用扩散模型提升公里级降水预报的精度与不确定性表达
Diffusion-Based Refinement for Kilometer-Scale Probabilistic Precipitation Nowcasting
- 基于扩散模型将4公里确定性预报转为1公里概率集合，修正系统误差
- 30成员集合可找回原模型漏报的38%-47%强雨区，误报率低于1%
- 单卡3.4秒生成一小时预报，适合高时效防灾应用
局部极端降水是引发城市内涝和滑坡的主要原因，但实现兼具精细空间分辨率与概率不确定性表达的短临预报仍具挑战。本文提出exPreCast-ENS，一种条件残差扩散框架，将原有的4公里雷达短临预报exPreCast升级为1公里概率集合预报，并修正系统性偏差。通过同时依赖预报结果和前期雷达观测进行条件控制，集合均值用于修正基线而非扰动，成员则捕捉未解析的细尺度变异性。在韩国半岛测试中，集合规模越大性能越优。2023年两次重大事件中，30成员集合成功恢复了原模型漏报的38%-47%强降雨像素，同时保留约95%的正确检测，仅错误预警不足1%的应清区域。该方法在单块GPU上3.4秒完成一小时预报，且在法国MeteoNet雷达数据集上也表现稳定提升。
原文摘要 · Abstract (English)
Localized extreme precipitation is a major trigger of urban flash floods and landslides, yet producing nowcasts that combine fine spatial detail with probabilistic uncertainty remains challenging. Here we introduce exPreCast-ENS, a conditional residual diffusion framework that transforms the deterministic 4 km radar nowcaster exPreCast into a 1 km probabilistic ensemble while correcting systematic forecast errors. Conditioning on both the forecast and preceding radar observations lets the ensemble-mean correct the baseline rather than perturb it, while members represent unresolved fine-scale variability. Over the Korean Peninsula, skill improves with ensemble size. In two high-impact events in 2023, a 30-member ensemble recovers 38-47% of heavy-rain pixels missed by exPreCast while retaining approximately 95% of its correct detections and alarming on under 1% of the pixels it correctly left clear. The method generates a 1-h forecast in 3.4 s on a single GPU and yields consistent improvements on the French regional MeteoNet radar dataset.
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。