logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

Physics-embedded deep learning inversion for transient electromagnetic method survey data

delete2025-07-01
delete0
PRE
AI
R
Ruiyou Li
Y
Yong Zhang
J
Jiayi Ju
R
Rongqiang Liu
DOI：10.1016/j.cageo.2025.106000delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• An unsupervised deep learning network embedding the physical laws is proposed for TEM inversion. • A loss function incorporating dynamics smoothing constraints is constructed to enhance network training efficiency. • A joint LSTM-Attention network and WOA-MVMD technique is presented to improve the inversion precision.

Journal

C
Computers and Geosciences
IF:
4.4
Papers:
5.0K
Citations:
1.5W

Organization

No organization information available