As climate change intensifies the frequency and severity of extreme precipitation and flooding events across the globe, the associated risks to public safety and economic assets continue to grow. In this context, accurate, real-time satellite-based precipitation estimation has become essential for operational large-scale hydrometeorological analysis and effective 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° spatial and 30-min temporal resolution. However, despite its superior performance over mainstream satellite precipitation datasets in capturing rainfall patterns and variability, its latency of approximately 3.5 months significantly limits its applicability for real-time operational use. We proposed Huayu, a novel deep learning-based real-time satellite precipitation retrieval system that relies solely on infrared observations from the FengYun-4B geostationary satellite to provide an accurate precipitation estimate at a finer spatiotemporal resolution (15 min, 0.05°) over a 120° × 120° domain. Experimental validations demonstrate that Huayu achieves strong consistency with rain gauge observations, yielding a Critical Success Index (CSI) of 0.693 - 3.3% improvement over IMERG Final Run (CSI: 0.671). • Infrared data could produce an accurate precipitation estimate. • Huayu is proven to be a real-time, accurate precipitation model. • A data-driven method could improve the timely hydrometeorological monitoring.
Song et al. (Thu,) studied this question.