Random-walk-path solution of unsteady flow equations for general channel networks

Tang, Hongwu; Luo, Xiangfeng; Yuan, Saiyu; Xiao, Yang; Liang, Dongfang; Gualtieri, Carlo

doi:10.1016/j.jhydrol.2022.128692

Cited by 3 publications

(2 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To further enhance the model's fidelity, conservation equations are integrated at these internal junction nodes, contributing an additional physical insight into the neural network framework. In traditional numerical models, the inclusion of junction equations often leads to heightened complexity and greater computational demands (Jamal & Bhallamudi, 2020; Tang et al, 2022). However, in the context of PINNs, the implementation of the ‘equality of water level’ principle primarily results in an increase in data constraints rather than a significant rise in the model's complexity.…”

Section: Pinns Approachmentioning

confidence: 99%

“…Methods like the separate‐segment approach (Akan & Yen, 1981; Fread, 1973) divide the network into manageable, independent components. More advanced techniques, such as the JPWSPC (Zhu & Chen, 2019) and random‐walk‐path method (Tang et al, 2022), build on foundational three‐step algorithms (Fang et al, 2012; Sen & Garg, 2002; Zhang & Shen, 2007) to offer efficient solutions for water stage prediction. Overall, these advances in numerical methods continue to enhance both the accuracy and computational efficiency of hydraulic modelling in complex channel networks.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enhanced physics‐informed neural networks for efficient modelling of hydrodynamics in river networks

Luo,

Yuan,

Tang

et al. 2024

Hydrological Processes

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Pinns Approachmentioning

confidence: 99%