Physics‐Informed Neural Networks of the Saint‐Venant Equations for Downscaling a Large‐Scale River Model
Физически информированные нейронные сети для уравнений Сен-Венана при понижении масштаба крупномасштабной речной модели
2023-02-01
SCID: 54.1/9q5khm9y
Discuss with AI
Fourier feature embeddingsSaint-Venant equationsphysics-informed neural networksriver model downscalingsubgrid-scale flow simulation
Figures from the paper
Abstract (AI)
Abstract Large‐scale river models are being refined over coastal regions to improve the scientific understanding of coastal processes, hazards and responses to climate change. However, coarse mesh resolutions and approximations in physical representations of tidal rivers limit the performance of such models at resolving the complex flow dynamics especially near the river‐ocean interface, resulting in inaccurate simulations of flood inundation. In this research, we propose a machine learning (ML) framework based on the state‐of‐the‐art physics‐informed neural network (PINN) to simulate the downscaled flow at the subgrid scale. First, we demonstrate that PINN is able to assimilate observations of various types and solve the one‐dimensional (1‐D) Saint‐Venant equations (SVE) directly. We perform the flow simulations over a floodplain and along an open channel in several synthetic case studies. The PINN performance is evaluated against analytical solutions and numerical models. Our results indicate that the PINN solutions of water depth have satisfactory accuracy with limited observations assimilated. In the case of flood wave propagation induced by storm surge and tide, a new neural network architecture is proposed based on Fourier feature embeddings that seamlessly encodes the periodic tidal boundary condition in the PINN's formulation. Furthermore, we show that the PINN‐based downscaling can produce more reasonable subgrid solutions of the along‐channel water depth by assimilating observational data. The PINN solution outperforms the simple linear interpolation in resolving the topography and dynamic flow regimes at the subgrid scale. This study provides a promising path toward improving emulation capabilities in large‐scale models to characterize fine‐scale coastal processes.
Key Findings
1
A Fourier-feature neural architecture seamlessly encodes periodic tidal boundary conditions for storm-surge- and tide-driven flood-wave simulations.
2
A physics-informed neural network (PINN) framework solves one-dimensional Saint-Venant equations for subgrid-scale downscaling of large-scale river models.
3
Observation-informed PINN downscaling produces more reasonable along-channel subgrid water-depth solutions than simple linear interpolation, resolving topography and dynamic flow regimes more effectively.
4
PINNs successfully assimilate diverse observation types and achieve satisfactory water-depth accuracy with limited observations in synthetic floodplain and open-channel cases.
5
The framework offers a promising approach for improving large-scale model emulation of fine-scale coastal river processes and flood inundation.
Research Object
large-scale tidal river and floodplain flow systems near the river–ocean interface
Research Subject
subgrid-scale downscaling of water depth and dynamic flow regimes under storm-surge and tidal forcing
Publication Details
Publication Date
2023-02-01
Journal
Publisher
ISSN
Cited by
136
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai3
Cited by5
A physics-informed neural network method for modeling one-dimensional water flow without roughness coefficient input2025
Application of PINNs to Define Roughness Coefficients for Channel Flow Problems2025
Physics-Informed Neural Network for Reconstructing Free-Surface Transient Flow Fields in Long-Distance Water-Conveyance Tunnels from Sparse Observations2026
APPLICATION OF PHYSICS-INFORMED NEURAL NETWORKS (PINN) COUPLED WITH ONE-DIMENSIONAL UNSTEADY FLOW SIMULATION TO OPEN CHANNEL FLOW2025
Physics-Informed Neural Network Surrogate Models for River Stage Prediction2025