Deep-TEMNet: A Hybrid U-Net–2D LSTM Network for Efficient and Accurate 2.5D Transient Electromagnetic Forward Modeling
The transient electromagnetic (TEM) method is a crucial tool for subsurface exploration, providing essential insights into the electrical resistivity structures beneath the Earth’s surface. Traditional forward modeling approaches, such as the finite-difference time-domain (FDTD) method and the finit...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/2/264 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587605816901632 |
|---|---|
| author | Zhijie Qu Yuan Gao Kang Xing Xiaojuan Zhang |
| author_facet | Zhijie Qu Yuan Gao Kang Xing Xiaojuan Zhang |
| author_sort | Zhijie Qu |
| collection | DOAJ |
| description | The transient electromagnetic (TEM) method is a crucial tool for subsurface exploration, providing essential insights into the electrical resistivity structures beneath the Earth’s surface. Traditional forward modeling approaches, such as the finite-difference time-domain (FDTD) method and the finite-element method (FEM), are computationally intensive, limiting their practicality for real-time, high-resolution, or large-scale investigations. To address these challenges, we present Deep-TEMNet, an advanced deep learning framework specifically designed for two-dimensional TEM forward modeling. Deep-TEMNet integrates the U-Net architecture with a tailored two-dimensional long short-term memory (2D LSTM) module, allowing it to effectively capture complex spatial-temporal relationships in TEM data. The U-Net component enables high-resolution spatial feature extraction, while the 2D LSTM module enhances temporal modeling by processing spatial sequences in two dimensions, thereby optimizing the representation of electromagnetic field dynamics over time. Trained on high-fidelity FEM-generated datasets, Deep-TEMNet achieves exceptional accuracy in reproducing electromagnetic field distributions across diverse geological scenarios, with a mean squared error of 0.00000134 and a root mean square percentage error of 0.002373019. The framework offers over 150 times the computational speed of traditional FEMs, with an average inference time of just 3.26 s. Extensive validation across varied geological conditions highlights Deep-TEMNet’s robustness and adaptability, establishing its potential for efficient, large-scale subsurface mapping and real-time data processing. By combining U-Net’s spatial resolution capabilities with the sequential processing strength of the 2D LSTM module, Deep-TEMNet significantly advances computational efficiency and accuracy, positioning it as a valuable tool for geophysical exploration, environmental monitoring, and other applications requiring scalable, real-time TEM analyses that are easily integrated into remote sensing workflows. |
| format | Article |
| id | doaj-art-e98154ba93e3459ab2fc5afbf10c2d64 |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-e98154ba93e3459ab2fc5afbf10c2d642025-01-24T13:47:55ZengMDPI AGRemote Sensing2072-42922025-01-0117226410.3390/rs17020264Deep-TEMNet: A Hybrid U-Net–2D LSTM Network for Efficient and Accurate 2.5D Transient Electromagnetic Forward ModelingZhijie Qu0Yuan Gao1Kang Xing2Xiaojuan Zhang3Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaState Key Laboratory of Space-Earth Integrated Information Technology, Beijing 100095, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaThe transient electromagnetic (TEM) method is a crucial tool for subsurface exploration, providing essential insights into the electrical resistivity structures beneath the Earth’s surface. Traditional forward modeling approaches, such as the finite-difference time-domain (FDTD) method and the finite-element method (FEM), are computationally intensive, limiting their practicality for real-time, high-resolution, or large-scale investigations. To address these challenges, we present Deep-TEMNet, an advanced deep learning framework specifically designed for two-dimensional TEM forward modeling. Deep-TEMNet integrates the U-Net architecture with a tailored two-dimensional long short-term memory (2D LSTM) module, allowing it to effectively capture complex spatial-temporal relationships in TEM data. The U-Net component enables high-resolution spatial feature extraction, while the 2D LSTM module enhances temporal modeling by processing spatial sequences in two dimensions, thereby optimizing the representation of electromagnetic field dynamics over time. Trained on high-fidelity FEM-generated datasets, Deep-TEMNet achieves exceptional accuracy in reproducing electromagnetic field distributions across diverse geological scenarios, with a mean squared error of 0.00000134 and a root mean square percentage error of 0.002373019. The framework offers over 150 times the computational speed of traditional FEMs, with an average inference time of just 3.26 s. Extensive validation across varied geological conditions highlights Deep-TEMNet’s robustness and adaptability, establishing its potential for efficient, large-scale subsurface mapping and real-time data processing. By combining U-Net’s spatial resolution capabilities with the sequential processing strength of the 2D LSTM module, Deep-TEMNet significantly advances computational efficiency and accuracy, positioning it as a valuable tool for geophysical exploration, environmental monitoring, and other applications requiring scalable, real-time TEM analyses that are easily integrated into remote sensing workflows.https://www.mdpi.com/2072-4292/17/2/264transient electromagneticforward modelfinite-element method (FEM)U-Net2D LSTM |
| spellingShingle | Zhijie Qu Yuan Gao Kang Xing Xiaojuan Zhang Deep-TEMNet: A Hybrid U-Net–2D LSTM Network for Efficient and Accurate 2.5D Transient Electromagnetic Forward Modeling Remote Sensing transient electromagnetic forward model finite-element method (FEM) U-Net 2D LSTM |
| title | Deep-TEMNet: A Hybrid U-Net–2D LSTM Network for Efficient and Accurate 2.5D Transient Electromagnetic Forward Modeling |
| title_full | Deep-TEMNet: A Hybrid U-Net–2D LSTM Network for Efficient and Accurate 2.5D Transient Electromagnetic Forward Modeling |
| title_fullStr | Deep-TEMNet: A Hybrid U-Net–2D LSTM Network for Efficient and Accurate 2.5D Transient Electromagnetic Forward Modeling |
| title_full_unstemmed | Deep-TEMNet: A Hybrid U-Net–2D LSTM Network for Efficient and Accurate 2.5D Transient Electromagnetic Forward Modeling |
| title_short | Deep-TEMNet: A Hybrid U-Net–2D LSTM Network for Efficient and Accurate 2.5D Transient Electromagnetic Forward Modeling |
| title_sort | deep temnet a hybrid u net 2d lstm network for efficient and accurate 2 5d transient electromagnetic forward modeling |
| topic | transient electromagnetic forward model finite-element method (FEM) U-Net 2D LSTM |
| url | https://www.mdpi.com/2072-4292/17/2/264 |
| work_keys_str_mv | AT zhijiequ deeptemnetahybridunet2dlstmnetworkforefficientandaccurate25dtransientelectromagneticforwardmodeling AT yuangao deeptemnetahybridunet2dlstmnetworkforefficientandaccurate25dtransientelectromagneticforwardmodeling AT kangxing deeptemnetahybridunet2dlstmnetworkforefficientandaccurate25dtransientelectromagneticforwardmodeling AT xiaojuanzhang deeptemnetahybridunet2dlstmnetworkforefficientandaccurate25dtransientelectromagneticforwardmodeling |