arXiv AI By Yanjie Tong, Phillip Si, Yuan Qiu, Peng Chen

C-STRIDE: An Observation-Driven AI Digital Twin for Predicting Basin-Wide Flood Fields from Sparse Stream-Gauge Histories

Read the original on arXiv AI →

The Flow has not summarised this story yet — read it at arXiv AI.

arXiv AI
Jul 28

AIFL: A Global Daily Streamflow Forecasting Model Using a Deterministic LSTM Pre-trained on ERA5-Land and Fine-tuned on IFS

arXiv:2602. 16579v2 Announce Type: replace-cross Abstract: Reliable global streamflow forecasting is essential for flood preparedness and water resource management, yet data-driven models often suffer from a performance gap when transitioning from historical reanalysis to operational forecast products.

By Maria Luisa Taccari, Kenza Tazi, Ois\'in M. Morrison, Andreas Grafberger, Juan Colonese, Corentin Carton de Wiart, Christel Prudhomme, Cinzia Mazzetti, Matthew Chantry, Florian Pappenberger
arXiv AI
Oct 27

EvoBench: An Evolving, Diagnostic Benchmark Framework for Environmental Modeling

EvoBench is a diagnostic benchmark framework designed to reveal where and when machine‑learning models for environmental variables fail, rather than relying on a single average accuracy score. It tracks model performance over time and across spatial extrapolation, highlighting issues such as non‑stationarity, poor performance at unmonitored sites, and under‑prediction of rare events like floods. In a case study on daily streamflow prediction across 9,000 U.S. basins, EvoBench shows that no model dominates all scenarios and that targeted fixes can mitigate identified weaknesses.

By Yiming Sun, Yuan Zhang, Qi Cheng, Yingda Fan, Runlong Yu, Yiqun Xie, Xiaowei Jia
arXiv Machine Learning
Oct 21

Learning global river system hydrodynamics with a topology-informed foundation model

The paper introduces GraphRiverCast (GRC), a topology-informed foundation model that predicts daily multivariate hydrodynamics across the global river network using sparse gauge data. By leveraging river connectivity and energetics, GRC outperforms both physics-based and traditional machine-learning models, maintaining skill over long lead times and generalizing to ungauged reaches and finer-resolution networks. The approach demonstrates how incorporating system structure can improve predictions in observation-limited Earth systems.

By Hancheng Ren, Gang Zhao, Shuo Wang, Louise Slater, Dai Yamazaki, Shu Liu, Jingfang Fan, Xueying Li, Shibo Cui, Ziming Yu, Shengyu Kang, Depeng Zuo, Dingzhi Peng, Zongxue Xu, Bo Pang