ESIP
Browse
ESIP21 RainBench.pdf (1.34 MB)

RainBench: Towards Global Precipitation Forecasting from Satellite Imagery

Download (1.34 MB)
poster
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.

History

Usage metrics

    ESIP Summer 2021

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC