基于支持向量机的非线性AVO反演

本文提出了一种新的AVO非线性反演方法,即利用支持向量机来求解AVO非线性反演问题.文中先对支持向量机的原理进行了阐述,然后建立了适合AVO反演的支持向量机模型.最后利用该方法对模型数据和实际资料进行了反演计算,反演结果表明,该方法在没有牺牲反演效果的情况下较好的解决了传统反演方法所具有的局限性,可以直接从合成记录中提取地层的弹性参数,反演速度快、稳定性好.

Non-linear AVO inversion based on support vector machine

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.