Data Samples for temperature forecasting by deep learning methods

DOI

Here we provide the data samples (one-year data) to allow the users to fast test the machine learning workflow code that is published on Zenodo (https://zenodo.org/record/6907316#.Yw9p9exBwUE), for the publication "Temperature forecasts by deep learning" by Bing Gong, Michael Langguth et al., submitted in GMD (doi: https://doi.org/10.5194/gmd-2021-430). You can untar the file by executing 'tar -xzvf '. This data were downloaded and extracted from ECMWF ERA5 dataset.

The file 'climatology_t2m_1991-2020.nc' contains the 2-meter temperature climatological mean which is inferred at each grid point from the ERA5 reanalysis data between 1990 and 2019. The climatology is calculated separately for each month of the year and each hour of the day. This results in 24 hours per month, which are stored on the first day of each month.

Identifier
DOI https://doi.org/10.23728/b2share.744bbb4e6ee84a09ad368e8d16713118
Source https://b2share.eudat.eu/records/744bbb4e6ee84a09ad368e8d16713118
Metadata Access https://b2share.eudat.eu/api/oai2d?verb=GetRecord&metadataPrefix=eudatcore&identifier=oai:b2share.eudat.eu:b2rec/744bbb4e6ee84a09ad368e8d16713118
Provenance
Creator Bing Gong; Michael Langguth
Publisher EUDAT B2SHARE
Publication Year 2022
Rights Creative Commons Attribution (CC-BY); info:eu-repo/semantics/openAccess
OpenAccess true
Contact b.gong(at)fz-juelich.de
Representation
Format gz; nc
Size 6.3 GB; 2 files
Discipline 3.3.14 → Earth sciences → Meteorology; 4.1.17.1.2.1 → Machine learning → Artificial neural network