发表机构
Argonne National Laboratory; Purdue University（阿贡国家实验室; 普渡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
Hapi是一种U-Net Swin Transformer模型，利用三维分层注意力预测美国本土多变量水文变量，在洪水检测和日流量再现上优于物理模型，且推理高效。
AI 中文摘要
提前数天进行准确的洪水预报对于防洪、水资源管理和应急响应至关重要。在大陆范围内以高分辨率生成这些预报，需要结合局部水文细节以及从流域到天气系统的空间背景。我们开发了Hapi，一种U-Net Swin Transformer，它利用精细的三维块和分层移位窗口注意力来预测美国本土的流量、地表径流、雪水当量和土壤湿度。该模型以0.05°分辨率生成24-72小时的预报，并通过学习到的拉普拉斯任务权重调整每个变量对训练的贡献。在2024年测试数据上，使用来自ERA5-Land的重建天气和陆面输入，Hapi在洪水检测方面优于基于物理的运营模型和最先进的AI模型。针对3,881个美国地质调查局测站的独立验证以及飓风海伦妮案例研究支持了其在再现日流量方面优于基于物理模型的优势。对照实验表明，学习到的任务权重增强了罕见洪水的检测，这尤其对降水输入的变化敏感。Hapi在单个A100 GPU上以平均推理时间0.11秒生成了覆盖美国本土的四变量、72小时预报。
英文摘要
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.
