Unsupervised Machine Learning for the Classification of Astrophysical X-ray Sources

Abstract

The automatic classification of X-ray detections is a necessary step in extracting astrophysical information from compiled catalogs of astrophysical sources. Classification is useful for the study of individual objects, statistics for population studies, as well as for anomaly detection, i.e., the identification of new unexplored phenomena, including transients and spectrally extreme sources. Despite the importance of this task, classification remains challenging in X-ray astronomy due to the lack of optical counterparts and representative training sets. We develop an alternative methodology that employs an unsupervised machine learning approach to provide probabilistic classes to Chandra Source Catalog sources with a limited number of labeled sources, and without ancillary information from optical and infrared catalogs. We provide a catalog of probabilistic classes for 8,756 sources, comprising a total of 14,507 detections, and demonstrate the success of the method at identifying emission from young stellar objects, as well as distinguishing between small-scale and large-scale compact accretors with a significant level of confidence. We investigate the consistency between the distribution of features among classified objects and well-established astrophysical hypotheses such as the unified AGN model. This provides interpretability to the probabilistic classifier. Code and tables are available publicly through GitHub. We provide a web playground for readers to explore our final classification at https://umlcaxs-playground.streamlit.app.

arXiv comment21 pages, 11 figures. Accepted in MNRAS

References in corpus (38)

• Array Programming with NumPy
• X-ray Properties of Black-Hole Binaries
• The SIMBAD astronomical database
• The eROSITA X-ray telescope on SRG
• Active Galactic Nuclei: what's in a name?
• The Chandra Source Catalog
• The distribution of absorbing column densities among Seyfert 2 galaxies
• The Origin of T Tauri X-ray Emission: New Insights from the Chandra Orion Ultradeep Project
• eROSITA Science Book: Mapping the Structure of the Energetic Universe
• ASCA observations of type-2 Seyfert galaxies: II. The Importance of X-ray Scattering and Reflection
• Testing Comptonization models using BeppoSAX observations of Seyfert 1 galaxies
• Long-term variability of AGN at hard X-rays
• Classification of X-ray Sources in the XMM-Newton Serendipitous Source Catalog
• Luminosity and Redshift Dependence of the Covering Factor of AGNs viewed with WISE and SDSS
• Unsupervised star, galaxy, qso classification: Application of HDBSCAN
• High-redshift galaxies and black holes in the eyes of JWST: a population synthesis model from infrared to X-rays
• Probabilistic classification of X-ray sources applied to Swift-XRT and XMM-Newton catalogs
• X-ray binary accretion states in Active Galactic Nuclei? Sensing the accretion disc of supermassive black holes with mid-infrared nebular lines
• Deep Chandra Monitoring Observations of NGC 4649: II. Wide-Field Hubble Space Telescope Imaging of the Globular Clusters
• Classifying Unidentified X-ray Sources in the Chandra Source Catalog Using a Multiwavelength Machine-learning Approach
• Automatic classification of time-variable X-ray sources
• Sustaining a Warm Corona in Active Galactic Nuclei Accretion Discs
• The Two-Dimensional Spatial Distributions of the Globular Clusters and Low-Mass X-Ray Binaries of NGC4649
• Deep Chandra Monitoring Observations of NGC 4649: I. Catalog of Source Properties
• X-ray emission processes in stars
• A New Halpha Emission-Line Survey in the Orion Nebula Cluster
• Deep Chandra Observations of HCG 16 - I. Active Nuclei, Star formation and Galactic Winds
• Chandra identification of 26 new black hole candidates in the central region of M31
• 50 M31 black hole candidates identified by Chandra and XMM-Newton
• Nustar view of the central region of the Perseus cluster
• Mixture Models for Photometric Redshifts
• Identifying New X-ray Binary Candidates in M31 using Random Forest Classification
• XMM-Newton reveals a Seyfert-like X-ray spectrum in the z=3.6 QSO B1422+231
• A search for the optical counterpart to the magnetar CXOU J010043.1-721134
• Possible Optical Detection of the Anomalous X-ray Pulsar CXOU J010043.1-721134
• Population of X-ray Sources in the Intermediate-Age Cluster NGC 3532: a Test Bed for Machine-Learning Classification
• Automated classification of Chandra X-ray point sources using machine learning methods
• X-Ray Redshifts of Obscured Chandra Source Catalog AGN

Cited by in corpus (8)

• Representation Learning for Time-Domain High-Energy Astrophysics: Discovery of Extragalactic Fast X-ray Transient XRT 200515
• Identifying type II quasars at intermediate redshift with few-shot learning photometric classification
• Classification of Radio Sources Through Self-Supervised Learning
• The hunt for new pulsating ultraluminous X-ray sources: a clustering approach
• Quantum Machine Learning for Identifying Transient Events in X-ray Light Curves
• Explainable machine learning classification of \textit{Chandra} X-ray sources: SHAP analysis of multi-wavelength features
• Hyperluminous Supersoft X-Ray Sources in the Chandra Catalog
• Extracting latent representations from X-ray spectra. Classification, regression, and accretion signatures of Chandra sources