Physics-Based Deep Spatiotemporal Hyperlocal Radar Nowcasting with a Multi-Variable U-Net for High-Resolution Precipitation Forecasting
Machine Learning
Summary
The authors created a fast and compact model that predicts rainfall over the next 10 to 90 minutes using only radar data from Mumbai, a city with tricky weather patterns. Their model uses radar features related to how air moves and changes to better spot rainy areas, especially heavy rain spots. It learns from past radar data and makes quick predictions without needing complex weather simulations. When tested, the model performed better than simply assuming the weather stays the same and can run in seconds on a normal computer. This could help with flood warnings and quick decisions during heavy rains.
Authors
Akshay Sunil, Muhammed Rashid, Raja Sekhar Sivaraju, Sushma Nair, Subimal Ghosh
Abstract
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.