User: Guest  Login
Title:

WeatherBench: A benchmark dataset for data-driven weather forecasting

Document type:
Forschungsdaten
Publication date:
12.06.2020
Responsible:
Rasp, Stephan
Authors:
Rasp, Stephan; Dueben, Peter D.; Scher, Sebastian; Weyn, Jonathan A.; Mouatadid, Soukayna; Thuerey, Nils
Author affiliation:
TUM
Publisher:
TUM
End date of data production:
31.12.2019
Subject area:
GEO Geowissenschaften; NAT Naturwissenschaften (allgemein); UMW Umweltwissenschaften
Resource type:
Simulationen / simulations
Data type:
mehrdimensionale Visualisierungen oder Modelle / models; Tabellen / tables
Description:
For more information, visit https://github.com/pangeo-data/WeatherBench. This dataset contains modified ERA5 reanalysis data targeted for training data-driven weather forecasting models. Contains modified Copernicus Climate Change Service Information [2019]. Neither the European Commission nor ECMWF is responsible for any use that may be made of the Copernicus Information or Data it contains. Original data source: Copernicus Climate Change Service (C3S) (2017): ERA5: Fifth generation of ECMWF...     »
Links:

Source code on GitHub and preprint of paper on arxiv.org

Key words:
Reanalysis; ERA5; machine learning
Technical remarks:
View and download (5.8 TB total, 315 files)
The data server also offers downloads with FTP
The data server also offers downloads with rsync (password m1524895):
rsync rsync://m1524895@dataserv.ub.tum.de/m1524895/
Language:
en
Rights:
by, http://creativecommons.org/licenses/by/4.0
 BibTeX