ESIP21 RainBench.pdf (1.34 MB)
Download file

RainBench: Towards Global Precipitation Forecasting from Satellite Imagery

Download (1.34 MB)
posted on 2021-07-14, 16:08 authored by Christian Schroeder de Witt, Catherine E. Tong, Valentina Zantedeschi, Daniele De Martini, Piotr Bilinski, Matthew Chantry, Freddie Kalaitzis, Duncan Watson-Parris
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. This poster was presented at the 2021 Earth Science Information Partners (ESIP) Summer Meeting held virtually in July 2021.