Skillful Nowcasting of Convective Clouds With a Cascade Diffusion Model
This work addresses the need for accurate nowcasting to mitigate meteorological disasters, especially in developing countries and remote regions, representing a strong specific gain in domain-specific applications.
The paper tackled the problem of nowcasting convective clouds from satellite imagery by introducing SATcast, a cascade diffusion model that incorporates physical fields and past observations, resulting in superior accuracy and robustness with predictive skill maintained for up to 24 hours.
Accurate nowcasting of convective clouds from satellite imagery is essential for mitigating the impacts of meteorological disasters, especially in developing countries and remote regions with limited ground-based observations. Recent advances in deep learning have shown promise in video prediction; however, existing models frequently produce blurry results and exhibit reduced accuracy when forecasting physical fields. Here, we introduce SATcast, a diffusion model that leverages a cascade architecture and multimodal inputs for nowcasting cloud fields in satellite imagery. SATcast incorporates physical fields predicted by FuXi, a deep-learning weather model, alongside past satellite observations as conditional inputs to generate high-quality future cloud fields. Through comprehensive evaluation, SATcast outperforms conventional methods on multiple metrics, demonstrating its superior accuracy and robustness. Ablation studies underscore the importance of its multimodal design and the cascade architecture in achieving reliable predictions. Notably, SATcast maintains predictive skill for up to 24 hours, underscoring its potential for operational nowcasting applications.