Presentation #241.27 in the session Evolution of Galaxies — iPoster Session.
Understanding the formation and evolution of ring galaxies, galaxies with an atypical ring-like structure, will improve understanding of black holes and galaxy dynamics as a whole. Current catalogs of rings are extremely limited: manual analysis takes months to accumulate an appreciable sample of rings and existing computational methods are vastly limited in terms of accuracy and detection rate. Without a sizable sample of rings further research into their properties is severely restricted. We investigate the usage of a convolutional neural network (CNN) to identify ring galaxies from unclassified samples of galaxies for the first time. A CNN was trained on a sample of 100,000 simulated galaxies, transfer learned to a sample of real galaxies and applied to a previously unclassified dataset to generate a catalog of rings which was then manually verified. The properties of these galaxies were then estimated from their photometries. A catalog of 580 ring galaxies, the current largest set of computationally identified rings, was extracted with 6.6 times the accuracy and 7.8 times the detection rate of conventional computational methods. The null hypothesis that the specific star formation rates of the ringed and non-ringed identifications were from the same distribution was rejected with a p-value of 0.015, agreeing with prior studies. With upcoming surveys such as the Vera Rubin Observatory Legacy Survey of Space and Time obtaining images of billions of galaxies, CNN models could be crucial to classify large populations of rings to better understand the peculiar mechanisms by which they form and evolve.