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

Abstract

We present a machine-learning framework to accurately characterize 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 $(0<z<0.25)$, medium $(0.25<z<0.5)$, 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 $\sim$ $60\%-70\%$ host galaxies from test sets, with a classification precision of $\sim$ $80\%-95\%$, depending on redshift bin. Specifically, our models achieve disk precision of $96\%/82\%/79\%$ and bulge precision of $90\%/90\%/80\%$ (for the 3 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 survey.

arXiv commentAccepted for publication in The Astrophysical Journal. 35 Pages. 25 Figures

References in corpus (66)

• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• Array Programming with NumPy
• The Sloan Digital Sky Survey: Technical Summary
• A Fundamental Relation Between Supermassive Black Holes and Their Host Galaxies
• Coevolution (Or Not) of Supermassive Black Holes and Host Galaxies
• Cosmic Star Formation History
• Binary companions of evolved stars in APOGEE DR14: Search method and catalog of ~5,000 companions
• The many lives of active galactic nuclei: cooling flows, black holes and the luminosities and colours of galaxies
• A Relationship Between Nuclear Black Hole Mass and Galaxy Velocity Dispersion
• Energy input from quasars regulates the growth and activity of black holes and their host galaxies
• Observational Evidence of AGN Feedback
• Detailed Structural Decomposition of Galaxy Images
• CANDELS: The Cosmic Assembly Near-infrared Deep Extragalactic Legacy Survey - The Hubble Space Telescope Observations, Imaging Data Products and Mosaics
• A Unified, Merger-Driven Model for the Origin of Starbursts, Quasars, the Cosmic X-Ray Background, Supermassive Black Holes and Galaxy Spheroids
• The Star Formation History of Field Galaxies
• The Co-Evolution of Galaxies and Supermassive Black Holes: Insights from Surveys of the Contemporary Universe
• An Observational Determination of the Bolometric Quasar Luminosity Function
• The Hyper Suprime-Cam SSP Survey: Overview and Survey Design
• The Assembly and Merging History of Supermassive Black Holes in Hierarchical Models of Galaxy Formation
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• The Green Valley is a Red Herring: Galaxy Zoo reveals two evolutionary pathways towards quenching of star formation in early- and late-type galaxies
• Toward the Standard Population Synthesis Model of the X-Ray Background: Evolution of X-Ray Luminosity and Absorption Functions of Active Galactic Nuclei Including Compton-Thick Populations
• A Catalog of Bulge+Disk Decompositions and Updated Photometry for 1.12 Million Galaxies in the Sloan Digital Sky Survey
• Black Holes in Galaxy Mergers: Evolution of Quasars
• Self-Consistent Models of the AGN and Black Hole Populations: Duty Cycles, Accretion Rates, and the Mean Radiative Efficiency
• Second Data Release of the Hyper Suprime-Cam Subaru Strategic Program
• Galaxy Merger Morphologies and Time-Scales from Simulations of Equal-Mass Gas-Rich Disc Mergers
• CANDELS: Constraining the AGN-Merger Connection with Host Morphologies at z~2
• Major Galaxy Mergers Only Trigger the Most Luminous AGN
• Improving galaxy morphologies for SDSS with Deep Learning
• Third Data Release of the Hyper Suprime-Cam Subaru Strategic Program
• A catalog of visual-like morphologies in the 5 CANDELS fields using deep-learning
• Evidence for Quasar Activity Triggered by Galaxy Mergers in HST Observations of Dust-reddened Quasars
• Merger Histories of Galaxy Halos and Implications for Disk Survival
• AGN Host Galaxy Morphologies in COSMOS
• Growing supermassive black holes in the late stages of galaxy mergers are heavily obscured
• A definitive merger-AGN connection at z~0 with CFIS: mergers have an excess of AGN and AGN hosts are more frequently disturbed
• HST WFC3/IR Observations of Active Galactic Nucleus Host Galaxies at z~2: Supermassive Black Holes Grow in Disk Galaxies
• Morphologies of z~0.7 AGN Host Galaxies in CANDELS: No trend of merger incidence with AGN luminosity
• GALAPAGOS: From Pixels to Parameters
• The effect of radiation pressure on dusty absorbing gas around AGN
• Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active Learning
• Secular evolution and a non-evolving black hole to galaxy mass ratio in the last 7 Gyr
• Using transfer learning to detect galaxy mergers
• Heavily Obscured Quasar Host Galaxies at z~2 are Disks, Not Major Mergers
• Radiative pressure feedback by a quasar in a galactic bulge
• Machine and Deep Learning Applied to Galaxy Morphology -- A Comparative Study
• A comprehensive and uniform sample of broad-line active galactic nuclei from the SDSS DR7
• Transfer learning for galaxy morphology from one survey to another
• Deep learning for galaxy surface brightness profile fitting
• Major mergers are not the dominant trigger for high-accretion AGNs at z = 2
• A catalog of polychromatic bulge-disk decompositions of ~ 17.600 galaxies in CANDELS
• Beyond the Hubble Sequence -- Exploring Galaxy Morphology with Unsupervised Machine Learning
• The Hierarchical Origins of Observed Galaxy Morphology
• Galaxy Morphological Classification Catalogue of the Dark Energy Survey Year 3 data with Convolutional Neural Networks
• The Accuracy of Morphological Decomposition of Active Galactic Nucleus Host Galaxies
• Galaxy Morphology Network: A Convolutional Neural Network Used to Study Morphology and Quenching in $\sim 100,000$ SDSS and $\sim 20,000$ CANDELS Galaxies
• The redshift evolution of major merger triggering of luminous AGN: a slight enhancement at z$\sim$2
• Pushing automated morphological classifications to their limits with the Dark Energy Survey
• A Catalog of AGN Host Galaxies Observed with HST/ACS: Correlations between Star Formation and AGN Activity
• The Spectral Energy Distributions of Active Galactic Nuclei
• The Spectral Energy Distributions of Active Galactic Nuclei
• Morphology and the Color-Mass Diagram as Clues to Galaxy Evolution at z~1
• PSFGAN: a generative adversarial network system for separating quasar point sources and host galaxy light
• Accretion History of AGN III: Radiative Efficiency and AGN Contribution to Reionization
• GaMPEN: A Machine Learning Framework for Estimating Bayesian Posteriors of Galaxy Morphological Parameters

Cited by in corpus (1)

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