Mergers between galaxies can be drivers of morphological transformation and various physical phenomena, including star-formation, black-hole accretion, and chemical redistribution. These effects are seen clearly among galaxies that are currently interacting (pairs) -- which can be selected with high purity spectroscopically with correctable completeness. Galaxies in the merger remnant phase (post-mergers) exhibit some of the strongest changes, but are more elusive because identification must rely on the remnant properties alone. Part I of this work combines images and stellar kinematics to identify merger remnants using deep learning (arXiv:2201.03579). There, I showed that kinematics are not the smoking-gun for improving remnant classification purity and that high posterior purity remains a significant challenge for remnant identification in the local Universe. However an alternative approach, explored in this work, that treats all galaxies as merger remnants and re-frames the problem as an image-based deep regression yields exciting results.

{"references": ["Bottrell, Connor et al (2022), MNRAS 511 100 (doi: 10.1093/mnras/stab3717, arXiv:2201.03579)"]}