基于光滑约束正则化的电磁波层析反演  

Electromagnetic wave tomography inversion based on smoothing constrained regularization

作　　者：林芳鹏 戴前伟[1,3] 雷轶 LIN Fangpeng;DAI Qianwei;LEI Yi(Key Laboratory of Metallogenic Prognosis of Nonferrous Ministry of Education,Central South University,Changsha 410083,China;Guangxi Traffic Engineering Testing Co.,Ltd,Nanning 530011,China;School of Geosciences and Info-Physics,Central South 0University,Changsha 410083,China)

机构地区：[1]中南大学有色金属成矿预测教育部重点实验室,长沙410083 [2]广西交通工程检测有限公司,南宁530011 [3]中南大学地球科学与信息物理学院,长沙410083

出　　处：《物探化探计算技术》2018年第2期212-217,共6页Computing Techniques For Geophysical and Geochemical Exploration

基　　金：国家自然科学基金重大项目(41374118)

摘　　要：层析反演的本质是解病态方程组,且系数矩阵通常为大型稀疏矩阵。正则化可提高解的稳定性,LSQR法可减小存储空间、加快计算效率,因此将二者结合提出了基于光滑约束正则化的层析反演算法。正则化参数在反演中有着至关重要的作用,采用L曲线法选择最佳正则化参数。列举了基于走时层析成像的数值计算实例,由最佳正则化参数下的速度剖面图可清晰地识别异常体特征,证明了基于光滑约束正则化的层析反演算法的有效性。The nature of the tomography inversion is used to solve the ill-conditioned equations,and the coefficient matrix is usually a large sparse matrix.Considering that regularization can improve the stability of the solution,and the LSQR method can reduce the storage space and speed up the calculation efficiency.Therefore,this paper proposes a new algorithm based on smoothing constrained regularization,which combines the above two advantages.The regularization parameter is a crucial factor in inversion,while the L-curve method is used to select the best regularization parameter in this paper.A numerical example based on the travel-time tomography shows that the velocity profile in the best regularization parameter can clearly recognize the anomaly feature,and prove the validity of the tomography inversion algorithm based on smoothing constrained regularization.

关 键 词：电磁波层析成像 正则化 最光滑模型约束 LSQR算法 L曲线法 

分 类 号：P631.2[天文地球—地质矿产勘探]