Bitmap Filtered Line of Sight HMI Active Region Patches with Augmentations

Dataset Description This dataset consists of processed Line-of-Sight (LoS) magnetogram images of Active Regions (ARs) from the Helioseismic and Magnetic Imager (HMI) onboard the Solar Dynamics Observatory (SDO). The images are derived from the Space-Weather HMI Active Region Patches (SHARP) data product definitive series and cover the period from May 2010 to 2018, sampled hourly. Dataset Contents: Processed Magnetogram Images: Each image represents a cropped and standardized view of an AR patch, extracted and adjusted from the original magnetograms. These images have been filtered and normalized to a size of 512×512 pixels. Processing Steps: Cropping: Magnetograms are cropped using bitmaps that define the region of interest within the AR patches. Regions smaller than 70 pixels in width are excluded. Flux Adjustment: Magnetic flux values are capped at ±256 G, with values within ±25 G set to 0 to minimize noise. Standardization: Patches are resized to 512×512 pixels using zero-padding for smaller patches or a 512×512 kernel to select regions with the maximum total unsigned flux (USFLUX) for larger patches. Normalization: Final images are scaled to fit within the range of 0-255. Data Dictionary: harp_N1_N2: These tar files contains folders where the AR patches with harp number N1 to N2 are included. complete_hourly_dataset.csv: This includes the list of hourly sampled magnetograms along with their associated goes flare class, assuming a 24 hour forecast horizon. augmentations: Five different augmentations of AR patches corresponding to GOES flare classes greater than C, assuming a 24 hour forecast horizon are listed as 5 different tar files. Look for: horizontal flip, vertical_flip, add noise, polarity change, and gaussian blur.