基于主成分分析和核主成分分析的地震属性优化的研究  

Seismic Attribute Optimization Research Based on Principal Component Analysis and Kernel Principal Component Analysis

作　　者：郑和忠 魏长江 王树华 

机构地区：[1]青岛大学数据科学与软件工程学院,青岛266071 [2]胜利油田勘探开发研究院西部分院,东营257000

出　　处：《青岛大学学报（自然科学版）》2017年第3期76-80,共5页Journal of Qingdao University(Natural Science Edition)

摘　　要：在地震属性分析技术中地震属性优化是重要的一步,主成分分析法是一种常用基于有效的线性变换的地震属性优化的方法,但对具有非线性关系地震属性数据降维效果不佳,为此提出了一种基于非线性变换的核主成分分析法。该方法通过核函数将低维输入空间映射到高维特征空间,实现了对地震属性数据的非线性到线性关系的转换,并通过主成分分析对属性优化。实验结果表明,同主成分分析法相比该方法对非线性关系的地震属性优化具有更好的效果。In the seismic attribute analysis technique,seismic attribute optimization is an important step.Principal component analysis is a commonly used method of seismic attribute optimization based on effective linear transformation,but it is not good to reduce the seismic attribute data with nonlinear relationship.A kernel principal component analysis method based on nonlinear transformation is proposed.This method maps the low-dimensional input space to the high-dimensional feature space through the kernel function,realizing the transformation from nonlinear to linear relation of seismic attribute data,and then optimizes the attribute by principal component analysis.The experimental results show that the proposed method has better effect on the seismic attribute optimization of nonlinear relation than principal component analysis.

关 键 词：地震属性优化 主成分分析 降维 核主成分分析 

分 类 号：TP311.52[自动化与计算机技术—计算机软件与理论]