Physics-Informed Residual Convolutional Network Model for Depth-Averaged Landslide Dynamics
Applied Sciences · 02.07.2026 · 16 (13) · 6637
DOI: 10.3390/app16136637 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 02.07.2026. Verfasst von Yuming Wu und 1 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Plan Project of Linzhi, Xizang, Key Project of Innovation LREIS.
Abstract (Originalsprache)
Rapid landslide motions control impact area, flow velocity, deposition pattern, and, in extreme cases, are a river-blocking hazard; therefore, reliable dynamic simulations are of direct importance to engineering–geological hazard assessments. Depth-averaged models provide an efficient framework for simulating large-scale mass movements, but conventional physics-informed neural networks (PINNs) remain challenged with regard to nonlinear flows, which can limit their applicability in landslide analysis. To address these limitations, this study develops a physics-informed residual convolutional network model (PI-RCN) for depth-averaged landslide dynamics. The proposed framework combines sequential residual learning with depth-wise separable convolutions (DSCs) and incorporates physics-based residuals, mass conservation, and hard constraints to preserve physical consistency during time marching. The model is evaluated using a 1+1D frictionless dam-break benchmark, a Hong Kong landslide, and the Yigong rock avalanche. Results show that PI-RCN accurately reproduces the benchmark flow evolution with substantially fewer trainable parameters than a baseline fully connected PINN. In the Hong Kong case, the model demonstrates improved convergence stability and optimization efficiency. In the Yigong case, PI-RCN reproduces the main spatiotemporal evolution and multi-stage velocity variation of a long-runout rock avalanche. These results suggest that PI-RCN provides a useful physics-informed framework for efficient and consistent landslide dynamic simulation.
Förderung
- Science and Technology Plan Project of Linzhi, Xizang
- Key Project of Innovation LREIS
Zitieren
APA
Wu, Y., & Yang, Z. (2026). Physics-Informed Residual Convolutional Network Model for Depth-Averaged Landslide Dynamics. Applied Sciences, 16(13), 6637. https://doi.org/10.3390/app16136637
Vancouver
Wu Y, Yang Z. Physics-Informed Residual Convolutional Network Model for Depth-Averaged Landslide Dynamics. Applied Sciences. 2026;16(13):6637. doi:10.3390/app16136637
BibTeX
@article{Wu2026,
author = {Wu, Yuming and Yang, Zhihua},
title = {Physics-Informed Residual Convolutional Network Model for Depth-Averaged Landslide Dynamics},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {13},
pages = {6637},
doi = {10.3390/app16136637}
}
EUVIMED