An Adaptive-Horizon Graph Neural Operator for coupled surrogate morphodynamic modelling
Abstract
Morphodynamic simulations require repeated coupling between hydrodynamic solvers, sediment transport modules, and bed updating. For long duration, multi-scenario simulations on large unstructured meshes, such coupling is computationally demanding. This study proposes an Adaptive-Horizon Graph Neural Operator (AH-GNO) that formulates bed evolution as a graph operator learning problem from recent hydrodynamic and topographic states to predict future bed elevation increments. The model operates directly on the native unstructured meshes. The approach integrates area-weighted graph learning, historical state selection, and forecast horizon estimation, allowing the effective history length (K) and update interval (B) to vary with the evolving flow and bed state. Using Telemac2D/GAIA solutions as supervised numerical references, the framework is evaluated on the official Bump and Yen bend benchmarks and on a field-scale application (Waiho River, New Zealand). Results show that the AH-GNO reproduces the main patterns of bedform migration, bend-scale erosion and deposition, and localized bed adjustment. Across the three cases, the tested CPU-GPU deployment reduced post-training bed-update workflow time from 12~1204 s with GAIA to 0.08~3.34 s with AH-GNO. This improvement corresponds to deployment-specific accelerations of approximately 150~360 times relative to 4-core GAIA CPU configurations, and with 105~186 times gains for 20-core CPU configurations. These results suggest that, while retaining hydrodynamic feedback from TELEMAC-2D, a learned operator for bed updating can provide an efficient acceleration component for morphodynamic scenario analysis and rapid coupled simulation.
Related
- Koopman Neural Operator-based surrogate modelling for high-frequency dynamics of high-speed rail pantographs
- Beyond Compression: Training Latent Representations for Stable Long-Horizon Rollout in Neural Surrogate Solvers
- Dimensionally consistent surrogate modelling through dimensional analysis and harmonic expansions
- Reconstruction of Unobserved Core Electron Density in Tokamak Plasmas with a Neural Operator Transport Surrogate and Uncertainty Quantification
- Fast and Differentiable MHD Surrogate for Solar Wind using Neural Operator
BibTeX
@misc{cao2026adaptivehorizon,
title = {{An Adaptive-Horizon Graph Neural Operator for coupled surrogate morphodynamic modelling}},
author = {Ying Cao and Yifan Yang and Junqiang Xia and Julia C. Mullarney and Mário J. Franca},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.22432},
eprint = {2610.22432},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.22432},
}
RIS
TY - UNPB
TI - An Adaptive-Horizon Graph Neural Operator for coupled surrogate morphodynamic modelling
AU - Ying Cao
AU - Yifan Yang
AU - Junqiang Xia
AU - Julia C. Mullarney
AU - Mário J. Franca
PY - 2026
DA - 2026/10/22
PB - arXiv
DO - 10.48550/arxiv.2610.22432
UR - https://arxiv.org/abs/2610.22432
AB - Morphodynamic simulations require repeated coupling between hydrodynamic solvers, sediment transport modules, and bed updating. For long duration, multi-scenario simulations on large unstructured meshes, such coupling is computationally demanding. This study proposes an Adaptive-Horizon Graph Neural Operator (AH-GNO) that formulates bed evolution as a graph operator learning problem from recent hydrodynamic and topographic states to predict future bed elevation increments. The model operates directly on the native unstructured meshes. The approach integrates area-weighted graph learning, historical state selection, and forecast horizon estimation, allowing the effective history length (K) and update interval (B) to vary with the evolving flow and bed state. Using Telemac2D/GAIA solutions as supervised numerical references, the framework is evaluated on the official Bump and Yen bend benchmarks and on a field-scale application (Waiho River, New Zealand). Results show that the AH-GNO reproduces the main patterns of bedform migration, bend-scale erosion and deposition, and localized bed adjustment. Across the three cases, the tested CPU-GPU deployment reduced post-training bed-update workflow time from 12~1204 s with GAIA to 0.08~3.34 s with AH-GNO. This improvement corresponds to deployment-specific accelerations of approximately 150~360 times relative to 4-core GAIA CPU configurations, and with 105~186 times gains for 20-core CPU configurations. These results suggest that, while retaining hydrodynamic feedback from TELEMAC-2D, a learned operator for bed updating can provide an efficient acceleration component for morphodynamic scenario analysis and rapid coupled simulation.
ER -