基于KICA属性优化的支持向量机储层参数预测

doi:10.11720/wtyht.2021.1170

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (7055 KB) HTML (0 KB)
Export: BibTeX | EndNote (RIS)

Abstract

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.

Key words： KICA seismic attribute optimization SVM reservoir parameters prediction

Received: 10 March 2020 Published: 20 August 2021

ZTFLH:

P631.4

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Wei-Qiang WANG

Cite this article:

Wei-Qiang WANG. The research of reservoir parameters forecasting based on KICA and SVM[J]. Geophysical and Geochemical Exploration, 2021, 45(4): 990-997.

URL:

https://www.wutanyuhuatan.com/EN/10.11720/wtyht.2021.1170 OR https://www.wutanyuhuatan.com/EN/Y2021/V45/I4/990

Chart of reservoir parameter prediction technology based on seismic attributes

Geological model of domal bodies

Synthetic seismogram of domal bodies

Prediction of reservoir thickness(a) and velocity(b) based on ICA attribute optimization and neural network

Prediction of reservoir thickness(a) and velocity(b) based on KICA attribute optimization and neural network

Prediction of reservoir thickness(a) and velocity(b) based on ICA attribute optimization and SVM

Prediction of reservoir thickness(a) and velocity(b) based on KICA attribute optimization and SVM

Reservoir characteristics optimized by ICA attributes
a—attribute component 1;b—attribute component 2

Reservoir characteristics optimized by KICA attributes
a—attribute component 1;b—attribute component 2

Porosity value of known wells

Prediction of the average porosity

Porosity prediction based on ICA optimization and neural network

Porosity prediction based on KICA optimization and SVM

[1]	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.
[3]	赵加凡, 陈小宏. 基于主成分分析与K_L变换的双重属性优化方法[J]. 物探与化探, 2005,29(3):253-256.
[3]	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.
[4]	郭华军, 刘庆成. 地震属性技术的历史、现状及发展趋势[J]. 物探与化探, 2008,32(1):19-22.
[4]	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.
[5]	杜世通, 王永刚. 地震参数综合处理方法在储层横向预测中的应用[J]. 石油大学学报:自然科学版, 1993,17(1):8-15.
[5]	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.
[10]	刘婷婷, 任民兴, 杨永锋. 核独立分量分析在机械振动信号分离中的应用[J]. 西北工业大学学报, 2011,29(1):108-112.
[10]	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.
[11]	姚伏天, 金连甫, 戴光. 基于核独立成分分析的盲源信号分离[J]. 计算机工程与应用, 2004,40(6):44-46.
[11]	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.
[13]	唐小彪. 基于对应分析的支持向量机回归在地震储层厚度预测中的应用[J]. 物探与化探, 2009,33(4):468-471.
[13]	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.
[14]	朱剑兵, 谭明友. 基于支持向量机的地震储层参数预测方法初探[J]. 油气地球物理, 2008,6(1):34-36.
[14]	Zhu J B, Tan M Y. Seismic reservoir parameters prediction via support vector machine[J]. Petroleum Geophysics, 2008,6(1):34-36.