物探与化探2024，Vol.48Issue(5)：1199-1207,9.DOI:10.11720/wtyht.2024.1005
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)data based on the supervised descent method
摘要
Abstract
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 in-version 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 di-rections with implicit model features.In the online prediction stage,the physical modeling functions and the descent directions are em-ployed 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 inver-sion 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Key words
transient electromagnetic(TEM)method/short-offset transient electromagnetic(SOTEM)method/fast inversion/super-vised descent method/machine learning分类
天文与地球科学引用本文复制引用
饶丽婷,武欣,郭睿,党博,党瑞荣..基于监督下降法的短偏移距瞬变电磁快速反演研究[J].物探与化探,2024,48(5):1199-1207,9.基金项目
国家自然科学基金项目(42004064,42074121) （42004064,42074121）
河南省豫地科技集团2024年重点科研项目(JTZDKY202405) （JTZDKY202405）
中央引导地方科技发展资金项目(2023ZY0036) （2023ZY0036）
广西壮族自治区重点研发计划项目(2023AB260490) （2023AB260490）
