The research of reservoir parameters forecasting based on KICA and SVM
WANG Wei-Qiang1,2()
1. Technology Innovation Center of Geothermal & Hot Dry Rock Exploration and Development,Ministry of Natural Resources,Shijiazhuang 050061,China 2. Institute of Hydrology and Environmental Geology,Chinese Academy of Geological Sciences,Shijiazhuang 050061,China
In order to improve the accuracy of prediction of reservoir parameters,the paper proposes the approach for reservoir parameters forecasting based on KICA and Support vector machine (SVM).The KICA attribute optimization technology reflects the non-linear relationship and high order statistical properties of the attributes,extract the reservoir information of mutual statistical independence which reflects the reservoir parameters of the subsurface.SVM technology based on structural risk minimization principle,which can solve problems of the nonlinear systems for the small sample,high dimensional and local minimum.KICA combined the SVM,which accurately predict the reservoir parameter distributions through the huge attribute space and less well data.Through the model and actual data, it shows that reservoir parameter prediction technology has good effect of application, and high prediction.
王维强. 基于KICA属性优化的支持向量机储层参数预测[J]. 物探与化探, 2021, 45(4): 990-997.
WANG Wei-Qiang. The research of reservoir parameters forecasting based on KICA and SVM. Geophysical and Geochemical Exploration, 2021, 45(4): 990-997.
Lawrence P, Aramco S, Dhahran Dhahran, et al. Seismic attributes in the characterization of small-scale reservoir in Abqaiq Field[J]. The Leading Edge, 1998,17(4):521-525.
[2]
Chen Q, Sidney S. Seismic attribute technology for reservoir forecasting and monitoring[J]. The Leading Edge, 1997,16(5):445-456.
Zhao J F, Chen X H. Dual optimization of seismic attributes based on principal component analysis and K_L transform[J]. Geophysical and Geochemical Exploration, 2005,29(3):253-256.
Guo H J, Liu Q C. The discussion of earthquake attribute technology's history,present situation and development tendency[J]. Geophysical and Geochemical Exploration, 2008,32(1):19-22.
Du S T, Wang Y G. Application of seismic parameter integrated processing in reservoir transverse prediction[J]. Journal of the University of Petroleum, 1993,17(1):8-15.
[6]
Bach F R, Jordan M I. Kernel independent component analysis[J]. Journal of Machine Learning Research, 2002,3:1-48.
[7]
王永刚, 乐有喜, 张军华. 地震属性分析技术[M]. 东营: 中国石油大学出版社, 2006.
[7]
Wang Y G, Yue Y X, Zhang J H. Seismic attributes analysis[M]. Dongying: China University of Petroleum Press, 2006.
[8]
Vapnik V N. Statistical learning theory[M]. New York:John Wiley and Sons, 1998.
[9]
Shi Z W, Tang H W, Tang Y Y. A new fixed-point algorithm for independent component analysis[J]. Neurocomputing, 2004,56:467-473.
Liu T T, Ren M X, Yang Y F. Applying kernel independent component analysis(KICA) to obtaining better blind separation of mechanical vibration signals[J]. Journal of Northwestern Polytechnical University, 2011,29(1):108-112.
Yao F T, Jin L F, Dai G. Blind source separation based on kernel independent component analysis[J]. Computer Engineering and Applications, 2004,40(6):44-46.
[12]
Cortes C, Vapnilk V. Support vector networks[J]. Machine Learning, 1995,20(3):273-297.
Tang X B. The application of the support vector machine regression based on corresponding analysis to the prediction of the seismic reservoir thickness[J]. Geophysical and Geochemical Exploration, 2009,33(4):468-471.
