Identifying galaxies, quasars, and stars with machine learning: A new catalogue of classifications for 111 million SDSS sources without spectra

Abstract

We used 3.1 million spectroscopically labelled sources from the Sloan Digital Sky Survey (SDSS) to train an optimised random forest classifier using photometry from the SDSS and the Widefield Infrared Survey Explorer (WISE). We applied this machine learning model to 111 million previously unlabelled sources from the SDSS photometric catalogue which did not have existing spectroscopic observations. Our new catalogue contains 50.4 million galaxies, 2.1 million quasars, and 58.8 million stars. We provide individual classification probabilities for each source, with 6.7 million galaxies (13%), 0.33 million quasars (15%), and 41.3 million stars (70%) having classification probabilities greater than 0.99; and 35.1 million galaxies (70%), 0.72 million quasars (34%), and 54.7 million stars (93%) having classification probabilities greater than 0.9. Precision, Recall, and F1 score were determined as a function of selected features and magnitude error. We investigate the effect of class imbalance on our machine learning model and discuss the implications of transfer learning for populations of sources at fainter magnitudes than the training set. We used a non-linear dimension reduction technique, Uniform Manifold Approximation and Projection (UMAP), in unsupervised, semi-supervised, and fully-supervised schemes to visualise the separation of galaxies, quasars, and stars in a two-dimensional space. When applying this algorithm to the 111 million sources without spectra, it is in strong agreement with the class labels applied by our random forest model.

arXiv commentAccepted for publication in A&A

References in corpus (29)

• Maps of Dust IR Emission for Use in Estimation of Reddening and CMBR Foregrounds
• The Wide-field Infrared Survey Explorer (WISE): Mission Description and Initial On-orbit Performance
• Unified Schemes for Radio-Loud Active Galactic Nuclei
• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• LOFAR: The LOw-Frequency ARray
• Composite Quasar Spectra From the Sloan Digital Sky Survey
• Galaxy Zoo : Morphologies derived from visual inspection of galaxies from the Sloan Digital Sky Survey
• A Unified Model for the Evolution of Galaxies and Quasars
• Galaxy Zoo 1 : Data Release of Morphological Classifications for nearly 900,000 galaxies
• Spectral Classification and Redshift Measurement for the SDSS-III Baryon Oscillation Spectroscopic Survey
• The LOFAR Two-metre Sky Survey - II. First data release
• The Lyman Alpha Forest in the Spectra of QSOs
• The Sloan Digital Sky Survey Quasar Catalog: Fourteenth Data Release
• The Fifteenth Data Release of the Sloan Digital Sky Surveys: First Release of MaNGA Derived Quantities, Data Visualization Tools and Stellar Library
• Detection of Cosmic Magnification with the Sloan Digital Sky Survey
• Photometric redshifts for the SDSS Data Release 12
• Mapping extreme-scale alignments of quasar polarization vectors
• Green Valley Galaxies
• Dark energy and curvature from a future baryonic acoustic oscillation survey using the Lyman-alpha forest
• The meaning of WISE colours - I. The Galaxy and its satellites
• LoTSS/HETDEX: Optical quasars I. Low-frequency radio properties of optically selected quasars
• Exploiting the full potential of photometric quasar surveys: Optimal power spectra through blind mitigation of systematics
• Machine learning Applied to Star-Galaxy-QSO Classification and Stellar Effective Temperature Regression
• Evaluating the optical classification of Fermi BCUs using machine learning
• Catalog of quasars from the Kilo-Degree Survey Data Release 3
• Exploring a new definition of the green valley and its implications
• The Extremely Luminous Quasar Survey in the Pan-STARRS 1 Footprint (PS-ELQS)
• Learning from the machine: interpreting machine learning algorithms for point- and extended- source classification
• Discovery of a New Blue Quasar: SDSS J022218.03-062511.1

Cited by in corpus (43)

• Astronomaly: Personalised Active Anomaly Detection in Astronomical Data
• Practical Galaxy Morphology Tools from Deep Supervised Representation Learning
• A review of unsupervised learning in astronomy
• On Neural Architectures for Astronomical Time-series Classification with Application to Variable Stars
• On the discovery of stars, quasars, and galaxies in the Southern Hemisphere with S-PLUS DR2
• Photometric redshift-aided classification using ensemble learning
• Attention-gating for improved radio galaxy classification
• Machine-learning classification of astronomical sources: estimating F1-score in the absence of ground truth
• Photometric selection and redshifts for quasars in the Kilo-Degree Survey Data Release 4
• Data mining techniques on astronomical spectra data. II : Classification Analysis
• The great Kite in the sky: a LOFAR observation of the radio source in Abell 2626
• Identification of BASS DR3 Sources as Stars, Galaxies and Quasars by XGBoost
• Euclid preparation: XXII. Selection of Quiescent Galaxies from Mock Photometry using Machine Learning
• Beyond the Local Volume. I. Surface Densities of Ultracool Dwarfs in Deep HST/WFC3 Parallel Fields
• Photometric identification of compact galaxies, stars and quasars using multiple neural networks
• Discovery of five new Galactic symbiotic stars in the VPHAS+ survey
• Deep Learning Assessment of galaxy morphology in S-PLUS DataRelease 1
• A new automated tool for the spectral classification of OB stars
• Evolutionary Map of the Universe (EMU):Compact radio sources in the SCORPIO field towards the Galactic plane
• Estimation of Photometric Redshifts. I. Machine Learning Inference for Pan-STARRS1 Galaxies Using Neural Networks
• Wide Area VISTA Extra-galactic Survey (WAVES): Unsupervised star-galaxy separation on the WAVES-Wide photometric input catalogue using UMAP and $\mathrm{HDBSCAN}$
• Improving machine learning-derived photometric redshifts and physical property estimates using unlabelled observations
• J-PLUS DR3: Galaxy-Star-Quasar classification
• VEXAS: VISTA EXtension to Auxiliary Surveys -- Data Release 2: Machine-learning based classification of sources in the Southern Hemisphere
• A Critical Analysis of the Usage of Dimensionality Reduction in Four Domains
• Selection of powerful radio galaxies with machine learning
• An Exploration of How Training Set Composition Bias in Machine Learning Affects Identifying Rare Objects
• Machine learning applications for the study of AGN physical properties using photometric observations
• The Seventeenth Data Release of the Sloan Digital Sky Surveys: Complete Release of MaNGA, MaStar and APOGEE-2 Data
• Identifying type II quasars at intermediate redshift with few-shot learning photometric classification
• Semi-supervised classification of stars, galaxies and quasars using K-means and random-forest approaches
• Machine learning based stellar classification with highly sparse photometry data
• Applying machine learning to Galactic Archaeology: how well can we recover the origin of stars in Milky Way-like galaxies?
• Photometric classification of QSOs from ALHAMBRA survey using random forest
• Euclid preparation. Estimating galaxy physical properties using CatBoost chained regressors with attention
• The Quasar Candidates Catalogs of DESI Legacy Imaging Survey Data Release 9
• Neural Posterior Estimation for Cataloging Astronomical Images with Spatially Varying Backgrounds and Point Spread Functions
• Identifying Radio Active Galactic Nuclei with Machine Learning and Large-Area Surveys
• Identification of Anomalous E+A Galaxies in GAMA Using an Isolation Forest
• E(2)-Equivariant Features in Machine Learning for Morphological Classification of Radio Galaxies
• A machine learning approach to estimate mid-infrared fluxes from WISE data
• The miniJPAS survey quasar selection I: Mock catalogues for classification
• Stellar Dynamical Modeling -- Counting Conserved Quantities