Huayu: Advanced Real-Time Precipitation Estimation from Geostationary Satellite

TL;DR

Huayu is a real-time machine learning system that estimates precipitation using infrared satellite data, providing more accurate and higher-resolution rainfall information crucial for disaster monitoring and climate analysis.

Contribution

The paper introduces Huayu, a novel infrared-based machine learning system for real-time precipitation estimation, outperforming existing satellite datasets in accuracy and resolution.

Findings

Huayu achieves a CSI of 0.693, outperforming IMERG Final Run by 3.43%.

Infrared satellite data can be effectively used for accurate real-time precipitation estimation.

Huayu provides precipitation estimates at 15-minute, 0.05-degree resolution.

Abstract

As climate change drives increased frequency and intensity of extreme precipitation and flooding worldwide, posing escalating threats to public safety and economic assets, accurate and real-time satellite-based precipitation estimation is essential for operational large-scale hydrometeorological analysis and disaster monitoring. NASA's Integrated Multi-satellitE Retrievals for GPM (IMERG Final Run) combines information from "all" satellite microwave observations with gauge correction and climatological adjustment to produce precipitation estimates at 0.1{\deg} spatial and 30-min temporal resolution. However, its latency of approximately 3.5 months restricts its utility for real-time applications, despite outperforming mainstream satellite precipitation datasets in representing rainfall patterns and variability. We present Huayu, a novel machine learning-based real-time satellite precipitation retrieval system that relies solely on infrared observations from the FengYun-4B geostationary satellite to provide a more accurate precipitation estimate at a finer spatiotemporal resolution (15 min, 0.05{\deg}) over a 120{\deg} by 120{\deg} domain. Performance evaluations demonstrate that Huayu achieves strong consistency with rain gauge observations, yielding a critical success index (CSI) of 0.693 - representing a 3.43% improvement over IMERG Final Run (CSI: 0.670). Experimental results confirm that infrared satellite observations can deliver more accurate precipitation estimates than conventional multi-source algorithms.