How Sparse and How Noisy? Systematic Benchmarking of Inverse Physics-Informed Neural Networks for Manning Friction Estimation in Shallow Water Equations
Abstract
Physics-informed neural networks (PINNs) offer a promising framework for inverse hydrodynamic modeling by combining sparse observations with governing physical constraints. However, their reliability for estimating hydraulic parameters under data limitations remains insufficiently characterized. This study benchmarks inverse PINN recovery of the Manning friction coefficient in the shallow water equations under controlled variations in observation sparsity, noise, and observed variable type. Two cases are considered: a one-dimensional MacDonald subcritical channel with an analytical steady reference solution, and a two-dimensional sloped channel with a parabolic transverse bed generated using a balanced finite-volume solver. The Manning coefficient is treated as a trainable positive scalar and recovered jointly with the flow field using a two-phase strategy that first fits observations and then incorporates the physics residual. Results show that the two-dimensional case achieves robust friction recovery, with errors below 5% when at least 10 depth and velocity observations are available and noise is at or below 10% of the field standard deviation. Recovery remains stable up to 20% noise with 50 observations, but becomes unreliable with only five observations. In contrast, the one-dimensional case shows a persistent positive bias of about 15% that is largely insensitive to observation count and noise, indicating a structural identifiability limitation rather than a data-density limitation. Observation-type ablation shows that recovery degrades substantially when only depth or velocity is observed, demonstrating that joint depth-velocity information is essential for reliable inverse identification. Overall, the results provide a reproducible benchmark for assessing when inverse PINNs can and cannot reliably estimate Manning friction from sparse and noisy shallow-water observations.
Versions
Related
- HypoNet Nankai PS: rapid hypocenter determination for the Nankai Trough using physics-informed neural networks with three-dimensional P- and S-wave velocity models
- How much does the graph help? An information-parity evaluation of graph neural networks for urban air-quality estimation
- Physics-Informed Machine Learning in Hydrology and Water Resources: A Systematic Bibliometric Analysis
- GeoSim: Benchmarking Multi-Field Neural Operators for Geodynamics
- Benchmarking a new urban scheme in the ORCHIDEE 2.2 land surface model
BibTeX
@misc{radfar2026sparse,
title = {{How Sparse and How Noisy? Systematic Benchmarking of Inverse Physics-Informed Neural Networks for Manning Friction Estimation in Shallow Water Equations}},
author = {Soheil Radfar},
howpublished = {arXiv},
year = {2026},
month = jun,
doi = {10.48550/arxiv.2606.18149},
eprint = {2606.18149},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.18149},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - How Sparse and How Noisy? Systematic Benchmarking of Inverse Physics-Informed Neural Networks for Manning Friction Estimation in Shallow Water Equations
AU - Soheil Radfar
PY - 2026
DA - 2026/06/16
PB - arXiv
DO - 10.48550/arxiv.2606.18149
UR - https://arxiv.org/abs/2606.18149
AB - Physics-informed neural networks (PINNs) offer a promising framework for inverse hydrodynamic modeling by combining sparse observations with governing physical constraints. However, their reliability for estimating hydraulic parameters under data limitations remains insufficiently characterized. This study benchmarks inverse PINN recovery of the Manning friction coefficient in the shallow water equations under controlled variations in observation sparsity, noise, and observed variable type. Two cases are considered: a one-dimensional MacDonald subcritical channel with an analytical steady reference solution, and a two-dimensional sloped channel with a parabolic transverse bed generated using a balanced finite-volume solver. The Manning coefficient is treated as a trainable positive scalar and recovered jointly with the flow field using a two-phase strategy that first fits observations and then incorporates the physics residual. Results show that the two-dimensional case achieves robust friction recovery, with errors below 5% when at least 10 depth and velocity observations are available and noise is at or below 10% of the field standard deviation. Recovery remains stable up to 20% noise with 50 observations, but becomes unreliable with only five observations. In contrast, the one-dimensional case shows a persistent positive bias of about 15% that is largely insensitive to observation count and noise, indicating a structural identifiability limitation rather than a data-density limitation. Observation-type ablation shows that recovery degrades substantially when only depth or velocity is observed, demonstrating that joint depth-velocity information is essential for reliable inverse identification. Overall, the results provide a reproducible benchmark for assessing when inverse PINNs can and cannot reliably estimate Manning friction from sparse and noisy shallow-water observations.
ER -