Physics‐Informed Deep Learning for Revealing the Evolutionary Characteristics of Landslides Induced by Rainfall Process
Geophysical Research Letters · 16.11.2025 · 52 (21)
DOI: 10.1029/2025gl117356 ↗Kurz gefasst
Fachartikel in der Zeitschrift Geophysical Research Letters, online erschienen am 03.11.2025. Verfasst von Changdong Li und 7 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 72 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Hubei Province.
Abstract (Originalsprache)
Rainfall‐induced landslides involve complex interactions of multi‐physical fields between seepage and stress fields across varying scales, posing challenges for conventional numerical models in achieving accuracy and generalization. We propose a Physical Information‐Driven and Guided Multimodal Multi‐task Neural Network (PMNN), which explicitly integrates fundamental geomechanical equations, including the Van Genuchten seepage model and Bishop's effective stress equation, while incorporates hydromechanical governing laws, such as mass conservation equation and Darcy's law, within the loss function to enforce physical constraints. Experiments on 800 numerically simulated and 55 model tested rainfall scenarios demonstrate that the internal physics embedding leads to over a twofold improvement in multi‐physical fields prediction accuracy, while external physical constraints effectively reduce stability prediction errors. Furthermore, our results reveal distinct triggering mechanisms: high‐intensity rainfall rapidly saturates shallow soils, forming a “shallow critical” zone and triggering shallow landslides, whereas prolonged low‐intensity rainfall promotes deeper infiltration fronts, leading to deep‐seated slope failures.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Hubei Province
Zitieren
APA
Li, C., Feng, P., Meng, J., Catani, F., Hellevang, H., Tang, H., Sun, X., & Huang, D. (2025). Physics‐Informed Deep Learning for Revealing the Evolutionary Characteristics of Landslides Induced by Rainfall Process. Geophysical Research Letters, 52(21). https://doi.org/10.1029/2025gl117356
Vancouver
Li C, Feng P, Meng J, Catani F, Hellevang H, Tang H, et al. Physics‐Informed Deep Learning for Revealing the Evolutionary Characteristics of Landslides Induced by Rainfall Process. Geophysical Research Letters. 2025;52(21). doi:10.1029/2025gl117356
BibTeX
@article{Li2025,
author = {Li, Changdong and Feng, Pengfei and Meng, Jie and Catani, Filippo and Hellevang, Helge and Tang, Huiming and Sun, Xinshuang and Huang, Dewei},
title = {Physics‐Informed Deep Learning for Revealing the Evolutionary Characteristics of Landslides Induced by Rainfall Process},
journal = {Geophysical Research Letters},
year = {2025},
volume = {52},
number = {21},
doi = {10.1029/2025gl117356}
}
EUVIMED