Composable multi-satellite precipitation estimation for evolving observing systems
Abstract
Rapid and spatially continuous precipitation monitoring is critical for flood, landslide, and other hydrometeorological hazard warnings, particularly in regions where rain-gauge and weather-radar networks are sparse. The coordinated use of heterogeneous satellite observations, including geostationary infrared, passive microwave, and spaceborne radar measurements, is therefore a key pathway toward more accurate and spatially refined precipitation monitoring. Recent deep-learning methods have substantially improved multi-source satellite precipitation estimation, but most remain tied to predefined combinations of satellite inputs. As satellite observing systems evolve, incorporating new instruments often requires substantial model retraining and maintenance. We propose PRISMA, a generative framework for precipitation retrieval from multi-source observations. The framework separates the training of the precipitation prior from sensor-specific observational constraints, enabling sensor branches to be flexibly composed or extended without retraining the precipitation generative backbone. We successively integrate FY-4B/AGRI, GPM/GMI, F16-F18 SSMIS, and GPM/DPR-Ka observations within the PRISMA framework, achieving consistent improvements in precipitation-estimation accuracy. Matched-footprint experiments further confirm the effective use of complementary information from coincident sensors. Independent station validation shows that PRISMA outperforms IMERG Final in both CRPS and RMSE while providing positive fair Brier skill across all precipitation thresholds. PRISMA enables flexible composition of heterogeneous satellite observations and rapid generation of accurate ensemble precipitation estimates, strengthening satellite-based precipitation monitoring.
Related
- GPROF-IR: An Improved Single-Channel Infrared Precipitation Retrieval for Merged Satellite Precipitation Products
- A Sensor-Adaptive Incremental Learning Framework for Artifact Detection in Satellite Precipitation Data
- Low-rank tensor structure of precipitation and its application to satellite-reference merging
- Improving global precipitation forecasts with an AI weather model trained on satellite observations
- Added value of integrated satellite precipitation products for event-based flood modeling in semi-arid regions
BibTeX
@misc{yang2026composable,
title = {{Composable multi-satellite precipitation estimation for evolving observing systems}},
author = {Yunfan Yang and Haofei Sun and Xiuyu Sun and Wei Han and Xiaoze Xu and Xingtao Song and Jun Li and Zhiqiu Gao and Wei Huang},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2605.14426},
eprint = {2605.14426},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.14426},
}
RIS
TY - UNPB
TI - Composable multi-satellite precipitation estimation for evolving observing systems
AU - Yunfan Yang
AU - Haofei Sun
AU - Xiuyu Sun
AU - Wei Han
AU - Xiaoze Xu
AU - Xingtao Song
AU - Jun Li
AU - Zhiqiu Gao
AU - Wei Huang
PY - 2026
DA - 2026/09/15
PB - arXiv
DO - 10.48550/arxiv.2605.14426
UR - https://arxiv.org/abs/2605.14426
AB - Rapid and spatially continuous precipitation monitoring is critical for flood, landslide, and other hydrometeorological hazard warnings, particularly in regions where rain-gauge and weather-radar networks are sparse. The coordinated use of heterogeneous satellite observations, including geostationary infrared, passive microwave, and spaceborne radar measurements, is therefore a key pathway toward more accurate and spatially refined precipitation monitoring. Recent deep-learning methods have substantially improved multi-source satellite precipitation estimation, but most remain tied to predefined combinations of satellite inputs. As satellite observing systems evolve, incorporating new instruments often requires substantial model retraining and maintenance. We propose PRISMA, a generative framework for precipitation retrieval from multi-source observations. The framework separates the training of the precipitation prior from sensor-specific observational constraints, enabling sensor branches to be flexibly composed or extended without retraining the precipitation generative backbone. We successively integrate FY-4B/AGRI, GPM/GMI, F16-F18 SSMIS, and GPM/DPR-Ka observations within the PRISMA framework, achieving consistent improvements in precipitation-estimation accuracy. Matched-footprint experiments further confirm the effective use of complementary information from coincident sensors. Independent station validation shows that PRISMA outperforms IMERG Final in both CRPS and RMSE while providing positive fair Brier skill across all precipitation thresholds. PRISMA enables flexible composition of heterogeneous satellite observations and rapid generation of accurate ensemble precipitation estimates, strengthening satellite-based precipitation monitoring.
ER -