KNOU-Flood：用预见期感知概率机器学习推进全球径流预报
原标题：KNOU-Flood: Advancing global streamflow forecasting with lead-aware probabilistic machine learning
AI 摘要
研究团队提出 KNOU-Flood，在保持单层 LSTM 与两阶段迁移学习核心不变的前提下，通过更长输入窗口、按预见期输入预报、引入 GraphCast 作为第二预报源以及带公平 CRPS 的潜在噪声集成，改进全球径流预报。在 2,099 个测试流域、2021–2023 年数据上，其 LT1 和 LT10 中位 KGE′ 分别达 0.65 和 0.48，优于 AIFL 复现基线。研究还发现 AIFL 报告的预见期技能衰减很大程度源于预报输入协议，而非预报本身质量。
正文节选
KNOU-Flood: Advancing global streamflow forecasting with lead-aware probabilistic machine learning Abstract Global streamflow forecasting supports flood preparedness, yet data-driven models trained on reanalysis lose skill when driven by operational forecasts, increasingly so with lead time. AIFL addresses this shift with a two-stage transfer-learning recipe and a deterministic LSTM, but it feeds one forecast lead time into the whole input window and gives no uncertainty. We ask how far this ope