arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.02876cs.LG
收藏

迈向基于图神经网络的多网格代理模型以实现快速洪水预报

Toward an Operational GNN-Based Multimesh Surrogate for Fast Flood Forecasting

Université de Toulouse, INP, IRIT, Toulouse, France(图卢兹大学, 国立图卢兹综合理工学院, 计算机与人工智能研究所, 图卢兹, 法国);Nvidia(英伟达);BRL Ingénierie(BRL工程公司)

Valentin Mercier, Serge Gratton, Lapeyre Corentin, Gwenaël Chevallet

AI总结:

本文提出基于图神经网络的多网格代理模型,用于快速洪水预报,通过合成数据训练并结合多网格连接性提升预测精度,实验表明该方法在洪峰流量和淹没地图预测中优于传统高精度模拟。

摘要:

操作性洪水预报仍依赖于高保真二维水力求解器,但其运行时间对于大都市洪水平原的快速决策支持可能是不可接受的。与此同时,基于AI的代理模型在计算物理学的多个领域中显示出加速昂贵高保真模拟的潜力。我们针对法国下特河(Lower Têt River)的问题,从一个生产级Telemac2D模型出发,该模型在高分辨率无结构有限元网格上定义,节点数超过4×10⁵。从该设置中,我们构建了一个合成但操作上可行的洪水事件数据库,涵盖几种代表性的水文图谱和峰值流量。在此数据库之上,我们开发了一个基于投影网格和多网格连接性的图神经网络代理。投影网格策略在保持原始Telemac模拟的高保真监督的同时,使训练变得可行,而多网格构建在不增加网络深度的情况下扩大了有效的空间感受野。我们进一步研究了显式流量特征Q(t)和推前训练对长自回归滚动的影响。实验表明,在边界驱动的设置中,对Q(t)的条件是关键的,一旦模型正确条件化,多网格连接性会带来额外的收益,而推前训练进一步提高了滚动稳定性。在测试的配置中,Q(t)、多网格连接性和推前的组合提供了最佳整体结果。这些收益在代理网格上的水力变量和插值到共同25米正则网格的淹没地图上均被观察到,并与原始高分辨率Telemac解法进行比较。在所研究的案例中,学习到的代理在单个NVIDIA A100 GPU上约0.4秒内生成6小时预测,相比之下,参考模拟在56个CPU核心上需要约180分钟。这些结果支持图基代理作为工业水力求解器的实用补充,用于操作性洪水制图。

英文摘要:

Operational flood forecasting still relies on high-fidelity two-dimensional hydraulic solvers, but their runtime can be prohibitive for rapid decision support on large urban floodplains. In parallel, AI-based surrogate models have shown strong potential in several areas of computational physics for accelerating otherwise expensive high-fidelity simulations. We address this issue on the lower Têt River (France), starting from a production-grade Telemac2D model defined on a high-resolution unstructured finite-element mesh with more than $4\times 10^5$ nodes. From this setup, we build a learning-ready database of synthetic but operationally grounded flood events covering several representative hydrograph families and peak discharges. On top of this database, we develop a graph-neural surrogate based on projected meshes and multimesh connectivity. The projected-mesh strategy keeps training tractable while preserving high-fidelity supervision from the original Telemac simulations, and the multimesh construction enlarges the effective spatial receptive field without increasing network depth. We further study the effect of an explicit discharge feature $Q(t)$ and of pushforward training for long autoregressive rollouts. The experiments show that conditioning on $Q(t)$ is essential in this boundary-driven setting, that multimesh connectivity brings additional gains once the model is properly conditioned, and that pushforward further improves rollout stability. Among the tested configurations, the combination of $Q(t)$, multimesh connectivity, and pushforward provides the best overall results. These gains are observed both on hydraulic variables over the surrogate mesh and on inundation maps interpolated onto a common $25\,\mathrm{m}$ regular grid and compared against the original high-resolution Telemac solution. On the studied case, the learned surrogate produces 6-hour predictions in about $0.4\,\mathrm{s}$ on a single NVIDIA A100 GPU, compared with about $180\,\mathrm{min}$ on 56 CPU cores for the reference simulation. These results support graph-based surrogates as practical complements to industrial hydraulic solvers for operational flood mapping.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑