Skip to content

Hapi: A Multivariable Land-Surface Transformer for Medium-Range Hydrological Forecasting at Continental Scale

Sep 2026 · 0 citations · 52 references
Computer Science

Abstract

Accurate flood forecasts several days in advance are essential for flood control, water-resource management, and emergency response. A central challenge is to produce high-resolution forecasts across continental domains where hydrological behavior varies widely from place to place. We developed Hapi, a U-Net Swin Transformer that uses fine three-dimensional patches and hierarchical shifted-window attention to forecast river discharge, surface runoff, snow water equivalent, and soil wetness index across the contiguous United States. The model produces medium-range forecasts (24--72~h) at $0.05^{\circ}$ resolution with adaptive task weighting and required only 0.11 seconds for a four-variable 72-h CONUS forecast on one A100 GPU. In a held-out 2024 potential-skill evaluation with ERA5-Land inputs prescribed over the forecast horizon, Hapi achieved the highest F1-score for floods in 20 of 21 comparisons across seven GloFAS return periods and three forecast leads. Independent validation against observed daily discharge at 3{,}881 U.S. Geological Survey gauges showed that Hapi achieved the highest median Nash--Sutcliffe efficiency at every lead, supported by regional-cluster bootstrap intervals. In a matched 24-h comparison of loss formulations, adaptive task balancing produced the lowest discharge errors and the highest F1-score for floods.

View source

Similar papers

#artificial intelligence Preprint Sep 2026

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

Emergency managers need to know where floodwater is, how deep it is, and how it will change over the coming hours across an entire river basin. During a flood, however, real-time measurements come from only a handful of stream gauges, and high-resolution hydrodynamic models are too costly to rerun each time new data ar...

Yan-Jie Tong, Phillip Si, Yuan Qiu et al. · 0 citations
Sep 2026

Advantages and Challenges of Mid-latitude Super-Ensemble Coastal Water Level Forecasting

In mid-latitude regions, year-round coastal water level forecast systems serve the public with reliable and consistent forecasts ranging from high-tide floods to extreme events. The Stevens Flood Advisory System (SFAS) is a probabilistic coastal water level forecast system forced by a super-ensemble of global atmosph...

Zi-Yu Chen, Philip M. Orton, N. Georgas et al. · 0 citations
Preprint Aug 2026

Bridging short- and medium-range weather forecasting with machine learning

Nested-EAGLE (Experimental Artificial intelligence Global and Limited-area Ensemble) is presented, showing that the skill gains for near-surface fields stem from incorporating high-resolution regional analysis data into training through the nesting process, and provides the most accurate forecasts of storm locations at...

Timothy A. Smith, Mariah Pope, Sergey Frolov et al. · 2 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.