Automatic Short-Term Solar Flare Prediction Using Machine Learning and Sunspot Associations

In this paper, a machine-learning-based system that could provide automated short-term solar flare prediction is presented. This system accepts two sets of inputs: McIntosh classification of sunspot groups and solar cycle data. In order to establish a correlation between solar flares and sunspot groups, the system explores the publicly available solar catalogues from the National Geophysical Data Center to associate sunspots with their corresponding flares based on their timing and NOAA numbers. The McIntosh classification for every relevant sunspot is extracted and converted to a numerical format that is suitable for machine learning algorithms. Using this system we aim to predict whether a certain sunspot class at a certain time is likely to produce a significant flare within six hours time and if so whether this flare is going to be an X or M flare. Machine learning algorithms such as Cascade-Correlation Neural Networks (CCNNs), Support Vector Machines (SVMs) and Radial Basis Function Networks (RBFN) are optimised and then compared to determine the learning algorithm that would provide the best prediction performance. It is concluded that SVMs provide the best performance for predicting whether a McIntosh classified sunspot group is going to flare or not but CCNNs are more capable of predicting the class of the flare to erupt. A hybrid system that combines a SVM and a CCNN is suggested for future use.     

Spatial Characterization of a Flare Using Radio Observations and Magnetic Field Topology

Using magnetograms, EUV and Hα images, Owens Valley Solar Array microwave observations, and 212-GHz flux density derived from the Solar Submillimeter Telescope data, we determine the spatial characteristics of the 1B/M6.9 flare that occurred on November 28, 2001, starting at 16:26 UT in active region (AR) NOAA 9715. This flare is associated with a chromospheric mass ejection or surge observed at 16:42 UT in the Hα images. We compute the coronal magnetic field under the linear force-free field assumption, constrained by the photospheric data of the Michelson Doppler Imager and loops observed by the Extreme Ultraviolet Imaging Telescope. The analysis of the magnetic field connectivity allows us to conclude that magnetic field reconnection between two different coronal/chromospheric sets of arches was at the origin of the flare and surge, respectively. The optically thick microwave spectrum at peak time shows a shape compatible with the emission from two different sites. Fitting gyrosynchrotron emission to the observed spectrum, we derive parameters for each source. Electronic Supplementary Material The online version of this article () contains supplementary material, which is available to authorized users.