mlsanityData to 7 Oct 2026

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

arXiv 2609.22702 ↗First posted 19 Sep 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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 0.05circ 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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 52 references that are in the map. First posted on arXiv 19 Sep 2026.

Builds on

22 of 52 references.

References · 22

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  3. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  4. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
  5. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
  6. 2021Perceiver IO: A General Architecture for Structured Inputs & Outputscited by 616
  7. 2023EVA-02: A Visual Representation for Neon Genesiscited by 377
  8. 2022Message Passing Neural PDE Solverscited by 368
  9. 2023ClimaX: A foundation model for weather and climatecited by 325
  10. 2025Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Freecited by 266
  11. 2023FuXi: A cascade machine learning forecasting system for 15-day global weather forecastcited by 237
  12. 2024Rotary Position Embedding for Vision Transformercited by 226
10 more
  1. 2023Scaling transformer neural networks for skillful and reliable medium-range weather forecastingcited by 106
  2. 2019Towards Learning Universal, Regional, and Local Hydrological Behaviors via Machine-Learning Applied to Large-Sample Datasetscited by 68
  3. 2024Prithvi WxC: Foundation Model for Weather and Climatecited by 28
  4. 2022Differentiable, learnable, regionalized process-based models with physical outputs can approach state-of-the-art hydrologic prediction accuracycited by 21
  5. 2021MC-LSTM: Mass-Conserving LSTMcited by 17
  6. 2021Flood forecasting with machine learning models in an operational frameworkcited by 14
  7. 2025AERIS: Argonne Earth Systems Model for Reliable and Skillful Predictionscited by 8
  8. 2020Rainfall-Runoff Prediction at Multiple Timescales with a Single Long Short-Term Memory Networkcited by 6
  9. 2025RiverMamba: A State Space Model for Global River Discharge and Flood Forecastingcited by 2
  10. 2024Towards Generalized Hydrological Forecasting using Transformer Models for 120-Hour Streamflow Predictioncited by 1

Built on by

Not cited yet.