Solar Flare Forecast Magnetogram Dataset

Solar flare forecasting magnetogram dataset. The magnetogram data are obtained from the Solar Dynamics Observatory/Helioseismic and Magnetic Imager (SDO/HMI), and the flare event records are collected from the National Oceanic and Atmospheric Administration (NOAA). The SDO/HMI magnetograms have a temporal resolution of 720 s and a spatial resolution of 0.5 arcsec per pixel. Magnetograms from 2010 to 2019 are selected with a sampling interval of 96 minutes. The magnetic field values are clipped to the range of ±500 G to preserve the main magnetic structures of active regions while avoiding excessive dynamic range. M-class and higher flares are labeled as “flare” events, and the remaining samples are labeled as “nonflare” events. For a given forecasting time window (12, 24, or 48 hours), magnetograms within the specified time window before a flare event are treated as positive samples, while negative samples are randomly selected from magnetograms without flare events. The final dataset spans from May 2010 to January 2019 and contains 2,988 positive samples and 70,822 negative samples. A nonoverlapping temporal splitting strategy is adopted, using data from 2011 and 2015 as the testing set and the remaining years as the training set, in order to avoid data leakage and ensure reliable model evaluation. The dataset is highly imbalanced, with positive-to-negative sample ratios of approximately 1:25 in the training set and 1:22 in the testing set.