Enhanced physics‐informed neural networks for efficient modelling of hydrodynamics in river networks
Hydrological Processes · 2024-04 · 38 (4)
DOI: 10.1002/hyp.15143 ↗Kurz gefasst
Fachartikel in der Zeitschrift Hydrological Processes, online erschienen am 11.04.2024. Verfasst von Xiao Luo und 6 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 81 Literaturangaben. Gefördert von: Fundamental Research Funds for the Central Universities, National Natural Science Foundation of China, National Key Research and Development Program of China.
Abstract (Originalsprache)
This article enhances the physics‐informed neural networks (PINNs) method to effectively model the hydrodynamics of real‐world river networks with irregular cross‐sections. First, we pre‐process hydraulic parameters to optimize training speed without compromising accuracy, achieving a 91.67% acceleration compared with traditional methods. To address the vanishing gradient problem, layer normalization is also incorporated into the architecture. We also introduce novel physical constraints—water level range and junction node equations—to ensure effective training convergence and enrich the model with additional physical insights. Two practical case studies using HEC‐RAS benchmarks demonstrate that our improved PINN method can predict river network hydrodynamics with less data and is less sensitive to time step size, allowing for longer computational time steps. Incorporating physical knowledge, our enhanced PINN methodology emerges as an efficient and promising avenue for modelling the complexities of hydrodynamic processes in natural river networks.
Förderung
- Fundamental Research Funds for the Central Universities
- National Natural Science Foundation of China
- National Key Research and Development Program of China
Zitieren
APA
Luo, X., Yuan, S., Tang, H., Xu, D., Ran, Q., Cen, Y., & Liang, D. (2024). Enhanced physics‐informed neural networks for efficient modelling of hydrodynamics in river networks. Hydrological Processes, 38(4). https://doi.org/10.1002/hyp.15143
Vancouver
Luo X, Yuan S, Tang H, Xu D, Ran Q, Cen Y, et al. Enhanced physics‐informed neural networks for efficient modelling of hydrodynamics in river networks. Hydrological Processes. 2024;38(4). doi:10.1002/hyp.15143
BibTeX
@article{Luo2024,
author = {Luo, Xiao and Yuan, Saiyu and Tang, Hongwu and Xu, Dong and Ran, Qihua and Cen, Yuhao and Liang, Dongfang},
title = {Enhanced physics‐informed neural networks for efficient modelling of hydrodynamics in river networks},
journal = {Hydrological Processes},
year = {2024},
volume = {38},
number = {4},
doi = {10.1002/hyp.15143}
}
EUVIMED