Paul J. Wright

Postdoc, Stanford University

paul [AT] pauljwright.co.uk

Machine Learning Data Set for NASA's Solar Dynamics Observatory

SDO/AIA, SDO/HMI, and SDO/EVE

Galvez et al ApJS, in press

We present a curated dataset from the NASA Solar Dynamics Observatory (SDO) mission in a format suitable for machine learning research. Beginning from level 1 scientific products we have processed various instrumental corrections, downsampled to manageable spatial and temporal resolutions, and synchronized observations spatially and temporally. We anticipate this curated dataset will facilitate machine learning research in heliophysics and the physical sciences generally, increasing the scientific return of the SDO mission. This work is a deliverable of the 2018 NASA Frontier Development Lab program.

The dataset is available through the Stanford Digital Repository:

Year Stanford Digital Repository Link
2010 https://purl.stanford.edu/vk217bh4910
2011 https://purl.stanford.edu/jc488jb7715
2012 https://purl.stanford.edu/dc156hp0190
2013 https://purl.stanford.edu/km388vz4371
2014 https://purl.stanford.edu/sr325xz9271
2015 https://purl.stanford.edu/qw012qy2533
2016 https://purl.stanford.edu/vf806tr8954
2017 https://purl.stanford.edu/kp222tm1554
2018 https://purl.stanford.edu/nk828sc2920

The AIA and HMI data is split in to monthly files (XX is the 2-digit representation of the month), and EVE is provided as one file such as shown in the table below. This table corresponds to the 2010 data set.

AIA HMI EVE
AIA_0094_2010XX.tar HMI_Bx_2010XX.tar EVE_lines_MEGS-A.tar.gz
AIA_0131_2010XX.tar HMI_By_2010XX.tar  
AIA_0171_2010XX.tar HMI_Bz_2010XX.tar  
AIA_0193_2010XX.tar    
AIA_0211_2010XX.tar    
AIA_0304_2010XX.tar    
AIA_0335_2010XX.tar    
AIA_1600_2010XX.tar    
AIA_1700_2010XX.tar    
AIA_4500_2010XX.tar    

The corresponding files for the 2010 data set, as on the Stanford Digital Repository, are here: