English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This study aims to evaluate the performance of deep learning models inpredicting $\geq$M-class solar flares with a prediction window of 24 hours,using hourly sampled full-disk line-of-sight (LoS) magnetogram images,particularly focusing on the often overlooked flare events corresponding to thenear-limb regions (beyond $\pm$70$^{\circ}$ of the solar disk). We trainedthree well-known deep learning architectures--AlexNet, VGG16, and ResNet34using transfer learning and compared and evaluated the overall performance ofour models using true skill statistics (TSS) and Heidke skill score (HSS) andcomputed recall scores to understand the prediction sensitivity in central andnear-limb regions for both X- and M-class flares. The following pointssummarize the key findings of our study: (1) The highest overall performancewas observed with the AlexNet-based model, which achieved an averageTSS$\sim$0.53 and HSS$\sim$0.37; (2) Further, a spatial analysis of recallscores disclosed that for the near-limb events, the VGG16- and ResNet34-basedmodels exhibited superior prediction sensitivity. The best results, however,were seen with the ResNet34-based model for the near-limb flares, where theaverage recall was approximately 0.59 (the recall for X- and M-class was 0.81and 0.56 respectively) and (3) Our research findings demonstrate that ourmodels are capable of discerning complex spatial patterns from full-diskmagnetograms and exhibit skill in predicting solar flares, even in the vicinityof near-limb regions. This ability holds substantial importance for operationalflare forecasting systems.

Unveiling the Potential of Deep Learning Models for Solar Flare Prediction in Near-Limb Regions