A Benchmark Dataset for Satellite-Based Estimation and Detection of Rain
Accurately tracking the global distribution of precipitation is essential for both research and operational meteorology. Satellite observations remain the only means of achieving consistent, global precipitation monitoring. While machine learning has long been applied to satellite-based precipitation retrieval, the absence of a standardized benchmark dataset has hindered fair comparisons between methods. To address this, the International Precipitation Working Group has developed SatRain, the first AI benchmark dataset for satellite-based detection and estimation of rain. SatRain integrates multi-sensor satellite observations from the primary platforms used in precipitation remote sensing with high-quality reference precipitation estimates derived from gauge-corrected ground-based radar composites over the conterminous United States. It offers a standardized evaluation protocol and out-of-distribution testing data from Asia and Europe to enable robust and reproducible comparisons across machine learning approaches. In addition to algorithm evaluation, the diversity of sensors and inclusion of time-resolved geostationary observations make SatRain a valuable foundation for developing next-generation AI models to deliver more accurate global precipitation estimates.
Authors
- Malarvizhi Arulraj (ORCID: https://orcid.org/0000-0003-2995-4804)
- Alan J. P. Calheiros (ORCID: https://orcid.org/0000-0002-6408-3410)
- Linda Bogerd (ORCID: https://orcid.org/0000-0002-7343-4542)
- Rayana Santos Araújo Palharini (ORCID: https://orcid.org/0000-0001-5503-8450)
- Daniele Casella (ORCID: https://orcid.org/0000-0001-7203-4232)
- Jie Gong (ORCID: https://orcid.org/0000-0002-7936-0433)
- Giulia Panegrossi (ORCID: https://orcid.org/0000-0002-5170-7087)
- Clément Guilloteau (ORCID: https://orcid.org/0000-0001-8142-7740)
- G. Lee
- Lisa Milani (ORCID: https://orcid.org/0000-0003-0498-1021)
- Maximilian Maahn (ORCID: https://orcid.org/0000-0002-2580-9100)
- Neda Dolatabadi (ORCID: https://orcid.org/0000-0001-6391-6997)
- Christian D. Kummerow (ORCID: https://orcid.org/0000-0001-5734-5518)
- Simon Pfreundschuh (ORCID: https://orcid.org/0000-0001-6566-2732)
- Paolo Sanò (ORCID: https://orcid.org/0000-0001-7059-1043)
- Veljko Petković
- Pierre Kirstetter
- Soorok Ryu
- Jackson Tan
Institutions
- Goddard Space Flight Center (US)
- University of Arizona (US)
- Cooperative Institute for Mesoscale Meteorological Studies (US)
- University of California, Irvine (US)
- Kyungpook National University (KR)
- Institute of Atmospheric Sciences and Climate (IT)
- Irvine University (US)
- Metropolitan University of Technology (CL)
- Earth System Science Interdisciplinary Center (US)
- Cooperative Institute for Climate and Satellites (US)
- University of Maryland, College Park (US)
- University of Maryland, Baltimore County (US)
- Instituto Nacional de Pesquisas Espaciais (BR)
- University of Oklahoma (US)
- Colorado State University (US)
- Leipzig University (DE)
Publication Details
- Journal
- Scientific Data
- Published
- 2026-01-15
- DOI
- https://doi.org/10.1038/s41597-026-06565-0
- Primary Topic
- Precipitation Measurement and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Aeronautics and Space Administration
- European Commission
- Nuclear Safety and Security Commission