Automated classification of galaxy morphologies
Prof. Giuseppe Vinci
ACMS
University of Notre Dame
The classification of galaxy morphologies is an important step in the investigation of theories of hierarchical structure formation. While human expert visual classification remains quite effective and accurate, it cannot keep up with the massive influx of data from emerging sky surveys. A variety of approaches have been proposed to classify large numbers of galaxies. These approaches include crowdsourced visual classification, and automated and computational methods, such as machine learning methods based on designed morphology statistics and deep learning. In this presentation I discuss the use of galaxy morphology statistics for automated galaxy morphology classification. I present two novel galaxy morphology statistics, descent average and descent variance, which can be efficiently extracted from telescope galaxy images, and discuss the performance of these statistics at accurately classifying spiral and elliptical galaxies when used as features of a random forest classifier together with other existing galaxy morphology statistics. Finally, I discuss my current and future research directions in astrostatistics.
Hosted by Prof. Howk