Physics-Informed Neural Network Surrogate Models for River Stage Prediction

Суррогатные модели на основе физически информированных нейронных сетей для прогнозирования уровня воды в реке
Maximilian Zöch, Edward A. Holmberg, Pujan Pokhrel, Ken Pathak, Steven D. Sloan, Kendall N. Niles, Jay Ratcliff, Maik C. Flanagin, Elias Ioup, Christian Gütl, Mahdi Abdelguerfi
2025-03-21

HEC-RASPhysics-Informed Neural NetworksSaint-Venant equationsriver stage predictionsurrogate models
This work investigates the feasibility of using Physics-Informed Neural Networks (PINNs) as surrogate models for river stage prediction, aiming to reduce computational cost while maintaining predictive accuracy. Our primary contribution demonstrates that PINNs can successfully approximate HEC-RAS numerical solutions when trained on a single river, achieving strong predictive accuracy with generally low relative errors, though some river segments exhibit higher deviations. By integrating the governing Saint-Venant equations into the learning process, the proposed PINN-based surrogate model enforces physical consistency and significantly improves computational efficiency compared to HEC-RAS. We evaluate the model's performance in terms of accuracy and computational speed, demonstrating that it closely approximates HEC-RAS predictions while enabling real-time inference. These results highlight the potential of PINNs as effective surrogate models for single-river hydrodynamics, offering a promising alternative for computationally efficient river stage forecasting. Future work will explore techniques to enhance PINN training stability and robustness across a more generalized multi-river model.
1
Embedding the Saint-Venant equations enforces physical consistency in the learned river-stage predictions.
2
Generalization to multiple rivers remains future work, with training stability and robustness identified as challenges.
3
Physics-Informed Neural Networks can successfully approximate HEC-RAS river-stage solutions when trained on a single river.
4
The PINN surrogate substantially reduces computational cost relative to HEC-RAS and supports real-time inference.
5
The surrogate model achieves strong predictive accuracy with generally low relative errors, although deviations are higher in some river segments.

single-river hydrodynamics and river stage dynamics represented by HEC-RAS numerical solutions

the predictive accuracy, physical consistency, computational efficiency, and real-time inference performance of PINN-based surrogate models for river stage

Publication Details
Publication Date
2025-03-21
Journal
Publisher
ISSN
Access Type
Author Information
Authors
Maximilian Zöch
Edward A. Holmberg
Pujan Pokhrel
Ken Pathak
Steven D. Sloan
Kendall N. Niles
Jay Ratcliff
Maik C. Flanagin
Elias Ioup
Christian Gütl
Mahdi Abdelguerfi
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%