Galaxy morphological classification in deep-wide surveys via unsupervised machine learning

Abstract

Galaxy morphology is a fundamental quantity, that is essential not only for the full spectrum of galaxy-evolution studies, but also for a plethora of science in observational cosmology. While a rich literature exists on morphological-classification techniques, the unprecedented data volumes, coupled, in some cases, with the short cadences of forthcoming 'Big-Data' surveys (e.g. from the LSST), present novel challenges for this field. Large data volumes make such datasets intractable for visual inspection (even via massively-distributed platforms like Galaxy Zoo), while short cadences make it difficult to employ techniques like supervised machine-learning, since it may be impractical to repeatedly produce training sets on short timescales. Unsupervised machine learning, which does not require training sets, is ideally suited to the morphological analysis of new and forthcoming surveys. Here, we employ an algorithm that performs clustering of graph representations, in order to group image patches with similar visual properties and objects constructed from those patches, like galaxies. We implement the algorithm on the Hyper-Suprime-Cam Subaru-Strategic-Program Ultra-Deep survey, to autonomously reduce the galaxy population to a small number (160) of 'morphological clusters', populated by galaxies with similar morphologies, which are then benchmarked using visual inspection. The morphological classifications (which we release publicly) exhibit a high level of purity, and reproduce known trends in key galaxy properties as a function of morphological type at z<1 (e.g. stellar-mass functions, rest-frame colours and the position of galaxies on the star-formation main sequence). Our study demonstrates the power of unsupervised machine learning in performing accurate morphological analysis, which will become indispensable in this new era of deep-wide surveys.

Accepted for publication in MNRAS. 19 pages, 12 figures

References in corpus (83)

• Astropy: A Community Python Package for Astronomy
• Stellar population synthesis at the resolution of 2003
• The UKIRT Infrared Deep Sky Survey (UKIDSS)
• SDSS-III: Massive Spectroscopic Surveys of the Distant Universe, the Milky Way Galaxy, and Extra-Solar Planetary Systems
• CANDELS: The Cosmic Assembly Near-infrared Deep Extragalactic Legacy Survey - The Hubble Space Telescope Observations, Imaging Data Products and Mosaics
• Color Separation of Galaxy Types in the Sloan Digital Sky Survey Imaging Data
• SparsePak: A Formatted Fiber Field Unit for The WIYN Telescope Bench Spectrograph. I. Design, Construction, and Calibration
• The Hyper Suprime-Cam SSP Survey: Overview and Survey Design
• Evolution since z = 0.5 of the Morphology-Density relation for Clusters of Galaxies
• Spectroscopic Target Selection for the Sloan Digital Sky Survey: The Luminous Red Galaxy Sample
• The Relationship Between Stellar Light Distributions of Galaxies and their Formation Histories
• A New Non-Parametric Approach to Galaxy Morphological Classification
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Galaxy Zoo 1 : Data Release of Morphological Classifications for nearly 900,000 galaxies
• The Green Valley is a Red Herring: Galaxy Zoo reveals two evolutionary pathways towards quenching of star formation in early- and late-type galaxies
• Galaxy Stellar Mass Assembly between 0.2<z<2 from the S-COSMOS survey
• First Data Release of the Hyper Suprime-Cam Subaru Strategic Program
• Galaxy Stellar Mass Functions from ZFOURGE/CANDELS: An Excess of Low-Mass Galaxies Since z=2 and the Rapid Buildup of Quiescent Galaxies
• The DEEP Groth Strip Survey II. Hubble Space Telescope Structural Parameters of Galaxies in the Groth Strip
• On the Survival and Destruction of Spiral Galaxies in Clusters
• eROSITA Science Book: Mapping the Structure of the Energetic Universe
• The Morphology - Density Relation in z ~ 1 Clusters
• The ACS Nearby Galaxy Survey Treasury VIII. The Global Star Formation Histories of 60 Dwarf Galaxies in the Local Volume
• The Mass Assembly Histories of Galaxies of Various Morphologies in the GOODS Fields
• The VISTA Deep Extragalactic Observations (VIDEO) Survey
• Photometric Redshifts for Hyper Suprime-Cam Subaru Strategic Program Data Release 1
• GALICS I: A hybrid N-body semi-analytic model of hierarchical galaxy formation
• Galaxy And Mass Assembly (GAMA): mass-size relations of z$<$0.1 galaxies subdivided by Sérsic index, colour and morphology
• A catalog of visual-like morphologies in the 5 CANDELS fields using deep-learning
• Connecting the cosmic web to the spin of dark halos: implications for galaxy formation
• Bulge mass is king: The dominant role of the bulge in determining the fraction of passive galaxies in the Sloan Digital Sky Survey
• Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit
• The Structures of Distant Galaxies I: Galaxy Structures and the Merger Rate to z~3 in the Hubble Ultra-Deep Field
• Galaxy Zoo: Disentangling the Environmental Dependence of Morphology and Colour
• The Fundamental Properties of Galaxies and a New Galaxy Classification System
• Impact of ejecta morphology and composition on the electromagnetic signatures of neutron star mergers
• Galaxy Interactions Trigger Rapid Black Hole Growth: an unprecedented view from the Hyper Suprime-Cam Survey
• Photometric redshift estimation via deep learning
• Photometric Redshift with Bayesian Priors on Physical Properties of Galaxies
• The importance of minor-merger-driven star formation and black-hole growth in disk galaxies
• Astrophysically Motivated Bulge-Disk Decompositions of SDSS Galaxies
• The formation and evolution of low-surface-brightness galaxies
• Galaxy And Mass Assembly (GAMA): Stellar mass functions by Hubble type
• Galaxy stellar mass functions of different morphological types in clusters, and their evolution between z=0.8 and z=0
• Galaxy Zoo: Evidence for Diverse Star Formation Histories through the Green Valley
• Optimising Automatic Morphological Classification of Galaxies with Machine Learning and Deep Learning using Dark Energy Survey Imaging
• Stellar mass functions: methods, systematics and results for the local Universe
• Galaxy Zoo: Quantitative Visual Morphological Classifications for 48,000 galaxies from CANDELS
• Galaxies, Human Eyes and Artificial Neural Networks
• The significant contribution of minor mergers to the cosmic star formation budget
• New Image Statistics for Detecting Disturbed Galaxy Morphologies at High Redshift
• Galaxy Zoo: Morphological Classifications for 120,000 Galaxies in HST Legacy Imaging
• An automatic taxonomy of galaxy morphology using unsupervised machine learning
• The morphologies of massive galaxies from z~3 - Witnessing the 2 channels of bulge growth
• The cosmic evolution of the spatially-resolved star formation rate and stellar mass of the CALIFA survey
• VDES J2325-5229 a z=2.7 gravitationally lensed quasar discovered using morphology independent supervised machine learning
• AGN in dwarf galaxies: frequency, triggering processes and the plausibility of AGN feedback
• Star/galaxy separation at faint magnitudes: Application to a simulated Dark Energy Survey
• Identification of Low Surface Brightness Tidal Features in Galaxies Using Convolutional Neural Networks
• The Relation Between Galaxy Morphology and Environment in the Local Universe: An RC3-SDSS Picture
• Integrating human and machine intelligence in galaxy morphology classification tasks
• Peculiar early-type galaxies in the SDSS Stripe82
• Star-Galaxy Classification in Multi-Band Optical Imaging
• Automated Galaxy Morphology: A Fourier Approach
• A Machine Learning Based Morphological Classification of 14,245 Radio AGNs Selected From The Best-Heckman Sample
• Normal black holes in bulge-less galaxies: the largely quiescent, merger-free growth of black holes over cosmic time
• Morpho-z: improving photometric redshifts with galaxy morphology
• Galaxy Formation as a Cosmological Tool. I: The Galaxy Merger History as a Measure of Cosmological Parameters
• Beyond Spheroids and Discs: Classifications of CANDELS Galaxy Structure at 1.4 < z < 2 via Principal Component Analysis
• The Morphological Demographics of galaxies in the ACS Hubble Ultra Deep Parallel Fields
• Return of the features. Efficient feature selection and interpretation for photometric redshifts
• MegaMorph: classifying galaxy morphology using multi-wavelength Sérsic profile fits
• A machine-learning method for identifying multi-wavelength counterparts of submillimeter galaxies: training and testing using AS2UDS and ALESS
• The colour-magnitude relation of Elliptical and Lenticular galaxies in the ESO Distant Cluster Survey
• A Bayesian approach to star-galaxy classification
• The Morphological Transformation of Red Sequence Galaxies in Clusters since $z\sim 1$
• A machine--vision method for automatic classification of stellar halo substructure
• Composite star formation histories of early-type galaxies from minor mergers: prospects for WFC3
• Identifying the progenitors of present-day early-type galaxies in observational surveys: correcting `progenitor bias' using the Horizon-AGN simulation
• Large Synoptic Survey Telescope Galaxies Science Roadmap
• Morpho-Photometric Redshifts
• Classification of pulsars with Dirichlet process Gaussian mixture model
• Impact of Galaxy Mergers on the Colours of Cluster Galaxies

Cited by in corpus (47)

• Introducing the NewHorizon simulation: Galaxy properties with resolved internal dynamics across cosmic time
• Galaxy Zoo DECaLS: Detailed Visual Morphology Measurements from Volunteers and Deep Learning for 314,000 Galaxies
• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Galaxy Merger Rates up to z $\sim$ 3 using a Bayesian Deep Learning Model $-$ A Major-Merger classifier using IllustrisTNG Simulation data
• Identifying Strong Lenses with Unsupervised Machine Learning using Convolutional Autoencoder
• Self-Supervised Representation Learning for Astronomical Images
• Preparing for low surface brightness science with the Vera C. Rubin Observatory: characterisation of tidal features from mock images
• The origin of low-surface-brightness galaxies in the dwarf regime
• Beyond the Hubble Sequence -- Exploring Galaxy Morphology with Unsupervised Machine Learning
• HOLISMOKES. VI. New galaxy-scale strong lens candidates from the HSC-SSP imaging survey
• SDSS IV MaNGA: Visual Morphological and Statistical Characterization of the DR15 sample
• Characterization of Low Surface Brightness structures in annotated deep images
• AstroVaDEr: Astronomical Variational Deep Embedder for Unsupervised Morphological Classification of Galaxies and Synthetic Image Generation
• Machine learning technique for morphological classification of galaxies from the SDSS. I. Photometry-based approach
• A review of unsupervised learning in astronomy
• Machine Learning for Observational Cosmology
• Galaxy Morphology Classification using Neural Ordinary Differential Equations
• The evolution of barred galaxies in the EAGLE simulations
• Spin Parity of Spiral Galaxies II: A catalogue of 80k spiral galaxies using big data from the Subaru Hyper Suprime-Cam Survey and deep learning
• SILVERRUSH X: Machine Learning-Aided Selection of $9318$ LAEs at $z=2.2$, $3.3$, $4.9$, $5.7$, $6.6$, and $7.0$ from the HSC SSP and CHORUS Survey Data
• Nonparametric galaxy morphology from UV to submm wavelengths
• Unsupervised Galaxy Morphological Visual Representation with Deep Contrastive Learning
• The morphological mix of dwarf galaxies in the nearby Universe
• A Robust Study of High-Redshift Galaxies: Unsupervised Machine Learning for Characterising morphology with JWST up to z ~ 8
• Rapid sorting of radio galaxy morphology using Haralick features
• Eigengalaxies: describing galaxy morphology using principal components in image space
• Galaxy merger challenge: A comparison study between machine learning-based detection methods
• Relaxed blue ellipticals: accretion-driven stellar growth is a key evolutionary channel for low mass elliptical galaxies
• Synergies between low- and intermediate-redshift galaxy populations revealed with unsupervised machine learning
• From Images to Features: Unbiased Morphology Classification via Variational Auto-Encoders and Domain Adaptation
• HOLISMOKES -- XI. Evaluation of supervised neural networks for strong-lens searches in ground-based imaging surveys
• The redshift evolution of the S0 fraction for $z<1$ in COSMOS
• Morphological Classification of Galaxies Using SpinalNet
• Low Surface Brightness structures from annotated deep CFHT images: effects of the host galaxy's properties and environment
• Uncovering Tidal Treasures: Automated Classification of Faint Tidal Features in DECaLS Data
• Halo Growth and Merger Rates as a Cosmological Test
• How the spectral energy distribution and galaxy morphology constrain each other, with application to morphological selection using galaxy colours
• A Morphological Study on AGN-host Dwarf Galaxies
• Machine Learning and galaxy morphology: for what purpose?
• Redshift and stellar mass dependence of intrinsic shapes of disc-dominated galaxies from COSMOS observations below $z=1.0$
• The Next Generation Virgo Cluster Survey (NGVS). XL. The Morphological Classification of Virgo Cluster Galaxies
• Morphological Feature Distances Among the Spectral Types of SDSS Galaxies
• Deciphering galaxy images using machine vision -- Combining variational autoencoder and principal component analysis for feature extraction
• A Simulation Driven Deep Learning Approach for Separating Mergers and Star Forming Galaxies: The Formation Histories of Clumpy Galaxies in all the CANDELS Fields
• Domain Adaptor Networks for Hyperspectral Image Recognition
• Timing the last major merger of galaxy clusters with large halo sparsity
• Passive spiral galaxies deeply captured by Subaru Hyper Suprime-Cam