WeatherDiagFlow：基于证据的雷达临近预报与诊断流细化
WeatherDiagFlow: Evidence-Grounded Radar Nowcasting with Diagnostic Flow Refinement
另 1 家 · 查看机构详情
- Southeast University（东南大学）
- Beijing Fengyun Meteorological Science and Technology Development Co., Ltd.（北京风云气象科技发展有限公司）
- Beihang University（北京航空航天大学）
- Fudan University（复旦大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
WeatherDiagFlow提出基于证据的雷达临近预报框架，通过诊断流细化和多智能体生成公报与审计，在FJRADAR上提升强回波预报技能。
中文摘要 AI 辅助
雷达临近预报对于短期预警和应急响应至关重要，然而传统系统主要返回未来雷达场，对业务沟通和事后验证的支持有限。我们将雷达临近预报表述为一项基于证据的预报-公报-审计任务，其中数值预报器同时生成未来雷达场和结构化诊断证据。预报时公报仅使用模型可获得的证据，而事后审计仅在预报时效被观测到后才纳入未来雷达真值。基于此任务表述，WeatherDiagFlow预测运动、增长与衰减、强回波风险及不确定性，以调节滚动流细化，同时冻结支架残差校准改善长时效强回波保持。一个多智能体层将结构化证据转换为业务公报，并独立生成验证审计，而不将文本输出反馈给预报器。在FJRADAR上的实验展示了具有竞争力的整体性能和改善的强回波事件技能。因此，WeatherDiagFlow在泄漏受控协议下连接了数值预测、基于证据的报告和可审计的验证。
英文摘要
Radar nowcasting is essential for short-term warning and emergency response, yet conventional systems mainly return future radar fields and provide limited support for operational communication and post-event verification. We formulate radar nowcasting as an evidence-grounded forecast--bulletin--audit task, in which a numerical forecaster produces both future radar fields and structured diagnostic evidence. Forecast-time bulletins use only model-available evidence, whereas post-event audits incorporate future radar truth only after the forecast horizon is observed. Based on this task formulation, WeatherDiagFlow predicts motion, growth and decay, heavy-echo risk, and uncertainty to condition rolling flow refinement, while frozen-scaffold residual calibration improves long-lead strong-echo preservation. A multi-agent layer converts the structured evidence into operational bulletins and independently generates verification audits without feeding textual outputs back into the forecaster. Experiments on FJRADAR demonstrate competitive overall performance and improved strong-echo event skill. WeatherDiagFlow therefore connects numerical prediction, evidence-grounded reporting, and auditable verification under a leakage-controlled protocol.
