Thunderstorm nowcasting with deep learning: a multi-hazard data fusion model
This addresses the need for accurate, multi-hazard predictions for sectors like first responders and aviation, though it is incremental as it adapts existing deep learning methods to this domain.
The paper tackles thunderstorm hazard prediction by developing a deep learning model that fuses multiple data sources to probabilistically forecast lightning, hail, and heavy precipitation at 1 km resolution with 5-minute updates and up to 60-minute lead times.
Predictions of thunderstorm-related hazards are needed in several sectors, including first responders, infrastructure management and aviation. To address this need, we present a deep learning model that can be adapted to different hazard types. The model can utilize multiple data sources; we use data from weather radar, lightning detection, satellite visible/infrared imagery, numerical weather prediction and digital elevation models. We demonstrate the ability of the model to predict lightning, hail and heavy precipitation probabilistically on a 1 km resolution grid, with a temporal resolution of 5 min and lead times up to 60 min. Shapley values quantify the importance of the different data sources, showing that the weather radar products are the most important predictors for all three hazard types.