期刊文献+

基于支持向量机的叠前地震反演方法 被引量:26

Prestack seismic inversion method based on support vector machine
下载PDF
导出
摘要 为了克服常规叠后地震反演方法中存在的缺陷,在保证反演效果的前提下提出了一种基于支持向量机的叠前地震反演方法。利用该方法可以得到比常规叠后波阻抗反演更丰富的储层物性参数,不但适合储集层物性反演,还可进行含油气性反演;可以直接从地震数据中提取地层的弹性参数,不需要对Zoeppritz方程进行简化以及对弹性参数做任何假设,也不需要初始地质模型和测井曲线的约束。反演结果表明,该方法具有反演速度快、稳定性好及抗噪能力强的特点,且易于进一步推广应用。 By analyzing the conventional seismic inversion methods and overcoming their defects, a prestack seismic inversion method based on support vector machine was proposed ensuring the inversion effect. The method can extract much more reser- voir physical properties than conventional poststack acoustic impedance inversion, so it is suitable for reservoir physical property and oil and gas property inversion. And it can directly estimate independent elastic parameters using seismic data. This method eliminates the need for any approximations of the Zoeppritz's equations or assumptions about the independent elastic parameters, initial model and constraint of well logging. The inversion results show that the proposed method is characterized by high inversion velocity, good stability and great antinoise ability. It is suitable for further popularization and application.
出处 《中国石油大学学报(自然科学版)》 EI CAS CSCD 北大核心 2008年第1期37-41,共5页 Journal of China University of Petroleum(Edition of Natural Science)
基金 国家'863'计划项目(2006AA09A102-13) 中国石油大学优秀博士学位论文培育项目(B2007-02)
关键词 叠前地震反演 支持向量机 ZOEPPRITZ方程 统计学习理论 prestack seismic inversion support vector machine Zoeppritz's equations statistical learning theory
  • 相关文献

参考文献11

  • 1LI Zhen-chun. Seismic exploration technology [ M ]. Dongying: China University of Petroleum Press, 2002.
  • 2陈天胜,刘洋,魏修成.纵波和转换波联合AVO反演方法研究[J].中国石油大学学报(自然科学版),2006,30(1):33-37. 被引量:31
  • 3沈凤,钱绍新,刘雯林,韩文杰.AVO多参数反演在气层检测和储层定量研究中的应用[J].石油学报,1994,15(2):11-20. 被引量:15
  • 4HAMPSON D. AVO inversion, theory and practice[ J]. Geophysics, 1991 (6) :39-42,
  • 5MOGENSEN S. Artificial neural network solutions to AVO inversion problems [ C ]//74th Annual International Meeting SEG, Expanded Abstracts, c2001:316-319.
  • 6KUZMA H A, RECTOR J W. Non-linear AVO inversion using support vector machines [ C ]//74th Annual International Meeting, SEG, Expanded Abstracts, c200d: 203- 206.
  • 7KAPPLER K, KUZMA H A, RECTOR J W. A comparison of standard inversion, neural networks and support vector machines [ C]//75th Annual international Meeting, SEG, Expanded Abstracts, c2005 : 1 725-1727.
  • 8LI Jia-kang, CASTAGNA J, LI Dong-an, et al. Reservoir prediction via SVM pattern recognition [ C]//74th Annual International Meeting, SEG, Expanded Abstracts, c2004 : 425-428.
  • 9王延江,杨培杰,史清江,孙正义.基于支撑向量机的井眼轨迹预测新方法[J].石油大学学报(自然科学版),2005,29(5):50-53. 被引量:7
  • 10Vapnik V N 张学工.统计学习理论的本质[M].北京:清华大学出版社,2000..

二级参考文献24

共引文献2460

同被引文献361

引证文献26

二级引证文献365

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部