Kernel Principal Component Analysis (KPCA) in Electrical Facies Classification

Okhovvat, Hamid Reza; Riahi, Mohammad Ali; Akbari Dehkharghani, Afshin

doi:10.22050/ijogst.2023.360469.1653

Kernel Principal Component Analysis (KPCA) in Electrical Facies Classification

Document Type : Research Paper

Authors

Hamid Reza Okhovvat ¹

Mohammad Ali Riahi ²

Afshin Akbari Dehkharghani ³

¹ Ph.D. Candidate, Petroleum, Mining, and Materials Engineering Department, Islamic Azad University, Central Tehran Branch, Tehran, Iran

² Professor, Institute of Geophysics, University of Tehran, Iran

³ Associate Professor, Petroleum, Mining, and Materials Engineering Department, Islamic Azad University, Central Tehran Branch, Tehran, Iran

https://doi.org/10.22050/ijogst.2023.360469.1653

Abstract

This study uses the kernel principal component analysis (KPCA) feature extraction method for facies classification to extract new features from the measured well logs. After applying the principal component analysis (PCA) and KPCA feature extraction approaches, the classification was made using three robust classifiers: multilayer perceptron neural network (MLP), support vector machine (SVM), and random forest (RF). Finally, the predicted results for the test data that were not included in the training process were evaluated with the F1 score criterion. The PCA method did not significantly affect the classification performance due to the nonlinear structure of the facies. Our results show that the KPCA improves the performance of facies classification. Compared with the conventional approach based on well-log data, our new approach improves the classification accuracy for each classifier algorithm. In the RF results, the classification accuracy has increased by about 6%, while using the KPCA feature extraction approach raises classification accuracy from 52% to 58% compared to the original well-log data.

Highlights

To extract the nonlinear feature based on the principal component using the kernel method is a vital step.
Machine learning methods are one of the most common methods in face classification.
Random forest classifier successfully increases the classification accuracy using the kernel principal component analysis (KPCA) method.

Keywords

Electro-Facies, Kernel Principal Component Analysis, SVM, Random Forest

Wire-Line Logs

Subjects

Petroleum Engineering – Exploration

Abdideh, M. and Ameri, A., Cluster Analysis of Petrophysical and Geological Parameters for Separating the Electrofacies of a Gas Carbonate Reservoir Sequence. Natural Resources Research, Vol. 29, No. 3, p. 1843–1856, 2020.

Ai, X., Wang, H., and Sun, B., Automatic Identification of Sedimentary Facies Based on A Support Vector Machine in The Aryskum Graben, Kazakhstan. Applied Sciences, Vol. 9, No. 21, 4489 P., 2019.

Breiman, L., Random Forests. Mach Learn, Vol. 45, No. 1, p. 5–32, 2001.

Datta, D., Singh, G., Routray, A., Mohanty, W. K., and Mahadik, R. (2021, October). Automatic Classification of Lithofacies with Highly Imbalanced Dataset Using Multistage SVM Classifier. In IECON 2021–47th Annual Conference of The IEEE Industrial Electronics Society. IEEE. p. 1–6, 2021.

Dubois MK, Bohling GC, and Chakrabarti, S., Comparison of Four Approaches to A Rock Facies Classification Problem. Comput Geosci, Vol. 33, No. 5, p. 599–617, 2007.

Dubois MK, Byrnes AP, Bohling GC, and Doveton JH., Multiscale Geologic and Petrophysical Modelling of The Giant Hugoton Gas Field (Permian), Kansas and Oklahoma, USA, 2006.

Dubois MK, Byrnes AP, Bohling GC, Seals SC, and Doveton JH., Statistically-Based Lithofacies Predictions For 3-D Reservoir Modeling: Examples from The Panoma (Council Grove) Field, Hugoton Embayment, Southwest Kansas. In: Proceedings of The American Association of Petroleum Geologists Annual Convention, Vol. 12, A44 P., 2003.

Fakhari, M. G. and Hashemi, H., Fisher Discriminant Analysis (FDA), A Supervised Feature Reduction Method in Seismic Object Detection. Geopersia, Vol. 9, No. 1, p. 141–149, 2019.

Ferraretti, D., Lamma, E., Gamberoni, G., Febo, M., and Di Cuia, R., Integrating Clustering and Classification Techniques: A Case Study for Reservoir Facies Prediction. Emerging Intelligent Technologies in Industry, p. 21–34, 2011.

Fukunaga, K., Introduction to Statistical Pattern Recognition. Academic Press, London, 1990.

Hall, B., Facies Classification Using Machine Learning. Lead Edge, Vol. 35, No. 10, p. 906–909, 2016.

Hall, B., Https://Github.Com/Seg/2016-Ml-Contest Mosser, P., And A., 2016.

Hall, M. and Hall, B., Distributed Collaborative Prediction: Results of The Machine Learning Contest. Lead Edge, Vol. 36, No. 3, p. 267–269, 2017.

Halotel, J., Demyanov, V., and Gardiner, A., Value of Geologically Derived Features in Machine Learning Facies Classification. Mathematical Geosciences, Vol. 52, p. 5–29, 2020.

Heyer, JF., Reservoir Characterization of The Council Grove Group, Texas County, Oklahoma, 1999.

Hinton, G. E. and Salakhutdinov, R. R., Reducing the Dimensionality of Data with Neural Networks. Science, Vol. 313, No. 5786, P. 504–507, 2006.

HUANG, G. and H. SHAO, Kernel Principal Component Analysis and Application in Face Recognition [J]. Computer Engineering, Vol. 13, 005 P., 2004.

Huang, L., Li, Z., Tian, B. S., Chen, Q., Liu, J. L., and Zhang, R., Classification and Snow Line Detection for Glacial Areas Using the Polarimetric SAR Image. Remote Sensing of Environment, Vol. 115, No. 7, p. 1721–1732, 2011.

Jolliffe, I.T., Principal Component Analysis. Springer, New York, NY, 1986.

Lin, Y., Support Vector Machines and The Bayes Rule in Classification. Data Min Knowl Discov Vol. 6, No. 3, p. 259–275, 2002.

Liu, M., Jervis, M., Li, W., and Nivlet, P., Seismic Facies Classification Using Supervised Convolutional Neural Networks and Semisupervised Generative Adversarial Networks. Geophysics, Vol. 85, No. 4, p. 047–058, 2020.

Liu, Y. and Zheng, Y. F., One-Against-All Multi-Class SVM Classification Using Reliability Measures. In Proceedings. 2005 IEEE International Joint Conference on Neural Networks, Vol. 2, p. 849–854. IEEE, 2005.

Lu, J. and Et Al., An Efficient Kernel Discriminant Analysis Method. Pattern Recognition, Vol. 38, No. 10, p. 1788–1790, 2005.

Mandal, P. P. and Rezaee, R., Facies Classification with Different Machine Learning Algorithm–An Efficient Artificial Intelligence Technique for Improved Classification. ASEG Extended Abstracts, Vol. 2019, No. 1, p. 1–6, 2019.

Olson, TM., Babcock, JA., Prasad, KVK., Boughton, SD., Wagner, PD., Franklin, MH., Thompson, KA., Reservoir Characterization of The Giant Hugoton Gas Field, Kansas. AAPG Bull, Vol. 81, No. 11, p.1785–1803, 1997.

Puckette, J., Boardman, DR II., Al-Shaieb, Z., Evidence for Sea-Level Fluctuation and Stratigraphic Sequences in The Council Grove Group (Lower Permian), Hugoton Embayment, Southern Mid Continent, 1995.

Serra, O. and Abbott, H.T., The Contribution of Logging Data to Sedimentology and Stratigraphic, SPE 9270, 55th Annual Fall Technical Conference and Exhibition, Dallas, Texas, Pp. 19. Serra, O., 1986. Fundamentals Of Well-Log Interpretation 2. The Interpretation of Logging Data. Developments In Petroleum Science, Vol. 15, No. B, p. 3–679, 1980.

Shi, G., Shen, X., Ren, H., Rao, Y., Weng, S., and Tang, X., Kernel Principal Component Analysis and Differential Nonlinear Feature Extraction of Pesticide Residues on Fruit Surface Based on Surface-Enhanced Raman Spectroscopy. Frontiers in Plant Science, Vol. 13, 2022.

Sutadiwirya, Y., Using MRGC (Multi-Resolution Graph-Based Clustering) Method to Integrate Log Data Analysis and Core Facies to Define Electrofacies, In the Benua Field, Central Sumatera Basin, Indonesia. International Gas Union Research Conference, IGRC, Paris, p. 2–12, 2008.

Vapnik, V., The Nature of Statistical Learning Theory. Springer, Berlin, 1995.

Yang, J., J.-Y. Yang, and A.F. Frangi, Combined Fisherfaces Framework. Image and Vision Computing, Vol. 21, No. 12, p. 1037–1044, Breiman L (2001) Random Forests. Mach Learn, Vol. 45, No. 1, p. 5–32, 2003.

Zhang, L. and Zhan, C., Machine Learning in Rock Facies Classification - An Application of Xgboost: International Geophysics Conference, Qingdao, China, p. 1371–1374, 2017.

Zhang, S., Zhang, Z., and Li, X., An Improved Convolutional Neural Network for Facies Classification Based on Stratigraphic Features. IEEE Access, Vol. 7, p. 30896–30906. Doi: 10.1109/Access.2019.2908579, 2019.