用雷达数据+物理启发模型，秒级预测未来90分钟暴雨，适合城市防灾。
Physics-Based Deep Spatiotemporal Hyperlocal Radar Nowcasting with a Multi-Variable U-Net for High-Resolution Precipitation Forecasting
- 用多层雷达数据融合的U-Net网络，直接学风暴演化规律。
- 90分钟预报时关键成功指数达0.437（≥10dBZ），显著优于传统方法。
- 模型轻量可实时运行，适合暴雨频发的城市应急决策。
未来10至90分钟的降水临近预报对城市防洪与实时决策至关重要。传统高分辨率数值天气预报需频繁数据同化、模型初始化和积分，存在计算延迟。机器学习可通过高频观测直接学习风暴演变，实现快速预报。本文针对印度孟买地区，该地季风对流、海陆交互及局地强降雨使短时预报困难，提出一种仅依赖雷达的紧凑型临近预报框架。模型融合多仰角反射率、径向速度及速度梯度代理特征，采用编码器-解码器结构的U-Net，基于最新一次雷达体扫数据，预测未来12个复合反射率场（每7.5分钟一帧，共90分钟）。所提取的速度幅值、似发散、似方向切变与似涡度通道，表征了辐合与边界相互作用的运动学特征，无需完整风场反演。高反射率注意力模块提升对对流核心的敏感性，物理引导归因分析验证了学习到的响应是否具有气象意义。模型使用2023年5月至8月孟买多普勒雷达观测数据训练，并在时间上独立事件上评估。在90分钟预报时，≥10、≥20、≥30 dBZ阈值下的临界成功指数分别为0.437、0.332和0.193。相比持续性预报，本模型在长时预报中具有更低均方根误差和更高空间相关性。模型训练完成后可在普通计算机上秒级生成预报结果，适用于实时场景。
原文摘要 · Abstract (English)
Precipitation nowcasting over the immediate 10-90 min period is important for flood management and real-time decision-making in urban regions. Conventional short-range forecasting with high-resolution numerical weather prediction requires frequent data assimilation, model initialization, and spin-up, introducing computational latency. Machine learning provides an alternative by learning storm evolution directly from high-frequency observations and producing forecasts quickly after training. This is particularly relevant for Mumbai, India, where monsoon convection, land-sea interactions, and localized intense rainfall make short-term prediction difficult. Here, we develop a compact radar-only nowcasting framework that combines multi-elevation reflectivity, Doppler radial velocity, and radial-velocity-gradient proxy features within an encoder-decoder U-Net. Using the most recent radar volume scan, the model predicts 12 future composite reflectivity fields at 7.5-min intervals up to 90 min lead time. The derived velocity magnitude, divergence-like, directional-shear, and vorticity-like channels represent kinematic signatures associated with convergence and boundary interactions without requiring full wind-field retrieval. A high-reflectivity attention module improves sensitivity to convective cores, and physics-guided attribution examines whether the learned sensitivities are meteorologically meaningful. The model is trained using Mumbai Doppler radar observations from May to August 2023 and evaluated on temporally independent events. At 90 min lead time, Critical Success Index values are 0.437, 0.332, and 0.193 for $\geq$10, $\geq$20, and $\geq$30 dBZ thresholds, respectively. Compared with persistence, the model gives lower RMSE and higher spatial correlation at longer lead times. Once trained, it runs on a standard computer, generating nowcasts within seconds for real-time use.
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。