# Thunderstorm nowcasting with deep learning: a multi-hazard data fusion model

arXiv: https://arxiv.org/abs/2211.01001 · HTML: https://mlsanity.com/paper/2211.01001/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 57 references that are in the map.
- First posted on arXiv 2 Nov 2022.

## Builds on (most cited first, 4 of 4)

- [Ensemble deep learning: A review](https://mlsanity.com/paper/2104.02395/) (2021)
- [Seamless lightning nowcasting with recurrent-convolutional deep learning](https://mlsanity.com/paper/2203.10114/) (2022)
- [Spatiotemporal Weather Data Predictions with Shortcut Recurrent-Convolutional Networks: A Solution for the Weather4cast challenge](https://mlsanity.com/paper/2111.02121/) (2021)
- [Improvements to short-term weather prediction with recurrent-convolutional networks](https://mlsanity.com/paper/2111.06240/) (2021)

## Built on by (most cited first, 7 of 7)

- [Latent diffusion models for generative precipitation nowcasting with accurate uncertainty quantification](https://mlsanity.com/paper/2304.12891/) (2023)
- [Interpretable Machine Learning for Weather and Climate Prediction: A Survey](https://mlsanity.com/paper/2403.18864/) (2024)
- [Transformer-based nowcasting of radar composites from satellite images for severe weather](https://mlsanity.com/paper/2310.19515/) (2023)
- [Inferring Thunderstorm Occurrence from Vertical Profiles of Convection-Permitting Simulations: Physical Insights from a Physical Deep Learning Model](https://mlsanity.com/paper/2409.20087/) (2024)
- [Increasing NWP Thunderstorm Predictability Using Ensemble Data and Machine Learning](https://mlsanity.com/paper/2502.13316/) (2025)
- [Integrating Weather Station Data and Radar for Precipitation Nowcasting: SmaAt-fUsion and SmaAt-Krige-GNet](https://mlsanity.com/paper/2502.16116/) (2025)
- [Temporal Context Conditioning for Seasonality-Aware Precipitation Nowcasting of High-Intensity Rainfall](https://mlsanity.com/paper/2606.09959/) (2026)

## Abstract (arXiv)

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.