基于优化步长的混叠数据编码全波形反演方法  

Encoded full waveform inversion method by an optimum inversion step length for aliasing data

作　　者：韩雨桐 黄建平[1] 曲英铭 李振春[1] 王延光[2] 国运东 

机构地区：[1]中国石油大学(华东)地球科学与技术学院,青岛266580 [2]胜利油田物探研究院,东营257022

出　　处：《地球物理学进展》2016年第1期198-204,共7页Progress in Geophysics

基　　金：国家重点基础研究发展计划(973)(2014CB239006;2011CB202402);国家自然科学基金(41104069;41274124);中石化课题(KJWX-2014-05);中央高校科研业务费专项基金(R1401005A)联合资助

摘　　要：近年来,针对混叠数据的全波形反演(FWI)方法,逐渐成为研究的热点.本文通过引入抛物拟合策略对反演步长进行优化,实现了基于变步长的混叠数据编码全波形反演理论方法.在编程实现算法的基础上,通过简单洼陷和复杂Marmousi模型试算得到如下几点认识:1)不编码混叠数据存在串扰噪声,反演迭代到15次后残差增大,反演不收敛;常规编码FWI串扰噪声减少,误差函数收敛,但出现"锯齿"的反演不稳定现象.2)优化步长编码FWI方法较好解决了反演收敛性和稳定性问题,反演结果误差函数曲线平滑且残差逐渐减小,验证了新方法的正确性和更好的适应性.Recent years,the full waveform inversion（ FWI） for aliasing data,gradually become a hot research topic. This paper implements aliasing data encoding full waveform inversion theory method based on optimum inversion step length,by a parabolic fitting strategy to optimize the inversion step. On the basis of the programming,through trial for simple sub-sag model and complex Marmousi model,we get several understanding： 1） aliasing data with no coding exist crosstalk noise,the residual increased after 15 inverse iteration times, the inversion is not convergence; In conventional coding FWI,crosstalk noise reduces,error function convergences,but the inversion is not stable,appear ＂saw tooth＂phenomenon. 2） optimum step length coding FWI is better solve the problem of the convergence and stability of inversion,the inversion results error function curve is smoothing and has decreasing residual,this method verifies the validity and applicability of the new method.

关 键 词：混叠数据 全波形反演 编码 优化步长 串扰噪声 

分 类 号：P631[天文地球—地质矿产勘探]