Deep Learning Inversion of Gravity Data With Multiple Physical Constraints
IEEE Geoscience and Remote Sensing Letters · 2026 · 23 · 1-5
DOI: 10.1109/lgrs.2026.3673191 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Geoscience and Remote Sensing Letters, 2026. Verfasst von Haoyuan He und 5 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben. Gefördert von: Deep Earth Probe and Mineral Resources Exploration—National Science and Technology Major Project, Science for Earthquake Resilience, Science and Technology Support Project of Langfang City.
Abstract (Originalsprache)
Gravity inversion is an important method for revealing underground density distribution. Traditional deterministic inversions face challenges such as easily becoming trapped in local minimum solutions and sensitivity to initial models, while conventional data-driven deep learning inversions (DD-DLIs) also exhibit limitations including dependence on datasets and lack of physical constraints. In this letter, we propose a multiphysical constrained deep learning inversion (MPC-DLI) method for gravity data based on the U-Net. Within an iterative descent inversion framework, the method employs a trained neural network to predict model updates for each iteration. Constraints about forward modeling laws and model smoothness are incorporated into the loss function during the training phase, serving respectively to promote the fitting of observation data and enhance stability. In the prediction phase, a focusing constraint is built into the objective function to yield model results with clear boundaries and pronounced density variations. Synthetic and field data examples are used to demonstrate the effectiveness of the new method.
Förderung
- Deep Earth Probe and Mineral Resources Exploration—National Science and Technology Major Project
- Science for Earthquake Resilience
- Science and Technology Support Project of Langfang City
Zitieren
APA
He, H., Li, T., Zhang, R., Li, Y., Gu, G., & Xu, Z. (2026). Deep Learning Inversion of Gravity Data With Multiple Physical Constraints. IEEE Geoscience and Remote Sensing Letters, 23, 1-5. https://doi.org/10.1109/lgrs.2026.3673191
Vancouver
He H, Li T, Zhang R, Li Y, Gu G, Xu Z. Deep Learning Inversion of Gravity Data With Multiple Physical Constraints. IEEE Geoscience and Remote Sensing Letters. 2026;23:1-5. doi:10.1109/lgrs.2026.3673191
BibTeX
@article{He2026,
author = {He, Haoyuan and Li, Tonglin and Zhang, Rongzhe and Li, Yong and Gu, Guanwen and Xu, Zhihe},
title = {Deep Learning Inversion of Gravity Data With Multiple Physical Constraints},
journal = {IEEE Geoscience and Remote Sensing Letters},
year = {2026},
volume = {23},
pages = {1--5},
doi = {10.1109/lgrs.2026.3673191}
}
EUVIMED