Two-dimensional deep learning magnetotelluric inversion

Deep learning (DL) inversion methods have showcased promising applications in solving geophysical inverse problems. In this work, we develop a DL model (SwinTUNet) to enable accurate reconstruction of the nonlinear mapping between the network inputs and outputs and achieve two-dimensional (2-D) magn...

Full description

Saved in:
Bibliographic Details
Published in:Journal of physics. Conference series 2024-11, Vol.2895 (1), p.012050
Main Authors: Liu, W, Wang, H, Guo, T, Yan, MS, Xi, ZZ
Format: Article
Language:English
Subjects:
Deep learning
Electrical resistivity
Geophysical methods
Inverse problems
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep learning (DL) inversion methods have showcased promising applications in solving geophysical inverse problems. In this work, we develop a DL model (SwinTUNet) to enable accurate reconstruction of the nonlinear mapping between the network inputs and outputs and achieve two-dimensional (2-D) magnetotelluric (MT) inversion. SwinTUNet is built by employing the strong Swin Transformer as the backbone network and adopting the UNet architecture. Moreover, to create a training dataset that aligns with practical MT inverse problems and ensuring effective applications, we design and generate a set of random synthetic resistivity models with gradual-varying resistivity values. Inversion examples demonstrate that the proposed SwinTUNet inversion method holds a great promise in promoting the applicability of DL inversion methods in realistic MT prospecting scenarios.
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/2895/1/012050