A Spatial-temporal Deep Probabilistic Diffusion Model for Reliable Hail Nowcasting with Radar Echo Extrapolation
On the map: Diffusion models → Flow matching, time series and science
Abstract (arXiv)
Hail nowcasting is a considerable contributor to meteorological disasters and there is a great need to mitigate its socioeconomic effects through precise forecast that has high resolution, long lead times and local details with large landscapes. Existing medium-range weather forecasting methods primarily rely on changes in upper air currents and cloud layers to predict precipitation events, such as heavy rainfall, which are unsuitable for hail nowcasting since it is mainly caused by low-altitude local strong convection associated with terrains. Additionally, radar captures the status of low cloud layers, such as water vapor, droplets, and ice crystals, providing rich signals suitable for hail nowcasting. To this end, we introduce a Spatial-Temporal gEnerAtive Model called SteamCast for hail nowcasting with radar echo extrapolation, it is a deep probabilistic diffusion model based on spatial-temporal representations including radar echoes as well as their position/time embeddings, which we trained on historical reanalysis archive from Yan'an Meteorological Bureau in China, where the crop yield like apple suffers greatly from hail damage. Considering the short-term nature of hail, SteamCast provides 30-minute nowcasts at 6-minute intervals for a single radar reflectivity variable, across 9 different vertical angles, on a latitude-longitude grid with approximately 1 km * 1 km resolution per pixel in Yan'an City, China. By successfully fusing the spatial-temporal features of radar echoes, SteamCast delivers competitive, and in some cases superior, results compared to other deep learning-based models such as PredRNN and VMRNN.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 7 of its 17 references that are in the map. First posted on arXiv 26 Mar 2025.
Builds on
7 of 17 references.
References · 7
- 2017Attention Is All You Needcited by 60,361
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
- 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,436
- 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 712
- 2021Skillful Precipitation Nowcasting using Deep Generative Models of Radarcited by 311
- 2021PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learningcited by 182
- 2024VMRNN: Integrating Vision Mamba and LSTM for Efficient and Accurate Spatiotemporal Forecastingcited by 35
Built on by
Citing papers per year: 2025: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025Nowcast3D: Reliable precipitation nowcasting via gray-box learning
- 2025RainDiff: End-to-end Precipitation Nowcasting Via Token-wise Attention Diffusion
- 2026Extreme Weather Nowcasting via Local Precipitation Pattern Prediction
- 2025SimCast: Enhancing Precipitation Nowcasting with Short-to-Long Term Knowledge Distillation
- 2026Just Weather Scoring: Efficient End-to-end Nowcasting with Distributional Diffusion
- 2024DuoCast: Duo-Probabilistic Diffusion for Precipitation Nowcasting
- 2025STLDM: Spatio-Temporal Latent Diffusion Model for Precipitation Nowcasting
- 2024Extreme Precipitation Nowcasting using Multi-Task Latent Diffusion Models