Search

In this work we study the association between eruptive filaments/prominences and coronal mass ejections (CMEs) using machine learning-based algorithms that analyse the solar data available between January 1996 and December 2001. The support vector machine (SVM) learning algorithm is used for the purpose of knowledge extraction from the association results. The aim is to identify patterns of associations that can be represented using SVM learning rules for the subsequent use in near real-time and reliable CME prediction systems. Timing and location data in the US National Geophysical Data Center (NGDC) filament catalogue and the Solar and Heliospheric Observatory/ Large Angle and Spectrometric Coronagraph (SOHO/LASCO) CME catalogue are processed to associate filaments with CMEs. In the previous studies, which classified CMEs into gradual and impulsive CMEs, the associations were refined based on the CME speed and acceleration. Then the associated pairs were refined manually to increase the accuracy of the training dataset. In the current study, a data-mining system is created to process and associate filament and CME data, which are arranged in numerical training vectors. Then the data are fed to SVMs to extract the embedded knowledge and provide the learning rules that can have the potential, in the future, to provide automated predictions of CMEs. The features representing the event time (average of the start and end times), duration, type, and extent of the filaments are extracted from all the associated and not-associated filaments and converted to a numerical format that is suitable for SVM use. Several validation and verification methods are used on the extracted dataset to determine if CMEs can be predicted solely and efficiently based on the associated filaments. More than 14 000 experiments are carried out to optimise the SVM and determine the input features that provide the best performance. [ABSTRACT FROM AUTHOR]

Machine-learning algorithms are applied to explore the relation between significant flares and their associated CMEs. The NGDC flares catalogue and the SOHO/LASCO CME catalogue are processed to associate X and M-class flares with CMEs based on timing information. Automated systems are created to process and associate years of flare and CME data, which are later arranged in numerical-training vectors and fed to machine-learning algorithms to extract the embedded knowledge and provide learning rules that can be used for the automated prediction of CMEs. Properties representing the intensity, flare duration, and duration of decline and duration of growth are extracted from all the associated (A) and not-associated (NA) flares and converted to a numerical format that is suitable for machine-learning use. The machine-learning algorithms Cascade Correlation Neural Networks (CCNN) and Support Vector Machines (SVM) are used and compared in our work. The machine-learning systems predict, from the input of a flare’s properties, if the flare is likely to initiate a CME. Intensive experiments using Jack-knife techniques are carried out and the relationships between flare properties and CMEs are investigated using the results. The predictive performance of SVM and CCNN is analysed and recommendations for enhancing the performance are provided. [ABSTRACT FROM AUTHOR]

This paper presents a hybrid system for automatic detection and McIntosh-based classification of sunspot groups on SOHO/MDI white-light images using active-region data extracted from SOHO/MDI magnetogram images. After sunspots are detected from MDI white-light images they are grouped/clustered using MDI magnetogram images. By integrating image-processing and neural network 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 rate 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. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

A fast hybrid system for the automated detection and verification of active regions (plages) and filaments in solar images is presented in this paper. The system combines automated image processing with machine learning. The imaging part consists of five major stages. The solar disk is detected in the first stage, using a morphological hit-miss transform, watershed transform and Filling algorithm. An image-enhancement technique is introduced to remove the limb-darkening effect and intensity filtering is implemented followed by a modified region-growing technique to detect the regions of interest (RoI). The algorithms are tested on H-α and CA II K3-line solar images that are obtained from Meudon Observatory, covering the period from July 2, 2001 till August 4, 2001. The detection algorithm is fast and it achieves false acceptance rate (FAR) error rate of 67% and false rejection rate (FRR) error rate of 3% for active regions, and FAR error rate of 19% and FRR error rate of 14% for filaments, when compared with the manually detected filaments in the synoptic maps. The detection performance is enhanced further using a neural network (NN), which is trained on statistical features extracted from the RoI and non-RoI. With the use of this combination the FAR has dropped to 2% for active regions and 4% for filaments.© 2006 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 15, 199–210, 2005 [ABSTRACT FROM AUTHOR]