Classifying Unidentified X-ray Sources in the Chandra Source Catalog Using a Multiwavelength Machine-learning Approach

Abstract

The rapid increase in serendipitous X-ray source detections requires the development of novel approaches to efficiently explore the nature of X-ray sources. If even a fraction of these sources could be reliably classified, it would enable population studies for various astrophysical source types on a much larger scale than currently possible. Classification of large numbers of sources from multiple classes characterized by multiple properties (features) must be done automatically and supervised machine learning (ML) seems to provide the only feasible approach. We perform classification of Chandra Source Catalog version 2.0 (CSCv2) sources to explore the potential of the ML approach and identify various biases, limitations, and bottlenecks that present themselves in these kinds of studies. We establish the framework and present a flexible and expandable Python pipeline, which can be used and improved by others. We also release the training data set of 2941 X-ray sources with confidently established classes. In addition to providing probabilistic classifications of 66,369 CSCv2 sources (21% of the entire CSCv2 catalog), we perform several narrower-focused case studies (high-mass X-ray binary candidates and X-ray sources within the extent of the H.E.S.S. TeV sources) to demonstrate some possible applications of our ML approach. We also discuss future possible modifications of the presented pipeline, which are expected to lead to substantial improvements in classification confidences.

Published in ApJ 941, 104 (2022). The data and software used in this paper are available at https://github.com/huiyang-astro/MUWCLASS_CSCv2 and also on Vizier https://cdsarc.cds.unistra.fr/viz-bin/cat/J/ApJ/941/104. The interactive training dataset visualization is available at https://home.gwu.edu/~kargaltsev/XCLASS/

References in corpus (34)

• The UKIRT Infrared Deep Sky Survey (UKIDSS)
• The Zwicky Transient Facility: System Overview, Performance, and First Results
• Estimating distances from parallaxes. V: Geometric and photogeometric distances to 1.47 billion stars in Gaia Early Data Release 3
• The All-Sky Automated Survey for Supernovae (ASAS-SN) Light Curve Server v1.0
• astroquery: An Astronomical Web-Querying Package in Python
• The UKIDSS Galactic Plane Survey
• The XMM-Newton Serendipitous Survey. V. The Second XMM-Newton Serendipitous Source Catalogue
• APOGEE Data and Spectral Analysis from SDSS Data Release 16: Seven Years of Observations Including First Results from APOGEE-South
• Catalogue of high-mass X-ray binaries in the Galaxy ($4^{th}$ edition)
• The unWISE Catalog: Two Billion Infrared Sources from Five Years of WISE Imaging
• A catalogue of low-mass X-ray binaries in the Galaxy, LMC, and SMC (Fourth edition)
• Detection of 16 Gamma-Ray Pulsars Through Blind Frequency Searches Using the Fermi LAT
• The CatWISE2020 Catalog
• The VST Photometric Halpha Survey of the Southern Galactic Plane and Bulge (VPHAS+)
• The Molonglo Galactic Plane Survey (MGPS-2): Compact Source Catalogue
• A Large Catalog of Accurate Distances to Molecular Clouds from PS1 Photometry
• A 3D extinction map of the Northern Galactic Plane based on IPHAS photometry
• Luminosity and Redshift Dependence of the Covering Factor of AGNs viewed with WISE and SDSS
• The onset of X-ray emission in young stellar objects: a Chandra observation of the Serpens star-forming region
• The NuSTAR Serendipitous Survey: The 40 month Catalog and the Properties of the Distant High Energy X-ray Source Population
• An X-ray Search for Compact Central Sources in Supernova Remnants II: Six Large Diameter SNRs
• Automatic classification of time-variable X-ray sources
• Search for Pulsar Wind Nebula Associations of Unidentified TeV Gamma-Ray Sources
• The Galactic LMXB Population and the Galactic Centre Region
• High-resolution Near-infrared Spectroscopic Study of Galactic Supernova Remnants. I. Kinematic Distances
• On the puzzling high-energy pulsations of the energetic radio-quiet $\gamma$-ray pulsar J1813$-$1246
• Is HESS J1912+101 associated with an old Supernova Remnant?
• Hard X-ray luminosity functions of cataclysmic variables: Joint Swift/BAT and Gaia data
• A Comparative Study of Machine Learning Methods for X-ray Binary Classification
• Observations of the $\gamma$-ray pulsar J1932+1916 in X-rays
• Populations of highly variable X-ray sources in the XMM$-$Newton slew survey
• Chandra observations of the HII complex G5.89-0.39 and TeV gamma-ray source HESSJ1800-240B
• "The Goose" Pulsar Wind Nebula of PSR J1016-5857: The Birth of a Plerion
• Studying the $\gamma$-ray pulsar J1932+1916 and its pulsar wind nebula with Chandra

Cited by in corpus (17)

• XRBcats: Galactic Low Mass X-ray Binary Catalogue
• Unsupervised Machine Learning for the Classification of Astrophysical X-ray Sources
• Representation Learning for Time-Domain High-Energy Astrophysics: Discovery of Extragalactic Fast X-ray Transient XRT 200515
• A Multiwavelength Machine-learning Approach to Classifying X-ray Sources in the Fields of Unidentified 4FGL-DR4 sources
• Population of X-ray Sources in the Intermediate-Age Cluster NGC 3532: a Test Bed for Machine-Learning Classification
• A New Mid-Infrared and X-ray Machine Learning Algorithm to Discover Compton-thick AGN
• Automated classification of Chandra X-ray point sources using machine learning methods
• X-ray Sources Classification Using Machine Learning: A Study with EP-WXT Pathfinder LEIA
• Multiwavelength Evidence for Two New Candidate Transitional Millisecond Pulsars in the Sub-luminous Disk State: 4FGL J0639.1--8009 and 4FGL J1824.2+1231
• ALMA detections of circumstellar disks in the giant Hii region M17. Probing the intermediate- to high-mass pre-main-sequence population
• QPOML: A Machine Learning Approach to Detect and Characterize Quasi-Periodic Oscillations in X-ray Binaries
• Multiwavelength Catalog of 10,000 4XMM-DR13 Sources with Known Classifications
• eROSITA (eRASS1) study of the Canis Major overdensity: Developing a multi-wavelength algorithm for classifying faint X-ray sources
• Hyperluminous Supersoft X-Ray Sources in the Chandra Catalog
• Extracting latent representations from X-ray spectra. Classification, regression, and accretion signatures of Chandra sources
• Explainable machine learning classification of \textit{Chandra} X-ray sources: SHAP analysis of multi-wavelength features
• Intriguing nature of AM Her type candidate CXOU J204734.8+300105