Skillful Short‐Term Forecasting of Clouds With a Cascade Diffusion Model

Haoming Chen, Xiaohui Zhong, Qiang Zhai, Xiaomeng Li, Ying Wa Chan, Pak Wai Chan, Muqing Yang, Yuanyuan Huang, Hao Li, Xiaoming Shi

Journal of Geophysical Research Machine Learning and Computation · 01 February 2026 · Fudan University (FuXi)

Paper PDF

In one sentence. SATcast cascaded diffusion model forecasts satellite cloud fields up to 24 hours using FuXi-predicted fields as conditioning, outperforming conventional methods on fractions skill score.

Abstract

Abstract Accurate short‐term forecasting of clouds from satellite imagery is a foundational technology for downstream meteorological disaster mitigation and aviation safety enhancement systems, particularly in developing countries and remote areas lacking ground‐based observation infrastructure. Existing deep learning models often produce blurry results and exhibit reduced accuracy when forecasting atmospheric variables, while recent advances in video prediction show the potential to solve these problems. Here, we introduce SATcast, a diffusion‐based model that employs a cascaded architecture and multimodal inputs for forecasting cloud evolution from satellite imagery. SATcast incorporates physical fields predicted by FuXi, a deep‐learning weather forecasting model, alongside historical satellite observations as conditional inputs to generate high‐quality future cloud fields. Comprehensive evaluations demonstrate that SATcast consistently outperforms conventional methods across multiple metrics such as fractions skill score, achieving superior accuracy and robustness. Ablation studies underscore the importance of its multimodal design and cascade architecture in enhancing predictive performance. Notably, SATcast maintains skillful predictions for up to 24 hr, underscoring its potential for operational forecasting applications.

Labels

Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.