Using Machine Learning to Determine Morphologies of z < 1 AGN Host Galaxies in the Hyper Suprime-Cam Wide Survey

We present a machine-learning framework to accurately characterize the morphologies of active galactic nucleus (AGN) host galaxies within z < 1. We first use PSFGAN to decouple host galaxy light from the central point source, then we invoke the Galaxy Morphology Network (GaMorNet) to estimate whether the host galaxy is disk-dominated, bulge-dominated, or indeterminate. Using optical images from five bands of the HSC Wide Survey, we build models independently in three redshift bins: low (0 < z < 0.25), mid (0.25 < z < 0.5), and high (0.5 < z < 1.0). By first training on a large number of simulated galaxies, then fine-tuning using far fewer classified real galaxies, our framework predicts the actual morphology for similar to 60%-70% of the host galaxies from test sets, with a classification precision of similar to 80%-95%, depending on the redshift bin. Specifically, our models achieve a disk precision of 96%/82%/79% and bulge precision of 90%/90%/80% (for the three redshift bins) at thresholds corresponding to indeterminate fractions of 30%/43%/42%. The classification precision of our models has a noticeable dependency on host galaxy radius and magnitude. No strong dependency is observed on contrast ratio. Comparing classifications of real AGNs, our models agree well with traditional 2D fitting with GALFIT. The PSFGAN+GaMorNet framework does not depend on the choice of fitting functions or galaxy-related input parameters, runs orders of magnitude faster than GALFIT, and is easily generalizable via transfer learning, making it an ideal tool for studying AGN host galaxy morphology in forthcoming large imaging surveys.

Automated summary

We propose a machine-learning framework for accurately characterizing the morphologies of active galactic nucleus (AGN) host galaxies within z < 1. The framework consists of two parts: PSFGAN for separating host galaxy light from the central point source, and GaMorNet for estimating the dominant morphology. The models built in three redshift bins achieve high prediction accuracy and classification precision, with a noticeable dependency on host galaxy radius and magnitude.