The data deposited here are the both the input and resulting output of our machine learning efforts for predicting solar flare events. The input data are produced by our pre-processing pipeline, which is built to extract useful data from multiple sources -- Geostationary Operational Environmental Satellites (GOES) and Solar Dynamics Observatory (SDO)/Helioseismic and Magnetic Imager (HMI) These data.  These input files are the GOES_B_flare_list.csv, GOES_MX_flare_list.csv, SHARP_B_flare_data_300.hdf5 SHARP_MX_flare_data_300.hdf5.  The GOES files provide a list of flare events while the SHARP files provide time sequences of physical parameters derived from SDO/HMI data.   

The remaining files (B_HARPs_CNNencoded_part_XXX.hdf5, and M_X_HARPs_CNNencoded_part_XXX.hdf5) are the output from the convolutional neural network (CNN), a deep learning algorithm used here to extract/select features from raw HMI data.  The CNN is a deep learning model trained to capture both the spatial and temporal information from HMI magnetogram data for strong/weak flare classification and for predictions of flare intensities.  The input data for the CNN are HMI Active Region Patch (HARP) 3-component vector magnetograms available online from the Stanford Joint Science Operations Center (JSOC) at  http://jsoc.stanford.edu/. 


include neural network encoded features derived from vector magnetogram images derived from the Solar Dynamics Observatory (SDO) Helioseismic and Magnetic Imager (HMI). The original data are HMI Active Region Patch (HAPR) 3-component vector magnetograms available online from the Stanford Joint Science Operations Center (JSOC) at  http://jsoc.stanford.edu/