Oya: Deep Learning for Accurate Global Precipitation Estimation

TL;DR

Oya is a deep learning-based algorithm that uses full-spectrum GEO satellite data to improve real-time global precipitation estimation, especially in data-sparse regions, outperforming existing methods.

Contribution

Introduces Oya, a novel two-stage deep learning model leveraging VIS-IR GEO satellite data for accurate, real-time precipitation retrieval with improved robustness and global coverage.

Findings

Oya outperforms existing precipitation estimation methods.

The two-stage U-Net approach effectively handles data imbalance.

Global coverage achieved with multiple GEO satellites.

Abstract

Accurate precipitation estimation is critical for hydrological applications, especially in the Global South where ground-based observation networks are sparse and forecasting skill is limited. Existing satellite-based precipitation products often rely on the longwave infrared channel alone or are calibrated with data that can introduce significant errors, particularly at sub-daily timescales. This study introduces Oya, a novel real-time precipitation retrieval algorithm utilizing the full spectrum of visible and infrared (VIS-IR) observations from geostationary (GEO) satellites. Oya employs a two-stage deep learning approach, combining two U-Net models: one for precipitation detection and another for quantitative precipitation estimation (QPE), to address the inherent data imbalance between rain and no-rain events. The models are trained using high-resolution GPM Combined Radar-Radiometer Algorithm (CORRA) v07 data as ground truth and pre-trained on IMERG-Final retrievals to enhance robustness and mitigate overfitting due to the limited temporal sampling of CORRA. By leveraging multiple GEO satellites, Oya achieves quasi-global coverage and demonstrates superior performance compared to existing competitive regional and global precipitation baselines, offering a promising pathway to improved precipitation monitoring and forecasting.