EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Physics-Inspired Multi-Flow Graph Neural Network with Explicit Flow Allocation for Sustainable Rainfall-Driven Flood Simulation

Xinru Zhang, Fuxin Chai, Hongping Zhang, Yuchen Xiao, Huimin Xu, Ying Ding, Xi Yang

Sustainability · 12.11.2026 · 18 (22) · 11514

DOI: 10.3390/su182211514 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sustainability, online erschienen am 12.11.2026. Verfasst von Xinru Zhang und 6 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Graph-based surrogate models offer an efficient alternative to hydrodynamic simulations, but accurately representing multi-directional runoff propagation remains challenging. This study proposes a physics-inspired multi-flow graph neural network with an explicit flow allocation mechanism for rainfall-driven surface runoff simulation. The method allows runoff information to propagate through multiple downstream pathways and dynamically regulates their relative contributions according to local water-surface elevation differences. The allocation coefficients are interpreted as relative information weights rather than volumetric fluxes, avoiding unverified mass-conservation claims. The framework was evaluated using flood simulation data from Harris County, Texas, and compared with a single-flow baseline and a multi-flow model without explicit allocation. The models were trained on nine watershed–event cases, validated on three cases, and evaluated on an independent test set of 51 independent watershed–event cases. Introducing multi-flow connectivity alone increased the root mean square error by 5.4% relative to the single-flow baseline, whereas the proposed model achieved the best performance, with a root mean square error of 0.164 m, a Nash–Sutcliffe efficiency of 0.880, and a Pearson correlation coefficient of 0.950. The results indicate that increasing graph connectivity is insufficient by itself; physics-inspired directional allocation is essential for representing multi-directional runoff propagation in graph-based flood surrogate models. By improving simulation efficiency and directional representation, the proposed method contributes to the goals of sustainable flood management and community resilience.

Zitieren

APA

Zhang, X., Chai, F., Zhang, H., Xiao, Y., Xu, H., Ding, Y., & Yang, X. (2026). A Physics-Inspired Multi-Flow Graph Neural Network with Explicit Flow Allocation for Sustainable Rainfall-Driven Flood Simulation. Sustainability, 18(22), 11514. https://doi.org/10.3390/su182211514

Vancouver

Zhang X, Chai F, Zhang H, Xiao Y, Xu H, Ding Y, et al. A Physics-Inspired Multi-Flow Graph Neural Network with Explicit Flow Allocation for Sustainable Rainfall-Driven Flood Simulation. Sustainability. 2026;18(22):11514. doi:10.3390/su182211514

BibTeX
@article{Zhang2026,
  author = {Zhang, Xinru and Chai, Fuxin and Zhang, Hongping and Xiao, Yuchen and Xu, Huimin and Ding, Ying and Yang, Xi},
  title = {A Physics-Inspired Multi-Flow Graph Neural Network with Explicit Flow Allocation for Sustainable Rainfall-Driven Flood Simulation},
  journal = {Sustainability},
  year = {2026},
  volume = {18},
  number = {22},
  pages = {11514},
  doi = {10.3390/su182211514}
}
Kostenlos starten →