Improving galaxy morphologies for SDSS with Deep Learning

Abstract

We present a morphological catalogue for $\sim$ 670,000 galaxies in the Sloan Digital Sky Survey in two flavours: T-Type, related to the Hubble sequence, and Galaxy Zoo 2 (GZ2 hereafter) classification scheme. By combining accurate existing visual classification catalogues with machine learning, we provide the largest and most accurate morphological catalogue up to date. The classifications are obtained with Deep Learning algorithms using Convolutional Neural Networks (CNNs). We use two visual classification catalogues, GZ2 and Nair & Abraham (2010), for training CNNs with colour images in order to obtain T-Types and a series of GZ2 type questions (disk/features, edge-on galaxies, bar signature, bulge prominence, roundness and mergers). We also provide an additional probability enabling a separation between pure elliptical (E) from S0, where the T-Type model is not so efficient. For the T-Type, our results show smaller offset and scatter than previous models trained with support vector machines. For the GZ2 type questions, our models have large accuracy (> 97\%), precision and recall values (> 90\%) when applied to a test sample with the same characteristics as the one used for training. The catalogue is publicly released with the paper.

18 pages, 21 figures; Accepted for publication in MNRAS

References in corpus (7)

• Overview of the SDSS-IV MaNGA Survey: Mapping Nearby Galaxies at Apache Point Observatory
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• A catalogue of 2D photometric decompositions in the SDSS-DR7 spectroscopic main galaxy sample: preferred models and systematics
• Galaxy Zoo: comparing the demographics of spiral arm number and a new method for correcting redshift bias
• The Euclid mission design
• Comparing PyMorph and SDSS photometry. I. Background sky and model fitting effects
• Improving galaxy morphology with machine learning

Cited by in corpus (229)

• The Fifteenth Data Release of the Sloan Digital Sky Surveys: First Release of MaNGA Derived Quantities, Data Visualization Tools and Stellar Library
• Intelligent Computing: The Latest Advances, Challenges and Future
• Galaxy Zoo DECaLS: Detailed Visual Morphology Measurements from Volunteers and Deep Learning for 314,000 Galaxies
• Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active Learning
• Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
• SDSS-IV DR17: Final Release of MaNGA PyMorph Photometric and Deep Learning Morphological Catalogs
• Optimising Automatic Morphological Classification of Galaxies with Machine Learning and Deep Learning using Dark Energy Survey Imaging
• Deep learning predictions of galaxy merger stage and the importance of observational realism
• Hidden AGN in dwarf galaxies revealed by MaNGA: light echoes, off-nuclear wanderers, and a new broad-line AGN
• SDSS-IV MaNGA PyMorph Photometric and Deep Learning Morphological Catalogs and implications for bulge properties and stellar angular momentum
• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• The Planck clusters in the LOFAR sky. I. LoTSS-DR2: new detections and sample overview
• Machine and Deep Learning Applied to Galaxy Morphology -- A Comparative Study
• The Hubble Sequence at $z\sim 0$ in the IllustrisTNG simulation with deep learning
• Transfer learning for galaxy morphology from one survey to another
• A Deep Learning Approach to Galaxy Cluster X-ray Masses
• Deep Learning Identifies High-z Galaxies in a Central Blue Nugget Phase in a Characteristic Mass Range
• Enabling real-time multi-messenger astrophysics discoveries with deep learning
• Convolutional neural network identification of galaxy post-mergers in UNIONS using IllustrisTNG
• Identifying Strong Lenses with Unsupervised Machine Learning using Convolutional Autoencoder
• Self-Supervised Representation Learning for Astronomical Images
• Applications and Techniques for Fast Machine Learning in Science
• A catalog of polychromatic bulge-disk decompositions of ~ 17.600 galaxies in CANDELS
• Hidden depths in the local Universe: The Stellar Stream Legacy Survey
• Identification of Low Surface Brightness Tidal Features in Galaxies Using Convolutional Neural Networks
• Morphological classification of radio galaxies: Capsule Networks versus Convolutional Neural Networks
• Practical Galaxy Morphology Tools from Deep Supervised Representation Learning
• Beyond the Hubble Sequence -- Exploring Galaxy Morphology with Unsupervised Machine Learning
• Galaxy Morphological Classification Catalogue of the Dark Energy Survey Year 3 data with Convolutional Neural Networks
• Photometry of high-redshift blended galaxies using deep learning
• Detecting outliers in astronomical images with deep generative networks
• Morphological classification of galaxies with deep learning: comparing 3-way and 4-way CNNs
• Star formation rates and stellar masses from machine learning
• SDSS IV MaNGA: Visual Morphological and Statistical Characterization of the DR15 sample
• Characterization of Low Surface Brightness structures in annotated deep images
• SDSS-IV MaNGA: 3D spin alignment of spiral and S0 galaxies
• PELICAN: deeP architecturE for the LIght Curve ANalysis
• Classifying the unknown: discovering novel gravitational-wave detector glitches using similarity learning
• Galaxy properties as revealed by MaNGA. I. Constraints on Initial Mass Function and M${}_{\ast }$/L gradients in ellipticals
• Characterizing the local relation between star formation rate and gas-phase metallicity in MaNGA spiral galaxies
• SDSS-IV MaNGA: the indispensable role of bars in enhancing the central star formation of low-$z$ galaxies
• Gas Content Regulates the Lifecycle of Star Formation and Black Hole Accretion in Galaxies
• On Neural Architectures for Astronomical Time-series Classification with Application to Variable Stars
• The distribution of star formation in galactic bars as seen with H$\alpha$ and stacked GALEX UV imaging
• Pushing automated morphological classifications to their limits with the Dark Energy Survey
• Forging new worlds: high-resolution synthetic galaxies with chained generative adversarial networks
• Galaxies in voids assemble their stars slowly
• Machine-learning classification of astronomical sources: estimating F1-score in the absence of ground truth
• Star formation characteristics of CNN-identified post-mergers in the Ultraviolet Near Infrared Optical Northern Survey (UNIONS)
• Dirt-cheap Gas Scaling Relations: Using Dust Absorption, Metallicity and Galaxy Size to Predict Gas Masses for Large Samples of Galaxies
• Galaxy sizes and the galaxy-halo connection -- I: the remarkable tightness of the size distributions
• Galaxy properties as revealed by MaNGA II. Differences in stellar populations of slow and fast rotator ellipticals and dependence on environment
• The Role of Groups in Galaxy Evolution: compelling evidence of pre-processing out to the turnaround radius of clusters
• Revisiting the role of bars in AGN fuelling with propensity score sample matching
• 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
• xGASS: The Impact of Photometric Bulges on the Scatter of HI Scaling Relations
• Galaxy properties as revealed by MaNGA. III. Kinematic profiles and stellar population gradients in S0s
• The effect of cosmic web filaments on galaxy evolution
• SDSS-IV MaNGA: drivers of stellar metallicity in nearby galaxies
• A Comprehensive Examination of the Optical Morphologies of 719 Isolated Galaxies in the AMIGA Sample
• The evolution of barred galaxies in the EAGLE simulations
• Stellar mass-metallicity relation throughout the large-scale structure of the Universe: CAVITY mother sample
• The dependency of Type Ia Supernova parameters on host galaxy morphology for the Pantheon cosmological sample
• Identification of tidal features in deep optical galaxy images with Convolutional Neural Networks
• SDSS-IV MaNGA: Stellar M/L gradients and the M/L-colour relation in galaxies
• A Method to Distinguish Quiescent and Dusty Star-forming Galaxies with Machine Learning
• xGASS: The Role of Bulges Along and Across the Local Star-Forming Main Sequence
• Rotation Curves of Galaxies and Their Dependence on Morphology and Stellar Mass
• Explaining deep learning of galaxy morphology with saliency mapping
• The Stellar Mass Fundamental Plane: The virial relation and a very thin plane for slow-rotators
• 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
• AGN in post-mergers from the Ultraviolet Near Infrared Optical Northern Survey
• 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
• From Blue Cloud to Red Sequence: Evidence of Morphological Transition Prior to Star Formation Quenching
• The dark side of galaxy stellar populations I: The stellar-to-halo mass relation and the velocity dispersion - halo mass relation
• An IFU View of the Active Galactic Nuclei in MaNGA Galaxy Pairs
• Galaxy classification: deep learning on the OTELO and COSMOS databases
• StarcNet: Machine Learning for Star Cluster Identification
• Deep Learning for Cardiologist-level Myocardial Infarction Detection in Electrocardiograms
• Double-peak emission line galaxies in the SDSS catalogue. A minor merger sequence
• The cosmic evolution of the stellar mass$-$velocity dispersion relation of early-type galaxies
• Capturing the physics of MaNGA galaxies with self-supervised Machine Learning
• Euclid preparation: XXII. Selection of Quiescent Galaxies from Mock Photometry using Machine Learning
• Active deep learning method for the discovery of objects of interest in large spectroscopic surveys
• A Robust Study of High-Redshift Galaxies: Unsupervised Machine Learning for Characterising morphology with JWST up to z ~ 8
• Prospects for Recovering Galaxy Intrinsic Shapes from Projected Quantities
• Star Formation and AGN Feedback in the Local Universe: Combining LOFAR and MaNGA
• Deriving star cluster parameters with convolutional neural networks. I. Age, mass, and size
• Comparison of Observed Galaxy Properties with Semianalytic Model Predictions using Machine Learning
• Estimating dust attenuation from galactic spectra. II. Stellar and gas attenuation in star-forming and diffuse ionized gas regions in MaNGA
• 21st Century Statistical and Computational Challenges in Astrophysics
• Building robust AGN mock catalogs to unveil black hole evolution and for survey planning
• Galaxy morphology prediction using capsule networks
• Multiband galaxy morphologies for CLASH: a convolutional neural network transferred from CANDELS
• J-PAS: Measuring emission lines with artificial neural networks
• Photometric identification of compact galaxies, stars and quasars using multiple neural networks
• MaNGA galaxy properties -- I. An extensive optical, mid-infrared photometric, and environmental catalogue
• A Virgo Environmental Survey Tracing Ionised Gas Emission (VESTIGE).XII. Ionised gas emission in the inner regions of lenticular galaxies
• The CAVITY project. The spatially resolved stellar population properties of galaxies in voids
• Wolf-Rayet galaxies in SDSS-IV MaNGA. I. Catalog construction and sample properties
• Galaxy morphoto-Z with neural Networks (GaZNets). I. Optimized accuracy and outlier fraction from Imaging and Photometry
• Galaxy shape measurement with convolutional neural networks
• BUDDI-MaNGA II: The Star-Formation Histories of Bulges and Discs of S0s
• Shaping physical properties of galaxy subtypes in the VIPERS survey: environment matters
• Investigating the Projected Phase Space of Gaussian and Non-Gaussian Clusters
• The local universe in the era of large surveys. I. Spectral classification of S0 galaxies
• The galaxy HI-(sub)halo connection and the HI spatial clustering of local galaxies
• Euclid preparation. XLIII. Measuring detailed galaxy morphologies for Euclid with machine learning
• Satellite quenching and morphological transformation of galaxies in groups and clusters
• The evolution of compact massive quiescent and starforming galaxies derived from the $R_e-R_h$ and $M_{\mathrm{star}}-M_h$ relations
• MaNGA galaxy properties -- II. A detailed comparison of observed and simulated spiral galaxy scaling relations
• Galaxy merger challenge: A comparison study between machine learning-based detection methods
• Enabling Unsupervised Discovery in Astronomical Images through Self-Supervised Representations
• Two interacting galaxies hiding as one, revealed by MaNGA
• CANDELS Meets GSWLC: Evolution of the Relationship Between Morphology and Star Formation Since z = 2
• Denoising Diffusion Probabilistic Models to Predict the Density of Molecular Clouds
• Self-supervised Learning with Physics-aware Neural Networks I: Galaxy Model Fitting
• Deep Learning Assessment of galaxy morphology in S-PLUS DataRelease 1
• The Activation of Galactic Nuclei and Their Accretion Rates are Linked to the Star Formation Rates and Bulge-types of Their Host Galaxies
• Quantifying the fine structures of disk galaxies with deep learning:Segmentation of spiral arms in different Hubble types
• Euclid Preparation XXXIII. Characterization of convolutional neural networks for the identification of galaxy-galaxy strong lensing events
• The origin of double-peak emission-line galaxies: rotating discs, bars or galaxy mergers?
• LeMoN: Lens Modelling with Neural networks -- I. Automated modelling of strong gravitational lenses with Bayesian Neural Networks
• Examining transitional galaxies to understand the role of clusters and their dynamical status in galaxy quenching
• The Systematics of Galaxy Morphology in the Comprehensive de Vaucouleurs revised Hubble-Sandage Classification System: Application to the EFIGI Sample
• Probing gaseous galactic halos through the rotational kSZ effect
• Exploring Galaxy Evolution Time-Scales in Clusters: Insights from the Projected Phase Space
• Morphology-assisted galaxy mass-to-light predictions using deep learning
• Classifying the formation processes of S0 galaxies using Convolutional Neural Networks
• The Puzzling Origin of Massive Compact Galaxies in MaNGA
• Unveiling Galaxy Morphology through an Unsupervised-Supervised Hybrid Approach
• A morphological study of galaxies in ZwCl0024+1652, a galaxy cluster at redshift z $\sim$ 0.4
• New Constraints on the Origin of Surface Brightness Profile Breaks of Disk Galaxies from MaNGA
• The Most Predictive Physical Properties for the Stellar Population Radial Profiles of Nearby Galaxies
• Improving machine learning-derived photometric redshifts and physical property estimates using unlabelled observations
• The weak dependence of velocity dispersion on disk fractions, mass-to-light ratio and redshift: Implications for galaxy and black hole evolution
• Diagnostic diagrams for ram-pressure stripped candidates
• Lessons Learned from the Two Largest Galaxy Morphological Classification Catalogues built by Convolutional Neural Networks
• The Velocity Map Asymmetry of Ionized Gas in MaNGA. I. The Catalog and General Properties
• Classification and Evolution of Galaxies According to the Dynamical State of Host Clusters and Galaxy Luminosities
• The miniJPAS survey quasar selection III: Classification with artificial neural networks and hybridisation
• Impact of Galaxy Mergers on Stellar Population Profiles of Early-type Galaxies
• The redshift evolution of the S0 fraction for $z<1$ in COSMOS
• Morphologies of galaxies within voids
• Ultimate Merging at z~0.1
• Galaxy mass-size segregation in the cosmic web from the CAVITY parent sample
• A Comparison of Deep Learning Architectures for Optical Galaxy Morphology Classification
• Morphological Classification of Galaxies Using SpinalNet
• Using angular momentum maps to detect kinematically distinct galactic components
• SDSS-IV MaNGA: When is morphology imprinted on galaxies?
• The influence of Hickson-like compact group environment on galaxy luminosities
• Uncovering Tidal Treasures: Automated Classification of Faint Tidal Features in DECaLS Data
• SDSS-IV MaNGA: Unveiling Galaxy Interaction by Merger Stages with Machine Learning
• Identifying Exoplanets with Deep Learning. IV. Removing Stellar Activity Signals from Radial Velocity Measurements Using Neural Networks
• The co-evolution of strong AGN and central galaxies in different environments
• Machine learning technique for morphological classification of galaxies from SDSS. II. The image-based morphological catalogs of galaxies at 0.02<z<0.1
• The origin of star-forming rings in S0 galaxies
• Size, shade or shape? The contribution of galaxies of different types to the star-formation history of the Universe from SDSS-IV MaNGA
• Machine learning technique for morphological classification of galaxies from the SDSS. III. Image-based inference of detailed features
• Search for the edge-on galaxies using an artificial neural network
• BUDDI-MaNGA I: A statistical sample of cleanly decomposed bulge and disc spectra
• The local Universe in the era of large surveys -- II. Multi-wavelength characterisation of activity in nearby S0 galaxies
• Investigation of stellar magnetic activity using variational autoencoder based on low-resolution spectroscopic survey
• J-PLUS: the impact of bars on quenching time-scales in nearby green valley disc galaxies
• The HI and stellar mass bivariate distribution of centrals and satellites for all, late- and early-type local galaxies
• A machine learning approach for identifying the counterparts of submillimetre galaxies and applications to the GOODS-North field
• Constraining the three-dimensional orbits of galaxies under ram pressure stripping with convolutional neural networks
• Automated Detection of Galactic Rings from SDSS Images
• The properties and environment of very young galaxies in the local Universe
• The Classification of Optical Galaxy Morphology Using Unsupervised Learning Techniques
• A post-merger enhancement only in star-forming Type 2 Seyfert galaxies: the deep learning view
• Visualizing the Hidden Features of Galaxy Morphology with Machine Learning
• The size function of massive satellites from the $R_e-R_h$ and $M_{star}-M_h$ relations: constraining the role of environment
• Identifying type II quasars at intermediate redshift with few-shot learning photometric classification
• Galaxy pairs in The Three Hundred simulations II: studying bound ones and identifying them via machine learning
• Understanding the role of morphology and environment on the dynamical evolution of isolated galaxy triplets
• SDSS-IV MaNGA: the physical origin of off-galaxy H$\alpha$ blobs in the local Universe
• Galaxy Morphological Classification with Manifold Learning
• Central star formation in double-peak gas rich radio galaxies
• Structure and Kinematics of Star-forming Elliptical Galaxies in SDSS-MaNGA
• Galaxy Manifold: Characterizing and understanding galaxies with two parameters
• Identification of ram pressure stripping features in galaxies using citizen science
• Sub-galactic scaling relations with T${}_{\mathrm{e}}$-based metallicity of low metallicity regions in galaxies: metal-poor gas inflow may have important effects?
• Applying machine learning to Galactic Archaeology: how well can we recover the origin of stars in Milky Way-like galaxies?
• A MaNGA view of isolated galaxy mergers in the star-forming Main Sequence
• Dependence of the ratio of total to visible mass on observable properties of SDSS MaNGA galaxies
• Using machine learning to study the kinematics of cold gas in galaxies
• Using Machine Learning to Determine Morphologies of $z<1$ AGN Host Galaxies in the Hyper Suprime-Cam Wide Survey
• YOLO-CL cluster detection in the Rubin/LSST DC2 simulation
• A self-supervised, physics-aware, Bayesian neural network architecture for modelling galaxy emission-line kinematics
• The MOSDEF Survey: Probing Resolved Stellar Populations at $z\sim 2$ Using a New Bayesian-defined Morphology Metric Called Patchiness
• Star formation histories of massive red spiral galaxies in the local universe
• A simple equivariant machine learning method for dynamics based on scalars
• Mock Observations: Morphological Analysis of Galaxies in TNG100 Simulations
• AGN -- host galaxy photometric decomposition using a fast, accurate and precise deep learning approach
• Bayesian and Convolutional Networks for Hierarchical Morphological Classification of Galaxies
• Sampling for Deep Learning Model Diagnosis (Technical Report)
• COSMOS2025: Machine Learning Classification of Early- and Late-type Galaxies at 0 < z < 3
• Late growth of early-type galaxies in low-z massive clusters
• Modelling the photometric and morphological evolution of disc galaxies in the cluster environment
• Galaxies OBserved as Low-luminosity Identified Nebulae (GOBLIN): a catalog of 43,000 high-probability dwarf galaxy candidates in the UNIONS survey
• Euclid preparation. Estimating galaxy physical properties using CatBoost chained regressors with attention
• Automated galaxy sizes in Euclid images using the Segment Anything Model
• Automatic Machine Learning Framework to Study Morphological Parameters of AGN Host Galaxies within $z<1.4$ in the Hyper Supreme-Cam Wide Survey
• A machine learning approach to assessing the presence of substructure in quasar host galaxies using the Hyper Suprime-Cam Subaru Strategic Program
• An analytical model to kinematically identify thin discs in MaNGA galaxies
• Neutron star envelopes with machine learning: a single-hidden-layer neural network application
• The distribution of lenticular galaxies in the phase space of present-day galaxy cluster regions
• PSF-based Analysis for Detecting Unresolved Wide Binaries
• J-PAS: A Neural Network Approach to Single Stellar Population Characterization
• Non-Sequential Neural Network for Simultaneous, Consistent Classification and Photometric Redshifts of OTELO Galaxies
• A phylogenetic analysis of galaxies in the Coma Cluster and the field: a new approach to galaxy evolution
• The Next Generation Virgo Cluster Survey (NGVS). XL. The Morphological Classification of Virgo Cluster Galaxies
• Modeling with the Crowd: Optimizing the Human-Machine Partnership with Zooniverse
• The CAVITY project. The spatially resolved SFR of galaxies in voids
• Merger fraction in galaxy groups and clusters at z < 0.2: A non-parametric morphological study with Subaru Hyper Suprime-Cam
• Galaxy Morphological Classification with Efficient Vision Transformer
• Spatially Resolved Properties of Supernova Host Galaxies in SDSS-IV MaNGA
• Star-forming S0 Galaxies in SDSS-MaNGA: fading spirals or rejuvenated S0s?
• Effect of AGN on the morphological properties of their host galaxies in the local Universe
• Quantifying the Poor Purity and Completeness of Morphological Samples Selected by Galaxy Colour
• Identifying AGN host galaxies by Machine Learning with HSC+WISE
• Testing the key role of the stellar mass-halo mass relation in galaxy merger rates and morphologies via DECODE, a novel Discrete statistical sEmi-empiriCal mODEl
• Photometric Redshift Estimation with Convolutional Neural Networks and Galaxy Images: A Case Study of Resolving Biases in Data-Driven Methods
• Deep Learning generated observations of galaxy clusters from dark-matter-only simulations
• The Kormendy relation of cluster galaxies in PPS regions
• A machine learning approach to estimating HI deficiency in galaxies
• Morphologies for DECaLS Galaxies through a combination of non-parametric indices and machine learning methods: A comprehensive catalog using the Galaxy Morphology Extractor (galmex) code