Transient electromagnetic rapid tunnel prediction method

A transient electromagnetic rapid tunnel prediction method includes: S101 setting an observation system on the basis of actual exploration requirements; S102 randomly generating a large number of theoretical tunnel resistivity models; S103 carrying out numerical computation on the tunnel resistivity...

Full description

Saved in:
Bibliographic Details
Main Authors Fengli Shen, Fusheng Li, Lu Gan, Rongjiang Tang
Format Patent
LanguageEnglish
Published 05.06.2024
Subjects
DETECTING MASSES OR OBJECTS
GEOPHYSICS
GRAVITATIONAL MEASUREMENTS
MEASURING
PHYSICS
TESTING
Online AccessGet full text

Cover

More Information
Summary:A transient electromagnetic rapid tunnel prediction method includes: S101 setting an observation system on the basis of actual exploration requirements; S102 randomly generating a large number of theoretical tunnel resistivity models; S103 carrying out numerical computation on the tunnel resistivity models on the basis of the observation system and a numerical simulation algorithm to obtain transient electromagnetic field data corresponding to each model; S104 constructing a residual neural network (ResNet) model, designing a loss function, and training a ResNet by means of the obtained transient electromagnetic field data corresponding to each model; and S105 predicting new observation data by means of a trained ResNet model to obtain an inversion result of tunnel transient electromagnetic method (TEM) data.
Bibliography:Application Number: GB20230011850