RainBench: Towards Global Precipitation Forecasting from Satellite Imagery
Abstract
Extreme precipitation events, such as violent rainfall and hail storms, routinely ravage economies and livelihoods around the developing world. Climate change further aggravates this issue. Data-driven deep learning approaches could widen the access to accurate multi-day forecasts, to mitigate against such events. However, there is currently no benchmark dataset dedicated to the study of global precipitation forecasts. In this paper, we introduce \textbf{RainBench}, a new multi-modal benchmark dataset for data-driven precipitation forecasting. It includes simulated satellite data, a selection of relevant meteorological data from the ERA5 reanalysis product, and IMERG precipitation data. We also release \textbf{PyRain}, a library to process large precipitation datasets efficiently. We present an extensive analysis of our novel dataset and establish baseline results for two benchmark medium-range precipitation forecasting tasks. Finally, we discuss existing data-driven weather forecasting methodologies and suggest future research avenues.
Cite
@article{arxiv.2012.09670,
title = {RainBench: Towards Global Precipitation Forecasting from Satellite Imagery},
author = {Christian Schroeder de Witt and Catherine Tong and Valentina Zantedeschi and Daniele De Martini and Freddie Kalaitzis and Matthew Chantry and Duncan Watson-Parris and Piotr Bilinski},
journal= {arXiv preprint arXiv:2012.09670},
year = {2020}
}
Comments
Work completed during the 2020 Frontier Development Lab research accelerator, a private-public partnership with NASA in the US, and ESA in Europe. Accepted as a spotlight/long oral talk at both Climate Change and AI, as well as AI for Earth Sciences Workshops at NeurIPS 2020