Semi-supervised least squares support vector machine algorithm: application to offshore oil reservoir
Luo Wei-Ping1,2, Li Hong-Qi1,2, and Shi Ning1,2
1. College of Geophysics and Information Engineering, China University of Petroleum (Beijing), Beijing 102200, China.
2. Beijing Key Laboratory of Petroleum Data Mining (No. 121109212008), China University of Petroleum (Beijing), Beijing 102200, China.
Abstract：
At the early stages of deep-water oil exploration and development, fewer and further apart wells are drilled than in onshore oilfields. Supervised least squares support vector machine algorithms are used to predict the reservoir parameters but the prediction accuracy is low. We combined the least squares support vector machine (LSSVM) algorithm with semi-supervised learning and established a semi-supervised regression model, which we call the semi-supervised least squares support vector machine (SLSSVM) model. The iterative matrix inversion is also introduced to improve the training ability and training time of the model. We use the UCI data to test the generalization of a semi-supervised and a supervised LSSVM models. The test results suggest that the generalization performance of the LSSVM model greatly improves and with decreasing training samples the generalization performance is better. Moreover, for small-sample models, the SLSSVM method has higher precision than the semi-supervised K-nearest neighbor (SKNN) method. The new semi-supervised LSSVM algorithm was used to predict the distribution of porosity and sandstone in the Jingzhou study area.
. Semi-supervised least squares support vector machine algorithm: application to offshore oil reservoir[J]. APPLIED GEOPHYSICS, 2016, 13(2): 406-415.
[1]
Ahmadi, M. A., and Bahadori, A., 2015, A LSSVM approach for determining well placement and conning phenomena in horizontal wells: Fuel, 153(1), 276-283.
[2]
Blum, A., and Mitchell, T., 1998, Combining labeled and unlabeled data with co-training: Proceedings of the 11th Annual Conference on Computational Learning Theory (COLT98), Wisconsin, MI, 92−100.
[3]
Blum, A., and Chawla, S., 2001, Learning from labeled and unlabeled data using graph mincuts: Proceedings of the 18th International Conference on Machine Learning (ICML’01), San Francisco, CA, 19−26.
[4]
Doquire, G., and Verleysen, M., 2013, A graph Laplacian based approach to semi-supervised feature selection for regression problems: Neurocomputing, 121, 5−13.
[5]
Liang, J. Y., Gao, J. W., and Chang, Y., 2009, The semi-supervised learning research progress: Journal of Shanxi University (Natural Science Edition), 32(4), 528−534.
[6]
Lu, Z. W., and Wang, L.W., 2015, Noise-robust semi-supervised learning via fast sparse coding: Pattern Recognition, 48(1), 605−612.
[7]
Mesbah, M., Soroushb, E., Azari, V., et al., 2015, Vapor liquid equilibrium prediction of carbon dioxide and hydrocarbon systems using LSSVM algorithm: The Journal of Supercritical Fluids, 97(1), 256−267.
[8]
Shamanism, B., and Landgrebe, D., 1994, The effect of unlabeled samples in reducing the small sample size problem and mitigating the Hughes phenomenon: IEEE Transactions on Geoscience and Remote Sensing, 32(5), 1087−1095.
[9]
Song, X. N., Liu, Z., Yang, X. B., Yang, J. Y., and Qi, Y. S., 2015, Extended semi-supervised fuzzy learning method for nonlinear outliers via pattern discovery: Applied Soft Computing, 29, 245−255.
[10]
Wang, X. J., Hu, G. M., and Cao, J. X., 2010, Application of multiple attributes fusion technology in the Su-14 Well Block: Applied Geophysics, 7(3), 257−264.
[11]
Yamazaki, K., 2015, Accuracy analysis of semi-supervised classification when the class balance changes: Neurocomputing, 160, 5−13.
[12]
Zhou, Z. H., and Li, M., 2007, Semi-Supervised Regression with Co-Training Style Algorithms: IEEE Transactions on Geoscience and Remote Sensing, 10(20), 1−32.
[13]
Zhou, Z. H., and Wang, Y., 2007, Machine learning and its applications: Tsinghua University Press, Beijing, 259−275.
[14]
Zuo, L., Li, L. Q., and Chen, C., 2015, The graph based semi-supervised algorithm with ?-1 regularizer: Neurocomputing, 149(PB), 966−974.
2016, Vol. 13 
