EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Learning-Based Gravity Inversion Integrating Physical Equations and Multiple Constraints

Wenxuan Shi, Jiapei Wang, Chongyang Shen, Shuai Zhang, Minghui Zhang, Hongbo Tan, Guangliang Yang

Applied Sciences · 01.12.2025 · 15 (23) · 12717

DOI: 10.3390/app152312717 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 01.12.2025. Verfasst von Wenxuan Shi und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Hubei Provincial Natural Science Foundation, Research Fund of the Institute of Earthquake Research of the China Earthquake Administration.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Three-dimensional gravity inversion technology involves inferring the underground density structure based on observed gravity anomaly data. In addition to gravity inversion based on physics-driven methods, deep learning, as a purely data-driven technique, is increasingly gaining attention in geophysical inversion problems. However, purely data-driven methods rely on the implicit relationships within the data during the inversion process, which results in a lack of clear physical significance. This study proposes a three-dimensional gravity inversion method that integrates physical equations with deep learning. Based on the U-Net architecture, the gravity forward equation is incorporated as a physical constraint term, and a composite loss function—comprising three-dimensional mean squared error, a depth-weighting function, and three-dimensional intersection-over-union loss—is constructed to enhance inversion accuracy. Numerical experiments indicate that this method outperforms traditional algorithms in terms of density recovery accuracy and boundary clarity. When applied to gravity anomaly data from the Tangshan earthquake region in China, this method successfully inverted the three-dimensional subsurface density structure, revealing a high-density anomaly beneath the seismic source area, which provides important evidence for understanding the regional earthquake generation mechanism.

Förderung

  • National Natural Science Foundation of China
  • Hubei Provincial Natural Science Foundation
  • Research Fund of the Institute of Earthquake Research of the China Earthquake Administration

Zitieren

APA

Shi, W., Wang, J., Shen, C., Zhang, S., Zhang, M., Tan, H., & Yang, G. (2025). Deep Learning-Based Gravity Inversion Integrating Physical Equations and Multiple Constraints. Applied Sciences, 15(23), 12717. https://doi.org/10.3390/app152312717

Vancouver

Shi W, Wang J, Shen C, Zhang S, Zhang M, Tan H, et al. Deep Learning-Based Gravity Inversion Integrating Physical Equations and Multiple Constraints. Applied Sciences. 2025;15(23):12717. doi:10.3390/app152312717

BibTeX
@article{Shi2025,
  author = {Shi, Wenxuan and Wang, Jiapei and Shen, Chongyang and Zhang, Shuai and Zhang, Minghui and Tan, Hongbo and Yang, Guangliang},
  title = {Deep Learning-Based Gravity Inversion Integrating Physical Equations and Multiple Constraints},
  journal = {Applied Sciences},
  year = {2025},
  volume = {15},
  number = {23},
  pages = {12717},
  doi = {10.3390/app152312717}
}
Kostenlos starten →