Search for: All records

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. 

Solar flares are transient space weather events that pose a significant threat to space and ground-based technological systems, making their precise and reliable prediction crucial for mitigating potential impacts. This paper contributes to the growing body of research on deep learning methods for solar flare prediction, primarily focusing on highly overlooked near-limb flares and utilizing the attribution methods to provide a post hoc qualitative explanation of the model’s predictions. We present a solar flare prediction model, which is trained using hourly full-disk line-of-sight magnetogram images and employs a binary prediction mode to forecast ≥M-class flares that may occur within the following 24-hour period. To address the class imbalance, we employ a fusion of data augmentation and class weighting techniques; and evaluate the overall performance of our model using the true skill statistic (TSS) and Heidke skill score (HSS). Moreover, we applied three attribution methods, namely Guided Gradient-weighted Class Activation Mapping, Integrated Gradients, and Deep Shapley Additive Explanations, to interpret and cross-validate our model’s predictions with the explanations. Our analysis revealed that full-disk prediction of solar flares aligns with characteristics related to active regions (ARs). In particular, the key findings of this study are: (1) our deep learning models achieved an average TSS∼0.51 and HSS∼0.35, and the results further demonstrate a competent capability to predict near-limb solar flares and (2) the qualitative analysis of the model’s explanation indicates that our model identifies and uses features associated with ARs in central and near-limb locations from full-disk magnetograms to make corresponding predictions. In other words, our models learn the shape and texture-based characteristics of flaring ARs even when they are at near-limb areas, which is a novel and critical capability that has significant implications for operational forecasting. 

Solar flare prediction is a central problem in space weather forecasting. Existing solar flare prediction tools are mainly dependent on the GOES classification system, and models commonly use a proxy of maximum (peak) X-ray flux measurement over a particular prediction window to label instances. However, the background X-ray flux dramatically fluctuates over a solar cycle and often misleads both flare detection and flare prediction models during solar minimum, leading to an increase in false alarms. We aim to enhance the accuracy of flare prediction methods by introducing novel labeling regimes that integrate relative increases and cumulative measurements over prediction windows. Our results show that the data-driven labels can offer more precise prediction capabilities and complement the existing efforts.