Flare Index Prediction with Machine Learning Algorithms

• Published in: Solar physics 2021-10, Vol.296 (10), Article 150
• Main Authors: Chen, Anqin, Ye, Qian, Wang, Jingxiu
• Format: Article
• Language: English
• Subjects: Algorithms; Astrophysics and Astroparticles; Atmospheric Sciences; Datasets; Flux density; Machine learning; Magnetic fields; Magnetic flux; Magnetic properties; Mathematical models; Parameters; Photosphere; Physics; Physics and Astronomy; Solar cycle; Solar flares; Solar physics; Space Exploration and Astronautics; Space Sciences (including Extraterrestrial Physics; Space weather; Sunspot cycle; Sunspot groups; Sunspots; Weather effects
• ISSN: 0038-0938; 1573-093X
• DOI: 10.1007/s11207-021-01895-1

Solar flares are one of the most important sources of disastrous space weather events, leading to negative effects on spacecrafts and living organisms. It is very important to predict solar flares to minimize the potential losses. In this paper, we use three different machine learning algorithms: K-Nearest Neighbors (KNN), Random Forest (RF), and XGBoost (XGB) to predict the total flare index T flare and the maximum flare index M flare of an active region (AR) within the subsequent of 24, 48, and 72 hrs. First, we selected 54514 vector magnetograms of 129 ARs on the visible solar hemisphere in solar cycle 24 whose maximum sunspot groups’ area was larger than 400 μh. Then the following four magnetic parameters of each magnetogram were calculated: 1) the total magnetic flux | Φ tot | , 2) the total photospheric free magnetic energy density E free , 3) the gradient-weighted integral length of the neutral line with horizontal magnetic gradient of line-of-sight magnetic field larger than 0.1 G km − 1 ( WL SG ), and 4) the area with magnetic shear angle larger than 40 ∘ ( A Ψ ), as well as T flare and M flare corresponding to each magnetogram. Afterward, we split samples randomly into training (85% of the whole data) and testing (15%) data sets. After hyperparameter tuning and model construction we found that RF is an optimal algorithm for the prediction task and that the coefficients of determination ( R 2 ) of test data set via the majority of RF models are beyond 0.97. In addition, the feature importance of RF and XGB models indicates that | Φ tot | and E free are two optimal parameters to predict both T flare and M flare , and | Φ tot | and E free are the best parameters for M flare and T flare , respectively.