., and Zhang, X. G., 2002, Pattern Recognition:Tsinghua University Press, China, 176−210.
[5]
Fayyad,U.,and Piatetsky-Shapiro, G., et al. 1996, From data mining to knowledge discovery in databases: AI Magazine, 17(3), 37−53.
[6]
Guo, H. F., Li, H. Q., and Meng, Z. X., 2008, Feature Selection, Genetic Algorithm and Support Vector Machine: Journal of Oil and Gas Technology, 30(6), 94−99.
[7]
Han, J. W., and Kamber, M., 2006, Data mining concepts and techniques: China Machine Press, China, 184-224.
[8]
Held, M., and Karp, R. M., 1970, The traveling-salesman problem and minimum spanning trees: Operations Research, 18(6), 1138−1162.
[9]
Jiang, H. L., and Zhao, Q. L., 2009, Machine learning methods: Publishing House of Electronics industry, China, 20−56.
[10]
Jutten, C., and Herault, J., 1988, Independent Component Analysis versus PCA. Proceeding of European Signal Processing Conf, 287-314.
[11]
Li, H. Q., Li, X. Y., and Tan, F. Q., et al. 2010, Lithology Identification of Conglomerate Reservoir Based on Decision Tree Method: Well Logging Technology, 34(1), 16-21.
[12]
Li, X. Y., 2011, Methods and Applications of Data Mining in the Reservoir Evaluation: PhD Thesis, University of Petroleum, Beijing.
[13]
Li, X. Y., and Li, H. Q., 2013, A new method of identification of complex lithologies and reservoirs: task-driven data mining: Journal of Petroleum Science and Engineering, 109, 241-249.
[14]
Liaqat Ali., and Sandip Bordoloi., et al. 2008,Modeling permeability in tight gas sands using intelligent and innovative data mining techniques. SPE Annual Technical Conference and Exhibition, 21−24.
[15]
Liu, J., Li, Z. C., and Wang, Z., 2011, Quantitative identification of microfacies based on ICA,PCA and SVM: Well Logging Technology, 35(3), 262−265.
[16]
Qin, F., Ren, S. L., and Cheng, Z, K., et al. 2007, Bayes classification model based on ICA: Computer Engineering and Design, 28(20), 4873−4877.
[17]
Quinlan, J. R., 1986, Induction of decision trees: Machine learning, 1(1), 81−106.
[18]
Shi, N., and Li, H. Q., and Luo, W. P., 2013, Lithology identification of reservoir containing anhydrite based on independent component analysis and Naive Bayes algorithm: Journal of Xi'an Shiyou University (Natural Science Edition), 28(5), 39−42.
[19]
Yang, F. S., and Hong, B., 2006, Independent component analysis principles and applications: Tsinghua University Press, China, 91−111.
[20]
Yong, S. H., and Zhang, C. M., 2006, Well logging data processing and integrated interpretation: China University of Petroleum Press, China, 533−566.
[21]
Zhong, Y. H., and Li, R., 2009, Application of Principal Component Analysis and Least Square Support Vector Machine to Lithology Identification: Well Logging Technology, 33(5), 425−429.
2015, Vol. 12 
