Machine Learning Methods for Postprocessing Ensemble Forecasts of Wind Gusts: Data

DOI

Datensatz zu Schulz und Lerch (2022): "Machine learning methods for postprocessing ensemble forecasts of wind gusts: A systematic comparison", Monthly Weather Review, 150 (1), 235-257, https://doi.org/10.1175/MWR-D-21-0150.1. Die Daten beinhalten die NWV-Vorhersagen und dazugehörigen Beobachtungen im gesamten Zeitraum von 2010 bis 2016 sowie die nachbearbeiteten Vorhersagen im Testzeitraum 2016. Weiter sind noch die Stationsdaten sowie die berechneten Scores im Testzeitraum enthalten. Die NWV-Vorhersagen beinhalten die einzelnen Ensemble-Member der Windböen-Vorhersage sowie die Mittelwerte und Standardabweichungen der anderen Ensemble-Variablen. Zusätzlich zu den nachbearbeiteten Vorhersagen sind auch Informationen zu den trainierten Modellen verfügbar (bspw. geschätzte Parameter).

Data set for Schulz and Lerch (2022): "Machine learning methods for postprocessing ensemble forecasts of wind gusts: A systematic comparison", Monthly Weather Review, 150 (1), 235-257, https://doi.org/10.1175/MWR-D-21-0150.1. The data includes the NWP forecasts and corresponding observations for the entire period from 2010 to 2016 as well as the postprocessed forecasts for the test period 2016. The station data and the calculated scores for the test period are also included. The NWP forecasts contain the individual ensemble members of the wind gust forecast as well as the ensemble mean and standard deviation values of the other ensemble variables. In addition to the postprocessed forecasts, information on the trained models is also available (e.g., estimated parameters).

A detailed description of the data is given on the corresponding Github-page (https://github.com/benediktschulz/paper_pp_wind_gusts).

Identifier
DOI https://doi.org/10.35097/afEBrMYqNrxxvrLX
Metadata Access https://www.radar-service.eu/oai/OAIHandler?verb=GetRecord&metadataPrefix=datacite&identifier=10.35097/afEBrMYqNrxxvrLX
Provenance
Creator Schulz, Benedikt ORCID logo; Lerch, Sebastian ORCID logo
Publisher Karlsruhe Institute of Technology
Contributor RADAR
Publication Year 2024
Rights Open Access; Creative Commons Attribution 4.0 International; info:eu-repo/semantics/openAccess; https://creativecommons.org/licenses/by/4.0/legalcode
OpenAccess true
Representation
Resource Type Dataset
Format application/x-tar
Discipline Mathematics; Natural Sciences