Deep-TEMNet: A Hybrid U-Net–2D LSTM Network for Efficient and Accurate 2.5D Transient Electromagnetic Forward Modeling

Αποθηκεύτηκε σε:
Λεπτομέρειες βιβλιογραφικής εγγραφής
Εκδόθηκε σε:Remote Sensing vol. 17, no. 2 (2025), p. 264
Κύριος συγγραφέας: Qu, Zhijie
Άλλοι συγγραφείς: Gao, Yuan, Kang, Xing, Zhang, Xiaojuan
Έκδοση:
MDPI AG
Θέματα:
Διαθέσιμο Online:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Ετικέτες: Προσθήκη ετικέτας
Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!

MARC

LEADER 00000nab a2200000uu 4500
001 3159535658
003 UK-CbPIL
022 |a 2072-4292 
024 7 |a 10.3390/rs17020264  |2 doi 
035 |a 3159535658 
045 2 |b d20250101  |b d20251231 
084 |a 231556  |2 nlm 
100 1 |a Qu, Zhijie  |u Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China; <email>quzhijie20@mails.ucas.ac.cn</email> (Z.Q.); <email>gaoyuan21@mails.ucas.ac.cn</email> (Y.G.); Key Laboratory of Electromagnetic Radiation and Sensing Technology, Chinese Academy of Sciences, Beijing 100190, China; School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100049, China 
245 1 |a Deep-TEMNet: A Hybrid U-Net–2D LSTM Network for Efficient and Accurate 2.5D Transient Electromagnetic Forward Modeling 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a 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. 
653 |a Finite element method 
653 |a Environmental monitoring 
653 |a Geophysical exploration 
653 |a Accuracy 
653 |a Geological mapping 
653 |a Data processing 
653 |a Deep learning 
653 |a Datasets 
653 |a Modelling 
653 |a Magnetic fields 
653 |a Finite difference time domain method 
653 |a Electromagnetic fields 
653 |a Remote sensing 
653 |a Spatial discrimination 
653 |a Computer applications 
653 |a Modules 
653 |a Electrical resistivity 
653 |a Long short-term memory 
653 |a Python 
653 |a Adaptability 
653 |a Efficiency 
653 |a Geology 
653 |a Machine learning 
653 |a Simulation 
653 |a Exploration 
653 |a Artificial intelligence 
653 |a Fourier transforms 
653 |a Spatial memory 
653 |a Spatial resolution 
653 |a Neural networks 
653 |a High resolution 
653 |a Methods 
653 |a Finite element analysis 
653 |a Information processing 
653 |a Algorithms 
653 |a Real time 
653 |a Subsurface mapping 
653 |a Software 
700 1 |a Gao, Yuan  |u Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China; <email>quzhijie20@mails.ucas.ac.cn</email> (Z.Q.); <email>gaoyuan21@mails.ucas.ac.cn</email> (Y.G.); Key Laboratory of Electromagnetic Radiation and Sensing Technology, Chinese Academy of Sciences, Beijing 100190, China; School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100049, China 
700 1 |a Kang, Xing  |u State Key Laboratory of Space-Earth Integrated Information Technology, Beijing 100095, China; <email>xingkang19@mails.ucas.ac.cn</email>; Beijing Institute of Satellite Information Engineering, Beijing 100095, China 
700 1 |a Zhang, Xiaojuan  |u Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China; <email>quzhijie20@mails.ucas.ac.cn</email> (Z.Q.); <email>gaoyuan21@mails.ucas.ac.cn</email> (Y.G.); Key Laboratory of Electromagnetic Radiation and Sensing Technology, Chinese Academy of Sciences, Beijing 100190, China 
773 0 |t Remote Sensing  |g vol. 17, no. 2 (2025), p. 264 
786 0 |d ProQuest  |t Advanced Technologies & Aerospace Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3159535658/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3159535658/fulltextwithgraphics/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3159535658/fulltextPDF/embedded/6A8EOT78XXH2IG52?source=fedsrch