Global River Forecasting with a Topology-Informed AI Foundation Model
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911469430374400 |
|---|---|
| author | Ren, Hancheng Zhao, Gang Wang, Shuo Slater, Louise Yamazaki, Dai Liu, Shu Fan, Jingfang Cui, Shibo Yu, Ziming Kang, Shengyu Zuo, Depeng Peng, Dingzhi Xu, Zongxue Pang, Bo |
| author_facet | Ren, Hancheng Zhao, Gang Wang, Shuo Slater, Louise Yamazaki, Dai Liu, Shu Fan, Jingfang Cui, Shibo Yu, Ziming Kang, Shengyu Zuo, Depeng Peng, Dingzhi Xu, Zongxue Pang, Bo |
| contents | River systems operate as inherently interconnected continuous networks, meaning river hydrodynamic simulation ought to be a systemic process. However, widespread hydrology data scarcity often restricts data-driven forecasting to isolated predictions. To achieve systemic simulation and reduce reliance on river observations, we present GraphRiverCast (GRC), a topology-informed AI foundation model designed to simulate multivariate river hydrodynamics in global river systems. GRC is capable of operating in a "ColdStart" mode, generating predictions without relying on historical river states for initialization. In 7-day global pseudo-hindcasts, GRC-ColdStart functions as a robust standalone simulator, achieving a Nash-Sutcliffe Efficiency (NSE) of approximately 0.82 without exhibiting the significant error accumulation typical of autoregressive paradigms. Ablation studies reveal that topological encoding serves as indispensable structural information in the absence of historical states, explicitly guiding hydraulic connectivity and network-scale mass redistribution to reconstruct flow dynamics. Furthermore, when adapted locally via a pre-training and fine-tuning strategy, GRC consistently outperforms physics-based and locally-trained AI baselines. Crucially, this superiority extends from gauged reaches to full river networks, underscoring the necessity of topology encoding and physics-based pre-training. Built on a physics-aligned neural operator architecture, GRC enables rapid and cross-scale adaptive simulation, establishing a collaborative paradigm bridging global hydrodynamic knowledge with local hydrological reality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_22293 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Global River Forecasting with a Topology-Informed AI Foundation Model Ren, Hancheng Zhao, Gang Wang, Shuo Slater, Louise Yamazaki, Dai Liu, Shu Fan, Jingfang Cui, Shibo Yu, Ziming Kang, Shengyu Zuo, Depeng Peng, Dingzhi Xu, Zongxue Pang, Bo Machine Learning Geophysics River systems operate as inherently interconnected continuous networks, meaning river hydrodynamic simulation ought to be a systemic process. However, widespread hydrology data scarcity often restricts data-driven forecasting to isolated predictions. To achieve systemic simulation and reduce reliance on river observations, we present GraphRiverCast (GRC), a topology-informed AI foundation model designed to simulate multivariate river hydrodynamics in global river systems. GRC is capable of operating in a "ColdStart" mode, generating predictions without relying on historical river states for initialization. In 7-day global pseudo-hindcasts, GRC-ColdStart functions as a robust standalone simulator, achieving a Nash-Sutcliffe Efficiency (NSE) of approximately 0.82 without exhibiting the significant error accumulation typical of autoregressive paradigms. Ablation studies reveal that topological encoding serves as indispensable structural information in the absence of historical states, explicitly guiding hydraulic connectivity and network-scale mass redistribution to reconstruct flow dynamics. Furthermore, when adapted locally via a pre-training and fine-tuning strategy, GRC consistently outperforms physics-based and locally-trained AI baselines. Crucially, this superiority extends from gauged reaches to full river networks, underscoring the necessity of topology encoding and physics-based pre-training. Built on a physics-aligned neural operator architecture, GRC enables rapid and cross-scale adaptive simulation, establishing a collaborative paradigm bridging global hydrodynamic knowledge with local hydrological reality. |
| title | Global River Forecasting with a Topology-Informed AI Foundation Model |
| topic | Machine Learning Geophysics |
| url | https://arxiv.org/abs/2602.22293 |