Non-Linear AVO Inversion Based on Support Vector Machine

详细信息   

• 责任者：Bing Pingping (Key Lab. of Geophysical Exploration of CNPC ; China University of Petroleum ; Beijing 102249 ; China) ; Cao Siyuan
• 刊名：Chinese Journal of Geophysics
• 出版年：2012
• 卷期：55(3)
• 关键词：AVO技术 ; AVO techniques ; 支持向量机 ; support vector machine
• 页码：p.1025-1032
• 图表：4 illus., 26 tables, 2 refs.
• 分类号：1600
• issnNo：ISSN0001-5733
• isbnNo：CN11-2074/P

摘要

This paper presents a new method for amplitude versus offset (AVO) nonlinear inversion that solved by support vector machine（SVM）. First the main principle of SVM is described,then the SVM model are established for AVO inversion. Finally, both real data and synthetic model are inverted based on SVM,the results show that the proposed method can resolve limitations associated with conventional inversion methods without sacrificing inversion effects. It can extract elastic parameters from synthetic seismogram directly. Meanwhile the method is characterized by high inversion velocity and good stability.