RainBench: Towards Global Precipitation ...
Document type :
Autre communication scientifique (congrès sans actes - poster - séminaire...): Communication dans un congrès avec actes
Title :
RainBench: Towards Global Precipitation Forecasting from Satellite Imagery
Author(s) :
de Witt, Christian Schroeder [Auteur]
Tong, Catherine [Auteur]
Zantedeschi, Valentina [Auteur]
The Inria London Programme [Inria-London]
MOdel for Data Analysis and Learning [MODAL]
Department of Computer science [University College of London] [UCL-CS]
de Martini, Daniele [Auteur]
Kalaitzis, Freddie [Auteur]
Chantry, Matthew [Auteur]
Watson-Parris, Duncan [Auteur]
Bilinski, Piotr [Auteur]
Tong, Catherine [Auteur]
Zantedeschi, Valentina [Auteur]
The Inria London Programme [Inria-London]
MOdel for Data Analysis and Learning [MODAL]
Department of Computer science [University College of London] [UCL-CS]
de Martini, Daniele [Auteur]
Kalaitzis, Freddie [Auteur]
Chantry, Matthew [Auteur]
Watson-Parris, Duncan [Auteur]
Bilinski, Piotr [Auteur]
Conference title :
Association for the Advancement of Artificial Intelligence
City :
Virtual
Country :
Royaume-Uni
Start date of the conference :
2021-02-01
HAL domain(s) :
Informatique [cs]/Apprentissage [cs.LG]
Planète et Univers [physics]/Océan, Atmosphère
Planète et Univers [physics]/Océan, Atmosphère
English abstract : [en]
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 ...
Show more >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.Show less >
Show more >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.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Comment :
Work completed during the 2020 Frontier Development Lab research accelerator, a private-public partnership with NASA in the US, and ESA in Europe
Collections :
Source :
Files
- 2012.09670
- Open access
- Access the document
- document
- Open access
- Access the document
- 2012.09670v1.pdf
- Open access
- Access the document