基于深度学习考虑激电效应的瞬变电磁正演方法及系统
By using a CNN-LSTM hybrid network model based on deep learning, combined with the Cole-Cole complex resistivity model and a piecewise weighted mean square error loss function, the computational efficiency and accuracy problems of traditional transient electromagnetic methods in simulating excited polarization effects are solved, and efficient and accurate transient electromagnetic response prediction is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA UNIV OF GEOSCIENCES (WUHAN)
- Filing Date
- 2026-04-20
- Publication Date
- 2026-07-17
AI Technical Summary
Traditional transient electromagnetic methods struggle to accurately characterize complex resistivity dispersion when simulating responses with induced polarization effects, resulting in insufficient explanatory power for sign inversion phenomena and high computational costs.
A CNN-LSTM hybrid network model based on deep learning is adopted, and the Cole-Cole complex resistivity model is used to replace the actual resistivity of the formation. The network is trained by combining a piecewise weighted mean square error loss function, and the key parameters of the induced polarization effect are explicitly introduced to construct an end-to-end nonlinear mapping model.
It significantly improves computational efficiency, can accurately predict transient electromagnetic responses throughout the entire time period, reduces computational costs, and improves the prediction accuracy and physical consistency of sign reversal phenomena, making it suitable for complex geoelectric structures.
Smart Images
Figure CN122065690B_ABST