Solar flares produce radiation which can have an almost immediate effect on the near-Earth environment, making it crucial to forecast flares in order to mitigate their negative effects. The number of published approaches to flare forecasting using photospheric magnetic field observations has proliferated, with varying claims about how well each works. Because of the different analysis techniques and data sets used, it is essentially impossible to compare the results from the literature. This problem is exacerbated by the low event rates of large solar flares. The challenges of forecasting rare events have long been recognized in the meteorology community, but have yet to be fully acknowledged by the space weather community. During the interagency workshop on "all clear" forecasts held in Boulder, CO in 2009, the performance of a number of existing algorithms was compared on common data sets, specifically line-of-sight magnetic field and continuum intensity images from MDI, with consistent definitions of what constitutes an event. We demonstrate the importance of making such systematic comparisons, and of using standard verification statistics to determine what constitutes a good prediction scheme. When a comparison was made in this fashion, no one method clearly outperformed all others, which may in part be due to the strong correlations among the parameters used by different methods to characterize an active region. For M-class flares and above, the set of methods tends towards a weakly positive skill score (as measured with several distinct metrics), with no participating method proving substantially better than climatological forecasts.

Citation: Ahmed OW, Qahwaji RSR, Colak T, Higgins PAB, Gallagher P and Bloomfield S (2013) Solar flare prediction using advanced feature extraction, machine learning and feature selection. Solar Physics. 283(1): 157-175. Abstract: Novel machine-learning and feature-selection algorithms have been developed to study: (i) the flare prediction capability of magnetic feature (MF) properties generated by the recently developed Solar Monitor Active Region Tracker (SMART); (ii) SMART's MF properties that are most significantly related to flare occurrence. Spatio-temporal association algorithms are developed to associate MFs with flares from April 1996 to December 2010 in order to differentiate flaring and non-flaring MFs and enable the application of machine learning and feature selection algorithms. A machine-learning algorithm is applied to the associated datasets to determine the flare prediction capability of all 21 SMART MF properties. The prediction performance is assessed using standard forecast verification measures and compared with the prediction measures of one of the industry's standard technologies for flare prediction that is also based on machine learning -Automated Solar Activity Prediction (ASAP). The comparison shows that the combination of SMART MFs with machine learning has the potential to achieve more accurate flare prediction than ASAP. Feature selection algorithms are then applied to determine the MF properties that are most related to flare occurrence. It is found that a reduced set of 6 MF properties can achieve a similar degree of prediction accuracy as the full set of 21 SMART MF properties. ABSTRACT:Novel machine-learning and feature-selection algorithms have been developed to study: (i) the flare prediction capability of magnetic feature (MF) properties generated by the recently developed Solar Monitor Active Region Tracker (SMART); (ii) SMART's MF properties that are most significantly related to flare occurrence. Spatio-temporal association algorithms are developed to associate MFs with flares from April 1996 to December 2010 in order to differentiate flaring and non-flaring MFs and enable the application of machine learning and feature selection algorithms. A machine-learning algorithm is applied to the associated datasets to determine the flare prediction capability of all 21 SMART MF properties. The prediction performance is assessed using standard forecast verification measures and compared with the prediction measures of one of the industry's standard technologies for flare prediction that is also based on machine learning -Automated Solar Activity Prediction (ASAP). The comparison shows that the combination of SMART MFs with machine learning has the potential to achieve more accurate flare prediction than ASAP. Feature selection algorithms are then applied to determine the MF properties that are most related to flare occurrence. It is found that a reduced set of 6 MF properties can achieve a similar degree of prediction accuracy as the full set of 21 SMART MF properties.

Abstract. In this paper, a machine learning-based system that could provide automated short-term solar flares 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 Centre (NGDC) 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 if a certain sunspot class at a certain time is likely to produce a significant flare within six hours time and whether this flare is going to be an X or M flare. Machine learning algorithms such as Cascade-Correlation Neural Networks (CCNN), Support Vector Machines (SVM) 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 SVM provides the best performance for predicting if a McIntosh classified sunspot group is going to flare or not but CCNN is more capable of predicting the class of the flare to erupt. A hybrid system that combines SVM and CCNN is suggested for future use.

[1] The importance of real-time processing of solar data especially for space weather applications is increasing continuously. In this paper, we present an automated hybrid computer platform for the shortterm prediction of significant solar flares using SOHO/Michelson Doppler Imager images. This platform is called the Automated Solar Activity Prediction tool (ASAP). This system integrates image processing and machine learning to deliver these predictions. A machine learning-based system is designed to analyze years of sunspot and flare data to create associations that can be represented using computerbased learning rules. An imaging-based real-time system that provides automated detection, grouping, and then classification of recent sunspots based on the McIntosh classification is also created and integrated within this system. The properties of the sunspot regions are extracted automatically by the imaging system and processed using the machine learning rules to generate the real-time predictions. Several performance measurement criteria are used and the results are provided in this paper. Also, quadratic score is used to compare the prediction results of ASAP with NOAA Space Weather Prediction Center (SWPC) between 1999 and 2002, and it is shown that ASAP generates more accurate predictions compared to SWPC.Citation: Colak, T., and R. Qahwaji (2009), Automated Solar Activity Prediction: A hybrid computer platform using machine learning and solar imaging for automated prediction of solar flares, Space Weather, 7, S06001,

Abstract.A hybrid system for the automated detection and McIntosh-based classification of sunspot groups on SOHO/MDI white-light images using active-region data extracted from SOHO/MDI magnetogram images is presented in this paper. After sunspots are detected from MDI white-light images they are grouped/clustered using MDI magnetogram images. By integrating image-processing and Neural Networks techniques, detected sunspot regions are classified automatically according to the McIntosh classification system. Our results show that the automated grouping and classification of sunspots is possible with a high success rates when compared to the existing manually created catalogues. In addition our system can detect and classify sunspot groups in their early stages, which are usually missed by human observers.