Using Machine Learning Methods to Forecast if Solar Flares Will Be Associated with CMEs and SEPs

Among the eruptive activity phenomena observed on the Sun, the most technology threatening ones are flares with associated coronal mass ejections (CMEs) and solar energetic particles (SEPs). Flares with associated CMEs and SEPs are produced by magnetohydrodynamical processes in magnetically active regions (ARs) on the Sun. However, these ARs do not only produce flares with associated CMEs and SEPs, they also lead to flares and CMEs, which are not associated with any other event. In an attempt to distinguish flares with associated CMEs and SEPs from flares and CMEs, which are unassociated with any other event, we investigate the performances of two machine learning algorithms. To achieve this objective, we employ support vector machines (SVMs) and multilayer perceptrons (MLPs) using data from the Space Weather Database of Notification, Knowledge, Information (DONKI) of NASA Space Weather Center, {\it the Geostationary Operational Environmental Satellite} ({\it GOES}), and the Space-Weather Heliospheric and Magnetic Imager Active Region Patches (SHARPs). We show that True Skill Statistics (TSS) and Heidke Skill Scores (HSS) calculated for SVMs are slightly better than those from the MLPs. We also show that the forecasting time frame of 96 hours provides the best results in predicting if a flare will be associated with CMEs and SEPs (TSS=0.92$\pm$0.09 and HSS=0.92$\pm$0.08). Additionally, we obtain the maximum TSS and HSS values of 0.91$\pm$0.06 for predicting that a flare will not be associated with CMEs and SEPs for the 36 hour forecast window, while the 108 hour forecast window give the maximum TSS and HSS values for predicting CMEs will not be accompanying any events (TSS=HSS=0.98$\pm$0.02).

[1]  P. Charbonneau.  Dynamo Models of the Solar Cycle , 2005 .

[2]  H. Koskinen,et al.  Coronal mass ejections and their sheath regions in interplanetary space , 2017, Living Reviews in Solar Physics.

[3]  A. Tylka,et al.  Spatial Distribution of Solar Energetic Particles in the Inner Heliosphere , 2013 .

[4]  Bill Wilson,et al.  In a relationship , 2013 .

[5]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[6]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[7]  C. J. Wolfson,et al.  Design and Ground Calibration of the Helioseismic and Magnetic Imager (HMI) Instrument on the Solar Dynamics Observatory (SDO) , 2012 .

[8]  L. Boucheron,et al.  PREDICTION OF SOLAR FLARE SIZE AND TIME-TO-FLARE USING SUPPORT VECTOR MACHINE REGRESSION , 2015, 1511.01941.

[9]  A. Benz,et al.  Flare Observations , 2016, Living Reviews in Solar Physics.

[10]  M. Aschwanden,et al.  RECONCILIATION OF WAITING TIME STATISTICS OF SOLAR FLARES OBSERVED IN HARD X-RAYS , 2010, 1002.4869.

[11]  K. Shibata,et al.  Solar Flares: Magnetohydrodynamic Processes , 2011 .

[12]  David J. C. MacKay,et al.  Information Theory, Inference, and Learning Algorithms , 2004, IEEE Transactions on Information Theory.

[13]  Monica G. Bobra,et al.  PREDICTING CORONAL MASS EJECTIONS USING MACHINE LEARNING METHODS , 2016, 1603.03775.

[14]  D. Baker,et al.  Sun Unleashes Halloween Storm , 2004 .

[15]  D. Hathaway.  The Solar Cycle , 2010, Living reviews in solar physics.

[16]  Edward W. Cliver,et al.  The 1859 space weather event revisited: limits of extreme activity , 2013 .

[17]  Chih-Jen Lin,et al.  A Comparison of Methods for Multi-class Support Vector Machines , 2015 .

[18]  Manolis K. Georgoulis,et al.  Forecasting Solar Flares Using Magnetogram-based Predictors and Machine Learning , 2018, 1801.05744.

[19]  Carolus J. Schrijver,et al.  Heliophysics: Space Storms and Radiation: Causes and Effects , 2010 .

[20]  Rami Qahwaji,et al.  Solar Flare Prediction Using Advanced Feature Extraction, Machine Learning, and Feature Selection , 2011, Solar Physics.

[21]  J. T. Hoeksema,et al.  The Helioseismic and Magnetic Imager (HMI) Vector Magnetic Field Pipeline: SHARPs – Space-Weather HMI Active Region Patches , 2014, 1404.1879.

[22]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

[23]  K. D. Leka,et al.  Photospheric Magnetic Field Properties of Flaring versus Flare-quiet Active Regions. I. Data, General Approach, and Sample Results , 2003 .

[24]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[25]  L. Goddard.  Information Theory , 1962, Nature.

[26]  Donald V. Reames.  The Two Sources of Solar Energetic Particles , 2012 .

[27]  Monica G. Bobra,et al.  SOLAR FLARE PREDICTION USING SDO/HMI VECTOR MAGNETIC FIELD DATA WITH A MACHINE-LEARNING ALGORITHM , 2014, 1411.1405.

[28]  P. Heidke,et al.  Berechnung Des Erfolges Und Der Güte Der Windstärkevorhersagen Im Sturmwarnungsdienst , 1926 .

[29]  D. Culler,et al.  Comparison of methods , 2000 .

[30]  Carolus J. Schrijver,et al.  A Characteristic Magnetic Field Pattern Associated with All Major Solar Flares and Its Use in Flare Forecasting , 2007 .

[31]  Lidia Driel-Gesztelyi,et al.  Evolution of Active Regions , 2015 .

[32]  Daren Yu,et al.  Short-Term Solar Flare Prediction Using a Sequential Supervised Learning Method , 2009 .

[33]  A. Sterling,et al.  THE LIMIT OF MAGNETIC-SHEAR ENERGY IN SOLAR ACTIVE REGIONS , 2012 .

[34]  P. Chen.  Coronal Mass Ejections: Models and Their Observational Basis , 2011 .

[35]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[36]  T. Howard,et al.  Coronal Mass Ejections: Observations , 2012 .

[37]  R. C. Carrington.  Description of a Singular Appearance seen in the Sun on September 1, 1859 , 1859 .

[38]  Geoffrey E. Hinton.  Connectionist Learning Procedures , 1989, Artif. Intell..