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

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

邓小英^1，2，李月²

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

收稿日期:2006-09-26 修回日期:1900-01-01 出版日期:2007-07-26 发布日期:2007-07-26
通讯作者: 李月

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

DENG Xiao-ying^1，2, LI Yue²

1.College of GeoExploration Science and Technology, Jilin University, Changchun 130026,China;2.College of Communications Engineering,Jilin University, Changchun 130012, China

Received:2006-09-26 Revised:1900-01-01 Online:2007-07-26 Published:2007-07-26
Contact: LI Yue

摘要/Abstract

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。

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

Abstract: 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.

Key words: support vector regression, Ricker wavelet kernel function, convolution filter, seismic prospecting event

中图分类号:

P631.44

邓小英，李月. 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[J]. J4, 2007, 37(4): 821-0827.

DENG Xiao-ying, LI Yue. Support Vector Regression Based on Ricker Wavelet Kernel Function and Its Application to Seismic Prospecting Data Denoising[J]. J4, 2007, 37(4): 821-0827.

参考文献

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

[1]	潘保芝, 石玉江, 蒋必辞, 刘丹, 张海涛, 郭宇航, 杨小明. 致密砂岩气层压裂产能及等级预测方法[J]. 吉林大学学报(地球科学版), 2015, 45(2): 649-654.
[2]	温忠辉, 任化准, 束龙仓, 王恩, 柯婷婷, 陈荣波. 岩溶地下河日流量预测的小样本非线性时间序列模型[J]. J4, 2011, 41(2): 455-458.