Huayu-Global: Skillful real-time quasi-global precipitation retrieval
Abstract
Satellite precipitation products face a persistent trade-off: real-time estimates are timely but less accurate, whereas the most reliable products are often released months after observation. This delay keeps high-quality precipitation information outside the decision window for flood warning and disaster response. Here we report Huayu-Global, a cross-constellation deep-learning system that combines three geostationary sensor streams from five satellites through a common retrieval framework and generates coherent quasi-global precipitation fields every thirty minutes. Across more than a million independent station records from two periods outside the training years, Huayu-Global improves event detection and precipitation-amount estimation relative to the real-time products evaluated and reaches delayed-product-level skill in key metrics. Huayu-Global therefore turns operational geostationary observations into a timely, high-skill precipitation layer for flood forecasting, water management and disaster response. Its cross-constellation design also provides a scalable foundation for incorporating future geostationary missions into hydrological and weather-prediction systems.
Related
- Skillful and realistic precipitation forecasting with reinforced diffusion
- GPROF-IR: An Improved Single-Channel Infrared Precipitation Retrieval for Merged Satellite Precipitation Products
- Characteristics of quasi-stationary Southwest Vortex and its mechanisms affecting precipitation
- Baroclinic Annular Mode Modulates Global Atmospheric Rivers and Extreme Precipitation
- Global Changes in Precipitation Concentration Through Consecutive Event Organization
BibTeX
@misc{song2026huayuglobal,
title = {{Huayu-Global: Skillful real-time quasi-global precipitation retrieval}},
author = {Zijiang Song and Shuang Yang and Yuying Li and Zilong Zhu and Xigang Sun and Ting Liu and Wenye Xiao and Lina Yuan and Min Liu},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.29213},
eprint = {2610.29213},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.29213},
}
RIS
TY - UNPB
TI - Huayu-Global: Skillful real-time quasi-global precipitation retrieval
AU - Zijiang Song
AU - Shuang Yang
AU - Yuying Li
AU - Zilong Zhu
AU - Xigang Sun
AU - Ting Liu
AU - Wenye Xiao
AU - Lina Yuan
AU - Min Liu
PY - 2026
DA - 2026/10/21
PB - arXiv
DO - 10.48550/arxiv.2610.29213
UR - https://arxiv.org/abs/2610.29213
AB - Satellite precipitation products face a persistent trade-off: real-time estimates are timely but less accurate, whereas the most reliable products are often released months after observation. This delay keeps high-quality precipitation information outside the decision window for flood warning and disaster response. Here we report Huayu-Global, a cross-constellation deep-learning system that combines three geostationary sensor streams from five satellites through a common retrieval framework and generates coherent quasi-global precipitation fields every thirty minutes. Across more than a million independent station records from two periods outside the training years, Huayu-Global improves event detection and precipitation-amount estimation relative to the real-time products evaluated and reaches delayed-product-level skill in key metrics. Huayu-Global therefore turns operational geostationary observations into a timely, high-skill precipitation layer for flood forecasting, water management and disaster response. Its cross-constellation design also provides a scalable foundation for incorporating future geostationary missions into hydrological and weather-prediction systems.
ER -