A robust morphological classification of high-redshift galaxies using support vector machines on seeing limited images. I Method description

Abstract

We present a new non-parametric method to quantify morphologies of galaxies based on a particular family of learning machines called support vector machines. The method, that can be seen as a generalization of the classical CAS classification but with an unlimited number of dimensions and non-linear boundaries between decision regions, is fully automated and thus particularly well adapted to large cosmological surveys. The source code is available for download at http://www.lesia.obspm.fr/~huertas/galsvm.html To test the method, we use a seeing limited near-infrared ($K_s$ band, $2,16\mu m$) sample observed with WIRCam at CFHT at a median redshift of $z\sim 0.8$. The machine is trained with a simulated sample built from a local visually classified sample from the SDSS chosen in the high-redshift sample's rest-frame (i band, $0.77\mu m$) and artificially redshifted to match the observing conditions. We use a 12-dimensional volume, including 5 morphological parameters and other caracteristics of galaxies such as luminosity and redshift. We show that a qualitative separation in two main morphological types (late type and early type) can be obtained with an error lower than 20% up to the completeness limit of the sample ($KAB\sim 22$) which is more than 2 times better that what would be obtained with a classical C/A classification on the same sample and indeed comparable to space data. The method is optimized to solve a specific problem, offering an objective and automated estimate of errors that enables a straightforward comparison with other surveys.

11 pages, 7 figures, 3 tables. Submitted to A&A. High resolution images are available on request

References in corpus (18)

• Detailed Structural Decomposition of Galaxy Images
• Hierarchical Galaxy Formation
• Accurate photometric redshifts for the CFHT Legacy Survey calibrated using the VIMOS VLT Deep Survey
• The Star Formation History of Field Galaxies
• The CANADA-FRANCE REDSHIFT SURVEY XIII: The luminosity density and star-formation history of the Universe to z ~ 1
• A New Non-Parametric Approach to Galaxy Morphological Classification
• A Direct Measurement of Major Galaxy Mergers at z < 3
• The Asymmetry of Galaxies: Physical Morphology for Nearby and High Redshift Galaxies
• The COMBO-17 Survey: Evolution of the Galaxy Luminosity Function from 25,000 Galaxies with 0.2<z<1.2
• The DEEP Groth Strip Survey II. Hubble Space Telescope Structural Parameters of Galaxies in the Groth Strip
• A New Approach to Galaxy Morphology: I. Analysis of the Sloan Digital Sky Survey Early Data Release
• Evolution of the Hubble Sequence in Hierarchical Models for Galaxy Formation
• Structural and Photometric Classification of Galaxies - I. Calibration Based on a Nearby Galaxy Sample
• HST imaging of CFRS and LDSS galaxies - I: Morphological Properties
• The VIMOS VLT Deep Survey - Evolution of the luminosity functions by galaxy type up to z=1.5 from first epoch data
• Galaxy luminosity function per morphological type up to z=1.2
• Optical-Infrared Colour Distribution of a Statistically-Complete Sample of Faint Field Spheroidal Galaxies
• The Morphological Demographics of galaxies in the ACS Hubble Ultra Deep Parallel Fields

Cited by in corpus (97)

• Galaxy Zoo 2: detailed morphological classifications for 304,122 galaxies from the Sloan Digital Sky Survey
• Data Mining and Machine Learning in Astronomy
• A Classical Morphological Analysis of Galaxies in the Spitzer Survey of Stellar Structure in Galaxies (S4G)
• A catalog of visual-like morphologies in the 5 CANDELS fields using deep-learning
• Revisiting the Hubble sequence in the SDSS DR7 spectroscopic sample: a publicly available bayesian automated classification
• The zCOSMOS Redshift Survey: the role of environment and stellar mass in shaping the rise of the morphology-density relation from z~1
• Early type galaxies have been the predominant morphological class for massive galaxies since only z~1
• The evolution of the mass-size relation for early type galaxies from z~1 to the present: dependence on environment, mass-range and detailed morphology
• Gemini multi-conjugate adaptive optics system review II: Commissioning, operation and overall performance
• Optimising Automatic Morphological Classification of Galaxies with Machine Learning and Deep Learning using Dark Energy Survey Imaging
• Galaxy Zoo: Quantitative Visual Morphological Classifications for 48,000 galaxies from CANDELS
• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Physical Properties of Spectroscopically-Confirmed Galaxies at z >= 6. II. Morphology of the Rest-Frame UV Continuum and Lyman-alpha Emission
• QSO Selection Algorithm Using Time Variability and Machine Learning: Selection of 1,620 QSO Candidates from MACHO LMC Database
• Larger sizes of massive quiescent early-type galaxies in clusters than in the field at 0.8 < z < 1.5
• An automatic taxonomy of galaxy morphology using unsupervised machine learning
• Automatic unsupervised classification of all SDSS/DR7 galaxy spectra
• Morphology of galaxies in the WINGS clusters
• The nature and nurture of bars and disks
• Ganalyzer: A tool for automatic galaxy image analysis
• Catalog of Visually Classified Galaxies in the Local ($z\sim 0.01$) Universe
• What shapes a galaxy? - Unraveling the role of mass, environment and star formation in forming galactic structure
• Integrating human and machine intelligence in galaxy morphology classification tasks
• Active Learning to Overcome Sample Selection Bias: Application to Photometric Variable Star Classification
• GalaxyNet: Connecting galaxies and dark matter haloes with deep neural networks and reinforcement learning in large volumes
• Early-type galaxies at z = 1.3. I. The Lynx supercluster: cluster and groups at z=1.3. Morphology and color-magnitude relation
• The merger rates and sizes of galaxies across the peak epoch of star formation from the HiZELS survey
• Galaxy Morphological Classification Catalogue of the Dark Energy Survey Year 3 data with Convolutional Neural Networks
• AGN-Host Galaxy Connection: Morphology and Colours of X-ray Selected AGN at z < 2
• Star formation of far-IR AGN and non-AGN galaxies in the green valley: possible implication of AGN positive feedback
• Evolution of blue E/S0 galaxies from z~1: merger remnants or disk rebuilding galaxies?
• The VIMOS Public Extragalactic Redshift Survey (VIPERS). A Support Vector Machine classification of galaxies, stars and AGNs
• Machine learning Applied to Star-Galaxy-QSO Classification and Stellar Effective Temperature Regression
• Machine-learning identification of galaxies in the WISExSuperCOSMOS all-sky catalogue
• The Extremely Luminous Quasar Survey (ELQS) in the SDSS footprint I.: Infrared Based Candidate Selection
• The minor role of gas-rich major mergers in the rise of intermediate-mass early types at z <~ 1
• The ALHAMBRA survey: reliable morphological catalogue of 22,051 early- and late-type galaxies
• Support Vector Machine classification of strong gravitational lenses
• Multivariate Approaches to Classification in Extragalactic Astronomy
• The ILIUM forward modelling algorithm for multivariate parameter estimation and its application to derive stellar parameters from Gaia spectrophotometry
• A robust morphological classification of high-redshift galaxies using support vector machines on seeing limited images. II. Quantifying morphological k-correction in the COSMOS field at 1<z<2: Ks band vs. I band
• Extreme emission-line galaxies out to z$\sim$1 in zCOSMOS. I. Sample and characterization of global properties
• Automatic Classification of Galaxy Morphology: a rotationally invariant supervised machine learning method based on the UML-dataset
• Quantifying Non-parametric Structure of High-redshift Galaxies with Deep Learning
• Predicting star formation properties of galaxies using deep learning
• A catalogue of structural and morphological measurements for DES Y1
• Classifying structures in the ISM with Support Vector Machines: the G16.05-0.57 supernova remnant
• Euclid preparation XXVI. The Euclid Morphology Challenge. Towards structural parameters for billions of galaxies
• Machine learning detects multiplicity of the first stars in stellar archaeology data
• The role of environment in the morphological transformation of galaxies in 9 intermediate redshift clusters
• Stellar populations of galaxies in the ALHAMBRA survey up to $z\sim 1$. I. MUFFIT: A Multi-Filter Fitting code for stellar population diagnostics
• The impact from survey depth and resolution on the morphological classification of galaxies
• Photometric Classification of quasars from RCS-2 using Random Forest
• Galaxy classification: deep learning on the OTELO and COSMOS databases
• The Morphological Transformation of Red Sequence Galaxies in Clusters since $z\sim 1$
• Star-galaxy separation in the AKARI NEP Deep Field
• Machine Learning Classification of Gaia Data Release 2
• Multiband galaxy morphologies for CLASH: a convolutional neural network transferred from CANDELS
• Pushing the limits of the Gaia space mission by analyzing galaxy morphology
• Galaxy size trends as a consequence of cosmology
• Searching for hot subdwarf stars from the LAMOST spectra. III. classifying the hot subdwarf stars from LAMOST DR4 using deep learning method
• Relationship between Hubble type and spectroscopic class in local galaxies
• ASTErIsM - Application of topometric clustering algorithms in automatic galaxy detection and classification
• The Tully-Fisher relation in dense groups at $z\sim 0.7$ in the MAGIC survey
• The Impact of Redshift on Galaxy Morphometric Classification: case studies for SDSS, DES, LSST and HST with Morfometryka
• Star formation in far-IR AGN and non-AGN galaxies in the green valley. II. Morphological analysis
• Large-scale structures in the $\Lambda$CDM Universe: network analysis and machine learning
• Reproducible $k$-means clustering in galaxy feature data from the GAMA survey
• A Virtual Observatory Census to Address Dwarfs Origins. AVOCADO - I. Science goals, sample selection and analysis tools
• Effect of richness on AGN and star formation activities in SDSS galaxy groups
• Deep Learning Assessment of galaxy morphology in S-PLUS DataRelease 1
• The OTELO survey as a morphological probe. Last ten Gyr of galaxy evolution. The mass--size relation up to z=2
• Soft clustering analysis of galaxy morphologies: A worked example with SDSS
• On the Anticorrelation Between Galaxy Light Concentration and X-ray-to-Optical Flux Ratio
• Reliable Photometric Membership (RPM) of Galaxies in Clusters. I. A Machine Learning Method and its Performance in the Local Universe
• A morphological study of galaxies in ZwCl0024+1652, a galaxy cluster at redshift z $\sim$ 0.4
• Lessons Learned from the Two Largest Galaxy Morphological Classification Catalogues built by Convolutional Neural Networks
• Non-Parametric Cell-Based Photometric Proxies for Galaxy Morphology: Methodology and Application to the Morphologically-Defined Star Formation -- Stellar Mass Relation of Spiral Galaxies in the Local Universe
• Clustering of the AKARI NEP Deep Field 24 $\mu$m selected galaxies
• Dissecting the morphological and spectroscopic properties of galaxies in the local Universe: I. Elliptical galaxies
• Advanced Classification of Hot Subdwarf Binaries Using Artificial Intelligence Techniques and Gaia DR3 data
• The Morphological Transformation of Red-Sequence Galaxies in the Distant Cluster XMMU J1229+0151
• A machine learning approach for identifying the counterparts of submillimetre galaxies and applications to the GOODS-North field
• Bayesian bulge-disc decomposition of galaxy images
• Multi-wavelength landscape of the young galaxy cluster RXJ1257.2+4738 at z=0.866. II. Morphological properties
• A post-merger enhancement only in star-forming Type 2 Seyfert galaxies: the deep learning view
• Classifying galaxies according to their HI content
• Searching for Barium Stars from the LAMOST Spectra Using the Machine Learning Method: I
• Morphological study of a sample of dwarf tidal galaxies using the C-A plane
• Automatic morphological classification of galaxies: convolutional autoencoder and bagging-based multiclustering model
• X-ray luminosity functions of different morphological and X-ray type AGN populations
• Non-Sequential Neural Network for Simultaneous, Consistent Classification and Photometric Redshifts of OTELO Galaxies
• The Next Generation Virgo Cluster Survey (NGVS). XL. The Morphological Classification of Virgo Cluster Galaxies
• GLACE survey: galaxy activity in ZwCl0024+1652 cluster from strong optical emission lines
• Effect of AGN on the morphological properties of their host galaxies in the local Universe
• AVOCADO: A Virtual Observatory Census to Address Dwarfs Origins
• The Next Generation Fornax Survey (NGFS).VIII. A Support Vector Machine Approach for Disentangling Globular Clusters from other Sources