RainPro-8: An Efficient Deep Learning Model to Estimate Rainfall Probabilities Over 8 Hours
This work addresses the need for accurate, long-lead-time precipitation forecasts in Europe, representing a domain-specific advancement in weather prediction.
The authors tackled the problem of high-resolution probabilistic precipitation forecasting over an 8-hour horizon in Europe by developing a deep learning model that integrates radar, satellite, and physics-based NWP data, resulting in forecasts that surpass current operational systems and deep-learning models.
We present a deep learning model for high-resolution probabilistic precipitation forecasting over an 8-hour horizon in Europe, overcoming the limitations of radar-only deep learning models with short forecast lead times. Our model efficiently integrates multiple data sources - including radar, satellite, and physics-based numerical weather prediction (NWP) - while capturing long-range interactions, resulting in accurate forecasts with robust uncertainty quantification through consistent probabilistic maps. Featuring a compact architecture, it enables more efficient training and faster inference than existing models. Extensive experiments demonstrate that our model surpasses current operational NWP systems, extrapolation-based methods, and deep-learning nowcasting models, setting a new standard for high-resolution precipitation forecasting in Europe, ensuring a balance between accuracy, interpretability, and computational efficiency.