Fine-grained estimation of galaxy merger stages from observations is a key problem useful for validation of our current theoretical understanding of galaxy formation. To this end, we demonstrate a CNN-based regression model that is able to predict, for the first time, using a single image, the merger stage relative to the first perigee passage with a median error of 38.3 million years (Myrs) over a period of 400 Myrs. This model uses no specific dynamical modeling and learns only from simulated merger events. We show that our model provides reasonable estimates on real observations, approximately matching prior estimates provided by detailed dynamical modeling. We provide a preliminary interpretability analysis of our models, and demonstrate first steps toward calibrated uncertainty estimation.
@article{arxiv.2102.05182,
title = {A Deep Learning Approach for Characterizing Major Galaxy Mergers},
author = {Skanda Koppula and Victor Bapst and Marc Huertas-Company and Sam Blackwell and Agnieszka Grabska-Barwinska and Sander Dieleman and Andrea Huber and Natasha Antropova and Mikolaj Binkowski and Hannah Openshaw and Adria Recasens and Fernando Caro and Avishai Deke and Yohan Dubois and Jesus Vega Ferrero and David C. Koo and Joel R. Primack and Trevor Back},
journal= {arXiv preprint arXiv:2102.05182},
year = {2021}
}
Comments
Third Workshop on Machine Learning and the Physical Sciences (NeurIPS 2020), Vancouver, Canada