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

Solar flares create adverse space weather impacting space and Earth-basedtechnologies. However, the difficulty of forecasting flares, and by extensionsevere space weather, is accentuated by the lack of any unique flare trigger ora single physical pathway. Studies indicate that multiple physical propertiescontribute to active region flare potential, compounding the challenge. Recentdevelopments in machine learning (ML) have enabled analysis ofhigher-dimensional data leading to increasingly better flare forecastingtechniques. However, consensus on high-performing flare predictors remainselusive. In the most comprehensive study to date, we conduct a comparativeanalysis of four popular ML techniques (k-nearest neighbor, logisticregression, random forest classifier, and support vector machine) by trainingthese on magnetic parameters obtained from the Helioseismic and Magnetic Imager(HMI) on board the Solar Dynamics Observatory (SDO) for the entirety of solarcycle 24. We demonstrate that the logistic regression and support vectormachine algorithms perform extremely well in forecasting active region flaringpotential. The logistic regression algorithm returns the highest true skillscore of $0.967 \pm 0.018$, possibly the highest classification performanceachieved with any strictly parametric study. From a comparative assessment, weestablish that the magnetic properties like total current helicity, totalvertical current density, total unsigned flux, R_VALUE, and total absolutetwist are the top-performing flare indicators. We also introduce and analyzetwo new performance metrics, namely, severe and clear space weather indicators.Our analysis constrains the most successful ML algorithms and identifiesphysical parameters that contribute most to active region flare productivity.

A Comparative Analysis of Machine-learning Models for Solar Flare Forecasting: Identifying High-performing Active Region Flare Indicators