2026-05-01T13:44:16Zhttp://doidb.wdc-terra.org/oaip/oai

oai:doidb.wdc-terra.org:86802026-04-16T14:06:37ZDOIDBDOIDB.GFZ

false4DOIDB.GFZ 10.5880/GFZ.OJSJ.2026.001 Collin, Daniel Daniel Collin 0000-0001-5426-3242 GFZ Helmholtz Centre for Geosciences, Potsdam, Germany Technical University of Berlin, Berlin, Germany Shprits, Yuri Yuri Shprits 0000-0002-9625-0834 GFZ Helmholtz Centre for Geosciences, Potsdam, Germany University of Potsdam, Potsdam, Germany University of California Los Angeles, Los Angeles, USA Chiarabini, Luca Luca Chiarabini 0009-0005-7347-0200 German Aerospace Center, Munich, Germany Hofmeister, Stefan Stefan Hofmeister 0000-0001-7662-1960 Columbia University, New York, USA Klein, Nadja Nadja Klein 0000-0002-5072-5347 Karlsruhe Institute of Technology, Karlsruhe, Germany Gallego, Guillermo Guillermo Gallego 0000-0002-2672-9241 Technical University of Berlin, Berlin, Germany Einstein Center Digital Future, Berlin, Germany GFZ Data Services 2026 solar cycle magnetograms solar extreme ultraviolet Platforms > Space-based Platforms > Solar/Space Observation Satellites > Living with a Star > SDO Science Keywords > EARTH SCIENCE > SUN-EARTH INTERACTIONS > SOLAR ACTIVITY > CORONA HOLES Science Keywords > EARTH SCIENCE > SUN-EARTH INTERACTIONS > SOLAR ACTIVITY > SOLAR IMAGERY Science Keywords > EARTH SCIENCE > SUN-EARTH INTERACTIONS > SOLAR ENERGETIC PARTICLE PROPERTIES > PARTICLE SPEED Science Keywords > EARTH SCIENCE SERVICES > DATA ANALYSIS AND VISUALIZATION > IMAGE PROCESSING Science Keywords > EARTH SCIENCE SERVICES > DATA ANALYSIS AND VISUALIZATION > STATISTICAL APPLICATIONS Science Keywords > EARTH SCIENCE SERVICES > MACHINE LEARNING TRAINING DATA Science Keywords > EARTH SCIENCE SERVICES > MODELS > MACHINE LEARNING MODELS > DEEP LEARNING Science Keywords > EARTH SCIENCE SERVICES > MODELS > MACHINE LEARNING MODELS > NEURAL NETWORKS Science Keywords > EARTH SCIENCE SERVICES > MODELS > MACHINE LEARNING MODELS > REGRESSION Science Keywords > EARTH SCIENCE SERVICES > MODELS > MACHINE LEARNING MODELS > SUPERVISED Science Keywords > EARTH SCIENCE SERVICES > MODELS > SOLAR-ATMOSPHERE/SPACE-WEATHER MODELS Solar/Space Observing Instruments > Photon/Optical Detectors > AIA-SDO Collin, Daniel Daniel Collin 0000-0001-5426-3242 GFZ Helmholtz Centre for Geosciences, Potsdam, Germany Technical University of Berlin, Berlin, Germany Collin, Daniel GFZ Helmholtz Centre for Geosciences, Potsdam, Germany 2025-08-01 Dataset (not available before paper is published) 10.1029/2020SW002673 10.1029/2021SW002976 10.24414/qnza-ac80 10.1029/2024SW004125 10.3847/1538-4365/ab1005 10.1002/2017JA024586 10.1007/s11207-024-02321-y 10.3847/1538-4365/adbaed 10.1051/0004-6361/202140640 10.1007/s11207-011-9776-8 10.48322/1shr-ht18 10.1029/2004JA010598 10.7910/DVN/C2MHTH 10.1007/s11207-011-9834-2 Creative Commons Attribution 4.0 International This dataset provides solar images and physical features from June 2010 to June 2024, which can be used for solar wind speed (SWS) forecasting. The data is a supplement to the publication "PROSWIN: Probabilistic Solar Wind Speed Forecasting Using Deep Distributional Regression With Solar Images" (Journal TBD) by Collin et al. (2026) and facilitates reproducing all results therein. We provide:

(1) three preprocessed solar image channels and preprocessed magnetograms from the SDO satellite (AIA: 171 Å, 193 Å, 211 Å; HMI: magnetograms; note that the images are not yet normalized and not scaled to the interval [-1,1]),

(2) 63 physical features describing the solar wind conditions from the previous solar rotation, the state of the solar cycle, and the position angle of Earth relative to the solar equator,

(3) the trained neural network models based on combinations of solar image channels, magnetograms, and physical features from the journal publication,

(4) a list of high-speed solar wind streams (HSSs) and coronal mass ejections (CMEs), which can be used for investigating the effectiveness of a prediction model with regard to HSSs and CMEs,

(5) the predicted time series of all the models we trained and of the models from the literature that we compare to in the journal publication, and

(6) the solar wind speed and sunspot number time series we use in the journal publication.

Image downloading and preprocessing was done using the following Python code: https://github.com/DanielCollin96/solar_image_processing. For all details on the data preparation and usage, we refer to the original journal article by Collin et al. (2026).
Covers the solar disk from June 2010 to June 2024 0 0 Helmholtz International Berlin Research School in Data Science (HEIBRiDS)