Abstract
The principal component analysis (PCA) is the most common attribute optimization analysis techniques, but it is a linear method and exists the problem of lack of probability model and the absence of higher-order statistics information. It has poor comprehensive ability to complex non-linear attributes. Therefore, in order to overcome two shortcomings of the principal component analysis (PCA) and improve the effect of attribute optimization, this paper studies the probability kernel principal component analysis (PKPCA) method which is based on Bayesian theory and kernel principal component analysis (KPCA). First, the sample data are mapped to the high dimensional feature space, then define probability model of the data in high-dimensional space, and finally, expectation maximization (EM) estimated is used to get the best results. This method has both the advantage of probability analysis and kernel principal component analysis (KPCA). It is able to effectively adapt to more complex reservoir conditions and can realize the non-linear probability analysis. The probability kernel principal component analysis (PKPCA) method is applied to reservoir prediction of the Southern oil fields in China. The predicted results show that the method can improve the precision of the attribute optimization, while improving the accuracy of the forecasts of reservoir.
Highlights
In recent years, seismic attribute analysis has become an important mean for people to understand and monitor oil and gas reservoirs, mainly because it can effectively reflect the lithology and physical properties information contained in seismic data
It is necessary to select the least number of seismic attributes or their combinations which are most sensitive to solve specific problems, enhance the prediction accuracy of seismic reservoirs, and improve the effect of processing and interpretation methods related to seismic attributes, which is called "seismic attribute optimization"
For the two shortcomings of PCA, this paper focuses on the method of probability kernel principal component analysis (PKPCA), which captures the statistical features of nonlinear high-dimensional feature space by the Bayesian probability model
Summary
Seismic attribute analysis has become an important mean for people to understand and monitor oil and gas reservoirs, mainly because it can effectively reflect the lithology and physical properties (such as porosity, permeability, shale content, oil saturation, etc.) information contained in seismic data. For the two shortcomings of PCA, this paper focuses on the method of probability kernel principal component analysis (PKPCA), which captures the statistical features of nonlinear high-dimensional feature space by the Bayesian probability model. It combines the advantages of PPCA and KPCA. Probabilistic Kernel Principal Component Analysis (PKPCA) defines the PPCA model in the high-dimensional feature space by nonlinear mapping (Figure 1 below), which is the extension of PPCA in the kernel space [14] It effectively overcomes the lack of probability model and high-order statistics information in PCA.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
