Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.15614 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908458967629824 |
|---|---|
| author | Holmberg, Edward Pokhrel, Pujan Zoch, Maximilian Ioup, Elias Pathak, Ken Sloan, Steven Niles, Kendall Ratcliff, Jay Flanagin, Maik Guetl, Christian Simeonov, Julian Abdelguerfi, Mahdi |
| author_facet | Holmberg, Edward Pokhrel, Pujan Zoch, Maximilian Ioup, Elias Pathak, Ken Sloan, Steven Niles, Kendall Ratcliff, Jay Flanagin, Maik Guetl, Christian Simeonov, Julian Abdelguerfi, Mahdi |
| contents | Physics-based solvers like HEC-RAS provide high-fidelity river forecasts but are too computationally intensive for on-the-fly decision-making during flood events. The central challenge is to accelerate these simulations without sacrificing accuracy. This paper introduces a deep learning surrogate that treats HEC-RAS not as a solver but as a data-generation engine. We propose a hybrid, auto-regressive architecture that combines a Gated Recurrent Unit (GRU) to capture short-term temporal dynamics with a Geometry-Aware Fourier Neural Operator (Geo-FNO) to model long-range spatial dependencies along a river reach. The model learns underlying physics implicitly from a minimal eight-channel feature vector encoding dynamic state, static geometry, and boundary forcings extracted directly from native HEC-RAS files. Trained on 67 reaches of the Mississippi River Basin, the surrogate was evaluated on a year-long, unseen hold-out simulation. Results show the model achieves a strong predictive accuracy, with a median absolute stage error of 0.31 feet. Critically, for a full 67-reach ensemble forecast, our surrogate reduces the required wall-clock time from 139 minutes to 40 minutes, a speedup of nearly 3.5 times over the traditional solver. The success of this data-driven approach demonstrates that robust feature engineering can produce a viable, high-speed replacement for conventional hydraulic models, improving the computational feasibility of large-scale ensemble flood forecasting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_15614 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Accelerating HEC-RAS: A Recurrent Neural Operator for Rapid River Forecasting Holmberg, Edward Pokhrel, Pujan Zoch, Maximilian Ioup, Elias Pathak, Ken Sloan, Steven Niles, Kendall Ratcliff, Jay Flanagin, Maik Guetl, Christian Simeonov, Julian Abdelguerfi, Mahdi Machine Learning Artificial Intelligence Physics-based solvers like HEC-RAS provide high-fidelity river forecasts but are too computationally intensive for on-the-fly decision-making during flood events. The central challenge is to accelerate these simulations without sacrificing accuracy. This paper introduces a deep learning surrogate that treats HEC-RAS not as a solver but as a data-generation engine. We propose a hybrid, auto-regressive architecture that combines a Gated Recurrent Unit (GRU) to capture short-term temporal dynamics with a Geometry-Aware Fourier Neural Operator (Geo-FNO) to model long-range spatial dependencies along a river reach. The model learns underlying physics implicitly from a minimal eight-channel feature vector encoding dynamic state, static geometry, and boundary forcings extracted directly from native HEC-RAS files. Trained on 67 reaches of the Mississippi River Basin, the surrogate was evaluated on a year-long, unseen hold-out simulation. Results show the model achieves a strong predictive accuracy, with a median absolute stage error of 0.31 feet. Critically, for a full 67-reach ensemble forecast, our surrogate reduces the required wall-clock time from 139 minutes to 40 minutes, a speedup of nearly 3.5 times over the traditional solver. The success of this data-driven approach demonstrates that robust feature engineering can produce a viable, high-speed replacement for conventional hydraulic models, improving the computational feasibility of large-scale ensemble flood forecasting. |
| title | Accelerating HEC-RAS: A Recurrent Neural Operator for Rapid River Forecasting |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2507.15614 |