Automatic Machine Learning Framework to Study Morphological Parameters of AGN Host Galaxies within $z < 1.4$ in the Hyper Supreme-Cam Wide Survey

TL;DR

We address the challenge of quantitatively characterizing AGN host galaxy morphology across redshift by developing a composite ML framework that combines PSFGAN for AGN light removal with GaMPEN for Bayesian morphology inference, yielding posterior estimates for $L_B/L_T$, $R_e$, and $F$ of host galaxies up to $z<1.4$. The models are trained on simulated data and refined via transfer learning on real Hyper Suprime-Cam Wide DR3 images, with transfer-labels derived from GALFIT fits to ~20,000 galaxies per redshift bin. The methodology splits the data into five redshift bins and optimizes separate models per bin while highlighting a speed-up of at least three orders of magnitude over traditional light-profile fitting. The approach demonstrates high agreement with GALFIT-derived values and offers a scalable, retrainable framework for future large surveys such as Rubin-LSST, Euclid, and Roman.

Abstract

We present a composite machine learning framework to estimate posterior probability distributions of bulge-to-total light ratio, half-light radius, and flux for Active Galactic Nucleus (AGN) host galaxies within $z<1.4$ and $m<23$ in the Hyper Supreme-Cam Wide survey. We divide the data into five redshift bins: low ($0<z<0.25$), mid ($0.25<z<0.5$), high ($0.5<z<0.9$), extra ($0.9<z<1.1$) and extreme ($1.1<z<1.4$), and train our models independently in each bin. We use PSFGAN to decompose the AGN point source light from its host galaxy, and invoke the Galaxy Morphology Posterior Estimation Network (GaMPEN) to estimate morphological parameters of the recovered host galaxy. We first trained our models on simulated data, and then fine-tuned our algorithm via transfer learning using labeled real data. To create training labels for transfer learning, we used GALFIT to fit $\sim 20,000$ real HSC galaxies in each redshift bin. We comprehensively examined that the predicted values from our final models agree well with the GALFIT values for the vast majority of cases. Our PSFGAN + GaMPEN framework runs at least three orders of magnitude faster than traditional light-profile fitting methods, and can be easily retrained for other morphological parameters or on other datasets with diverse ranges of resolutions, seeing conditions, and signal-to-noise ratios, making it an ideal tool for analyzing AGN host galaxies from large surveys coming soon from the Rubin-LSST, Euclid, and Roman telescopes.