Studying Morphology & Quenching of Galaxies in the NGRST Era using Interpretable Convolutional Neural Networks

The traditional methods of obtaining morphological classifications of galaxies are not scalable to the large data volumes expected from future surveys like NGRST. To overcome this, we have developed a publicly available convolutional neural network (CNN) called Galaxy Morphology Network (GaMorNet) that classifies galaxies according to their bulge-to-total light ratio. GaMorNet does not need a large amount of real data for training and can be applied to datasets with a range of signal-to-noise ratios and spatial resolutions. We have used GaMorNet to study the quenching of star formation in ∼100,000 (z∼0) SDSS and ∼20,000 (z∼1) CANDELS galaxies using morphology-separated color-mass diagrams. We first trained GaMorNet on simulations of galaxies and then transfer-learned using ∼25% of each data set to achieve misclassification rates of ≲5%. Using the GaMorNet classifications, we find that bulge- and disk-dominated galaxies have distinct color-mass diagrams. For both datasets, disk-dominated galaxies peak in the blue cloud, across a broad range of masses, consistent with the slow exhaustion of star-forming gas. In contrast, bulge-dominated galaxies are mostly red, with much smaller numbers down toward the blue cloud, suggesting rapid quenching and fast evolution across the green valley. We have also used a combination of different CNN visualisation techniques to investigate GaMorNet’s decision-making process, making our results interpretable and robust.