Accurate Identification of Galaxy Mergers with Imaging

Abstract: Merging galaxies play a key role in galaxy evolution, and progress in our understanding of galaxy evolution is slowed by the difficulty of making accurate galaxy merger identifications. We use GADGET-3 hydrodynamical simulations of merging galaxies with the dust radiative transfer code SUNRISE to produce a suite of merging galaxies that span a range of initial conditions. This includes simulated mergers that are gas poor and gas rich and that have a range of mass ratios (minor and major). We adapt the simulated images to the specifications of the SDSS imaging survey and develop a merging galaxy classification scheme that is based on this imaging. We leverage the strengths of seven individual imaging predictors ($Gini$, $M_{20}$, concentration, asymmetry, clumpiness, S\'ersic index, and shape asymmetry) by combining them into one classifier that utilizes Linear Discriminant Analysis. It outperforms individual imaging predictors in accuracy, precision, and merger observability timescale (>2 Gyr for all merger simulations). We find that the classification depends strongly on mass ratio and depends weakly on the gas fraction of the simulated mergers; asymmetry is more important for the major mergers, while concentration is more important for the minor mergers. This is a result of the relatively disturbed morphology of major mergers and the steadier growth of stellar bulges during minor mergers. Since mass ratio has the largest effect on the classification, we create separate classification approaches for minor and major mergers that can be applied to SDSS imaging or adapted for other imaging surveys.