Saved in:
Bibliographic Details
Main Authors: Chen, Haoming, Zhong, Xiaohui, Zhai, Qiang, Li, Xiaomeng, Chan, Ying Wa, Chan, Pak Wai, Huang, Yuanyuan, Li, Hao, Shi, Xiaoming
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.10957
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929717792210944
author Chen, Haoming
Zhong, Xiaohui
Zhai, Qiang
Li, Xiaomeng
Chan, Ying Wa
Chan, Pak Wai
Huang, Yuanyuan
Li, Hao
Shi, Xiaoming
author_facet Chen, Haoming
Zhong, Xiaohui
Zhai, Qiang
Li, Xiaomeng
Chan, Ying Wa
Chan, Pak Wai
Huang, Yuanyuan
Li, Hao
Shi, Xiaoming
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_10957
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Skillful Nowcasting of Convective Clouds With a Cascade Diffusion Model
Chen, Haoming
Zhong, Xiaohui
Zhai, Qiang
Li, Xiaomeng
Chan, Ying Wa
Chan, Pak Wai
Huang, Yuanyuan
Li, Hao
Shi, Xiaoming
Computer Vision and Pattern Recognition
Atmospheric and Oceanic Physics
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.
title Skillful Nowcasting of Convective Clouds With a Cascade Diffusion Model
topic Computer Vision and Pattern Recognition
Atmospheric and Oceanic Physics
url https://arxiv.org/abs/2502.10957