Oya: Deep Learning for Accurate Global Precipitation Estimation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911289289211904 |
|---|---|
| author | Brempong, Emmanuel Asiedu Hassen, Mohammed Alewi MohamedKhair, MohamedElfatih Dube, Vusumuzi Potes, Santiago Hincapie Graham, Olivia Brik, Amanie McGovern, Amy Huffman, George J. Hickey, Jason |
| author_facet | Brempong, Emmanuel Asiedu Hassen, Mohammed Alewi MohamedKhair, MohamedElfatih Dube, Vusumuzi Potes, Santiago Hincapie Graham, Olivia Brik, Amanie McGovern, Amy Huffman, George J. Hickey, Jason |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_10562 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Oya: Deep Learning for Accurate Global Precipitation Estimation Brempong, Emmanuel Asiedu Hassen, Mohammed Alewi MohamedKhair, MohamedElfatih Dube, Vusumuzi Potes, Santiago Hincapie Graham, Olivia Brik, Amanie McGovern, Amy Huffman, George J. Hickey, Jason Machine Learning Atmospheric and Oceanic Physics 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. |
| title | Oya: Deep Learning for Accurate Global Precipitation Estimation |
| topic | Machine Learning Atmospheric and Oceanic Physics |
| url | https://arxiv.org/abs/2511.10562 |