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 are among the most severe space weather phenomena, and they havethe capacity to generate radiation storms and radio disruptions on Earth. Theaccurate prediction of solar flare events remains a significant challenge,requiring continuous monitoring and identification of specific features thatcan aid in forecasting this phenomenon, particularly for different classes ofsolar flares. In this study, we aim to forecast C and M class solar flaresutilising a machine-learning algorithm, namely the Light Gradient BoostingMachine. We have utilised a dataset spanning 9 years, obtained from theSpace-weather Helioseismic and Magnetic Imager Active Region Patches (SHARP),with a temporal resolution of 1 hour. A total of 37 flare features wereconsidered in our analysis, comprising of 25 active region parameters and 12flare history features. To address the issue of class imbalance in solar flaredata, we employed the Synthetic Minority Oversampling Technique (SMOTE). Weused two labeling approaches in our study: a fixed 24-hour window label and avarying window that considers the changing nature of solar activity. Then, thedeveloped machine learning algorithm was trained and tested using forecastverification metrics, with an emphasis on evaluating the true skill statistic(TSS). Furthermore, we implemented a feature selection algorithm to determinethe most significant features from the pool of 37 features that coulddistinguish between flaring and non-flaring active regions. We found thatutilising a limited set of useful features resulted in improved predictionperformance. For the 24-hour prediction window, we achieved a TSS of 0.63(0.69) and accuracy of 0.90 (0.97) for $\geq$C ($\geq$M) class solar flares.

Solar Flare Prediction and Feature Selection using Light Gradient Boosting Machine Algorithm