Integrating kernel support vector machines for efficient rock facies classification in the main pay of Zubair formation in South Rumaila oil field, Iraq
详细信息 查看全文
- 作者：Watheq J. Al-Mudhafar
- 关键词：Lithofacies classification ; Posterior distribution ; Discrete distribution ; Kernel support vector machines ; South Rumaila oil field
- 刊名：Modeling Earth Systems and Environment
- 出版年：2017
- 出版时间：March 2017
- 年：2017
- 卷：3
- 期：1
- 全文大小：5600KB
- 刊物类别：Earth System Sciences; Math. Appl. in Environmental Science; Statistics for Engineering, Physics, Co
- 刊物主题：Earth System Sciences; Math. Appl. in Environmental Science; Statistics for Engineering, Physics, Computer Science, Chemistry and Earth Sciences; Mathematical Applications in the Physical Sciences; Ec
- 出版者：Springer International Publishing
- ISSN：2363-6211
- 卷排序：3
文摘
Precisely prediction of rock facies leads to adequate reservoir characterization by improving the porosity-permeability relationships and accurately identifying the spatial facies distribution. In this paper, the discrete and conditional posterior probability distributions of well lithofacies were modeled and predicted through the Kernel Support Vector Machines (KSVM) as a function of well log interpretations in a well in the Upper Sandstone Member of Zubair formation in South Rumaila Oil Field, located in Iraq. The log data include neutron porosity, water saturation, and shale volume. The multinomial response factor is the measured vertical Lithofacies sequence that has mainly sand, shale, and shaly sand. KSVM is a supervised statistical learning algorithm that recognizes the discrete classes for the given data based on maximizing the margin around the separating hyperplane and the decision function is fully specified by a subset of the Support vectors. The predicted lithofacies were validated by computing the total correct percent of predicted facies counts matrix, estimated by KSVM. The nonlinear separations of components handled by KSVM led to obtaining high level of accuracy of lithofacies prediction and attained 99.55% of the total correct percent. After depicting the vertical sand, shale, and shaly sand posterior distribution, it was shown that KSVM prediction has compatible between the sand posterior values with the high records of neutron porosity and low intervals of shale volume. Consequently, the KSVM can be considered for Lithofacies prediction in the other wells in the reservoir to provide a solid basis for the geospatial modeling.