Steps Toward Large-scale Solar Image Data Analysis to Differentiate Solar Phenomena

We detail the investigation of the first application of several dissimilarity measures for large-scale solar image data analysis. Using a solar-domain-specific benchmark dataset that contains multiple types of phenomena, we analyzed combinations of image parameters with different dissimilarity measures in order to determine which combinations will allow us to differentiate among the multiple solar phenomena from both intra-class and inter-class perspectives, where by class we refer to same types of solar phenomena. We also investigate the issue of reducing data dimensionality by applying multidimensional scaling to the dissimilarity matrices we produced using the previously mentioned combinations. As an early investigation into dimensionality reduction, by applying multidimensional scaling (MDS) we will investigate how many MDS components are needed in order to maintain a good representation of our data (in a new artificial data space) and how many can be discarded in order to enhance our querying performance. Finally, we present a comparative analysis among several classifiers in order to determine the quality of the dimensionality reduction achieved with the aforementioned combination of image parameters, similarity measures, and multidimensional scaling (MDS).