Topology enables learning-based hydrodynamic prediction of the global river system
cs.LG, physics.geo-ph
Submitted: 2026-02-25
Updated: 2026-08-24
Comments: 21 pages, 4 figures. Main text only; the supplementary materials accompany the journal version
License: http://creativecommons.org/licenses/by/4.0/
The gist: Accurate river prediction is essential for water, food and energy security, yet remains challenging across entire river networks.
Terminology
Abstract
Accurate river prediction is essential for water, food and energy security, yet remains challenging across entire river networks. Machine learning has transformed Earth-system modeling, but a system-level advance for river prediction lags for lack of reliable data. Exploiting the connectivity and dissipative dynamics of rivers, we introduce GraphRiverCast, a neural model for global river systems that predicts daily multivariate hydrodynamics at every reach of a 0.25°network with only sparse gauges and no initial state. It shows no intrinsic skill decay with lead time, outperforms leading global river models by 25% in accuracy, and robustly generalizes to ungauged reaches and finer resolutions. GraphRiverCast lifts learning-based river prediction from isolated basins to a unified global system and offers insights for machine learning in data-scarce Earth systems.
Sources
- Physics-aware Machine Learning Revolutionizes Scientific Paradigm for Machine Learning and Process-based Hydrology
- GraphCast: Learning skillful medium-range global weather forecasting
- RiverMamba: A State Space Model for Global River Discharge and Flood Forecasting
- The Merit of River Network Topology for Neural Flood Forecasting
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks