用风云四号卫星数据直接预测站点附近短时强降雨，提升预警精度和提前量。
MAGPIE-Net: Predicting short-duration heavy-rainfall events in station neighborhoods from multitemporal FY-4A AGRI observations
- 设计可微的网格到站点映射，让卫星云图直接指导站点预警。
- 0-3小时预报CSI达0.371~0.238，检测率65.1%，领先基线三倍以上。
- 适合需要高精度短临预警的气象部门和防灾应用。
短时强降水预警旨在判断未来数小时内目标站点周边1小时降水量是否会超过阈值。风云四号先进静止气象辐射计（FY-4A AGRI）的多时相红外与水汽观测能捕捉云顶降温、水汽演变和云体扩张等对流启动前兆。然而，多数深度学习临近预报方法通过后处理格点降水预测生成局部预警，使站点邻域事件目标无法直接监督卫星到站点的学习路径。本文提出MAGPIE-Net，其结合对流启动特征、多尺度编码与辅助格点降水诊断，嵌入地理自适应可微的网格到站点映射。站点邻域事件损失直接约束卫星表征及其向不规则站点位置的映射，实现0-3小时事件预测。在2023年中东部中国暖季独立测试中，基于40 km/20 mm h⁻¹定义的临界成功指数（CSI）分别为0.371、0.304和0.238；整体检测率达65.1%，平均提前时间64.6分钟，优于最佳格点输出基线（23.6%检测率，18.3分钟提前时间），且在更小邻域和50 mm h⁻¹阈值下仍具优势。在关键预警阶段（40 km内前1小时降水低于1 mm时），仍能检测51.9%的事件，平均提前38.5分钟。结果表明，面向事件的卫星到站点建模比格点降水建模更有效利用静止卫星云与水汽信息。
原文摘要 · Abstract (English)
Short-duration heavy-rainfall warning determines whether 1 h rainfall will exceed a threshold within a target-station neighborhood over the next few hours. Multitemporal infrared and water-vapor observations from the Fengyun-4A Advanced Geostationary Radiation Imager (FY-4A AGRI) capture cloud-top cooling, moisture evolution, and cloud expansion before substantial surface rainfall develops. However, most deep-learning nowcasting methods convert these signals into local warnings by post-processing gridded precipitation predictions, preventing station-neighborhood event targets from directly supervising the satellite-to-station learning pathway. We propose MAGPIE-Net, which embeds a geographically adaptive, differentiable grid-to-station mapping in a pathway combining convection-initiation features, multiscale encoding, and auxiliary gridded precipitation diagnosis. Station-neighborhood event losses thereby constrain the satellite representation and its mapping to irregular station locations for 0-3 h event prediction. In independent 2023 warm-season tests over central and eastern China, critical success index (CSI) values under the primary 40 km/20 mm h-1 definition were 0.371, 0.304, and 0.238 at 0-1, 1-2, and 2-3 h. Across episodes, MAGPIE-Net achieved a detection rate of 65.1% and a mean lead time of 64.6 min, compared with 23.6% and 18.3 min for the best gridded-output baseline, and remained superior for smaller neighborhoods and the 50 mm h-1 threshold. During the critical early-warning stage, when antecedent 1 h rainfall within 40 km remained below 1 mm, MAGPIE-Net detected 51.9% of episodes with a mean lead time of 38.5 min. These results show that event-oriented satellite-to-station modeling converts multitemporal geostationary cloud and moisture observations into local heavy-rainfall warnings more effectively than gridded-precipitation modeling.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。