A Comparative Study of Machine Learning Methods for X-ray Binary Classification

Abstract

X-ray Binaries (XRBs) consist of a compact object that accretes material from an orbiting secondary star. The most secure method we have for determining if the compact object is a black hole is to determine its mass: this is limited to bright objects, and requires substantial time-intensive spectroscopic monitoring. With new X-ray sources being discovered with different X-ray observatories, developing efficient, robust means to classify compact objects becomes increasingly important. We compare three machine learning classification methods (Bayesian Gaussian Processes (BGP), K-Nearest Neighbors (KNN), Support Vector Machines (SVM)) for determining the compact objects as neutron stars or black holes (BHs) in XRB systems. Each machine learning method uses spatial patterns which exist between systems of the same type in 3D Color-Color-Intensity diagrams. We used lightcurves extracted using six years of data with MAXI/GSC for 44 representative sources. We find that all three methods are highly accurate in distinguishing pulsing from non-pulsing neutron stars (NPNS) with 95\% of NPNS and 100\% of pulsars accurately predicted. All three methods have high accuracy distinguishing BHs from pulsars (92\%) but continue to confuse BHs with a subclass of NPNS, called the Bursters, with KNN doing the best at only 50\% accuracy for predicting BHs. The precision of all three methods is high, providing equivalent results over 5-10 independent runs. In a future work, we suggest a fourth dimension be incorporated to mitigate the confusion of BHs with Bursters. This work paves the way towards more robust methods to efficiently distinguish BHs, NPNS, and pulsars.

arXiv comment24 pages, 17 figures, Accepted for publication in ApJ

References in corpus (21)

• Kernel methods in machine learning
• The MAXI Mission on the ISS: Science and Instruments for Monitoring All Sky X-Ray Images
• First Results from the All-Sky Monitor on the Rossi X-ray Timing Explorer
• The Swift/BAT Hard X-ray Transient Monitor
• Catalogue of high-mass X-ray binaries in the Galaxy ($4^{th}$ edition)
• A catalogue of low-mass X-ray binaries in the Galaxy, LMC, and SMC (Fourth edition)
• Bayesian Estimation of Hardness Ratios: Modeling and Computations
• In-Orbit Performance of MAXI Gas Slit Camera (GSC) on ISS
• XTE J1701-462 and its Implications for the Nature of Subclasses in Low-Magnetic-Field Neutron Star Low-Mass X-Ray Binaries
• The binary mass ratio in the black hole transient MAXI J1820+070
• AstroSat view of MAXI J1535-571: broadband spectro-temporal features
• Solid-state Slit Camera (SSC) on Board MAXI
• Chandra Grating Spectroscopy of the X-ray Binary 4U 1700-37 in a Flaring State
• The hypersoft state of Cygnus X-3 - A key to jet quenching in X-ray binaries?
• Common Patterns in the Evolution between the Luminous Neutron Star Low-Mass X-ray Binary Subclasses
• New Evidence for a Black Hole in the Compact Binary Cygnus X-3
• Orbital evolution and search for eccentricity and apsidal motion in the eclipsing HMXB 4U 1700-37
• A Machine Learning Approach For Classifying Low-mass X-ray Binaries Based On Their Compact Object Nature
• Evidence of Compton cooling during an X-ray flare supports a neutron star nature of the compact object in 4U1700-37
• Classifying X-ray Binaries: A Probabilistic Approach
• Comparing X-ray color selection in separating X-ray binary classes using Color-Color-Intensity diagrams

Cited by in corpus (3)

• Classifying Unidentified X-ray Sources in the Chandra Source Catalog Using a Multiwavelength Machine-learning Approach
• Ask The Machine: Systematic detection of wind-type outflows in low-mass X-ray binaries
• QPOML: A Machine Learning Approach to Detect and Characterize Quasi-Periodic Oscillations in X-ray Binaries