基于监督下降法的短偏移距瞬变电磁快速反演研究  

Fast inversion of short-offset transient electromagnetic (SOTEM) databased on the supervised descent method

作　　者：饶丽婷 武欣 郭睿[5] 党博 党瑞荣[1] RAO Li-Ting;WU Xin;GUO Rui;DANG Bo;DANG Rui-Rong(School of Electronic Engineering,Xi’an Shiyou University,Xi’an 710065,China;Key Laboratory of Mineral Resources,Institute of Geology and Geophysics,Chinese Academy of Sciences,Beijing 100029,China;College of Earth and Planetary Sciences,University of Chinese Academy of Sciences,Beijing 100049,China;Innovation Academy of Earth Science,Chinese Academy of Sciences,Beijing 100029,China;Department of Electronic Engineering,Tsinghua University,Beijing 100084,China)

机构地区：[1]西安石油大学电子工程学院,陕西西安710065 [2]中国科学院矿产资源研究重点实验室中国科学院地质与地球物理研究所,北京100029 [3]中国科学院大学地球与行星科学学院,北京100049 [4]中国科学院地球科学研究院,北京100029 [5]清华大学电子工程系,北京100084

出　　处：《物探与化探》2024年第5期1199-1207,共9页Geophysical and Geochemical Exploration

基　　金：国家自然科学基金项目(42004064,42074121);河南省豫地科技集团2024年重点科研项目(JTZDKY202405);中央引导地方科技发展资金项目(2023ZY0036);广西壮族自治区重点研发计划项目(2023AB260490)。

摘　　要：短偏移距瞬变电磁法(简称SOTEM)通常采用传统式基于物理建模的反演方法,反演效率较低,不易灵活融入先验信息,而基于数据驱动的反演方法能够提高反演精度与效率,泛化能力却难以保证。为了提高SOTEM数据反演的精度和效率,并兼顾可靠的泛化能力,本文探索了一种融合物理建模与数据驱动的反演方法,将机器学习中监督下降法应用于SOTEM数据反演中。基于监督下降法的SOTEM数据反演分为线下训练和线上预测,线下训练时通过合理的训练集灵活融入先验信息,获得隐含模型特征的平均下降方向,线上预测时借助物理建模函数和训练所得下降方向,在传统反演框架下完成模型参数重建。文中利用层状大地模型构建训练集和测试集,实现了基于监督下降法的SOTEM数据一维反演,并与传统Occam算法进行了对比。结果表明:基于监督下降法的SOTEM反演效率大幅提升,反演精度较高,具有良好的泛化能力。The short-offset transient electromagnetic(SOTEM)data are typically processed using conventional inversion methods based on physical modeling,manifesting relatively low efficiency and difficulty in integrating priori information.In contrast,the data-driven inversion methods can enhance the inversion accuracy and efficiency but fail to ensure the generalization capability.To achieve high inversion accuracy and efficiency for SOTEM data and a reliable generalization capability,this study proposed an inversion method that integrates physical modeling with the data-driven approach,introducing the supervised descent method in machine learning into SOTEM data inversion.The proposed inversion method involves the offline training and online prediction stages.In the offline training stage,the prior information is flexibly integrated into the model training through a reasonable training dataset to obtain the average descent directions with implicit model features.In the online prediction stage,the physical modeling functions and the descent directions are employed to reconstruct the model parameters under the conventional inversion framework.In this study,the layered geodetic model was applied to design the training and test datasets for the 1D inversion of SOTEM data based on the supervised descent method.The inversion results were compared with those obtained using Occam's inversion algorithm,demonstrating that the proposed inversion method shows significantly enhanced inversion efficiency,higher inversion accuracy,and higher generalization capability.

关 键 词：瞬变电磁法 SOTEM 快速反演 监督下降法 机器学习 

分 类 号：P631.1[天文地球—地质矿产勘探]