基于Ricker子波核的支持向量回归方法及其在地震勘探记录去噪处理中的应用  

Support Vector Regression Based on Ricker Wavelet Kernel Function and Its Application to Seismic Prospecting Data Denoising

作　　者：邓小英[1] 李月[2] 

机构地区：[1]吉林大学地球探测科学与技术学院,长春130026 [2]吉林大学通信工程学院,长春130012

出　　处：《吉林大学学报（地球科学版）》2007年第4期821-827,共7页Journal of Jilin University：Earth Science Edition

基　　金：国家自然科学基金项目(40574051);吉林省自然科学基金项目(20050526)

摘　　要：针对地震勘探中强随机噪声的去噪问题,引进支持向量回归方法,提出并证明一种新的Ricker子波核函数。支持向量回归采用核映射的基本思想,基于结构风险最小化原则,将回归问题转化为一个二次规划问题。对单道记录或多道记录中任选道的仿真实验表明,与传统的基于径向基核函数的支持向量回归及褶积滤波方法相比,使用本方法去噪后的同相轴更为清晰,波形恢复得更好,信噪比也较高,因此有可能将其应用于地震勘探记录的去噪处理中。Aiming at suppressing the strong stochastic noise in seismic prospecting data, support vector regression（SVR） is introduced. A new permitted support vector kernel function-Ricker wavelet kernel function is proposed and demonstrated. Based on the elementary idea of kernel mapping and the principle of structural risk minimization, SVR transforms the regression problem into a quadratic programming problem. The results of simulation experiments for single channel data or arbitrary channel of multi-channel data show the clearer event, the better wave shape and the higher SNR compared with the conventional convolution filter and common SVR based on RBF. So it is possible that SVR based on Ricker wavelet kernel function is applied to suppressing noise in seismic prospecting data.

关 键 词：支持向量回归 Ricker子波核函数 褶积滤波 地震勘探同相轴 

分 类 号：P631.44[天文地球—地质矿产勘探]