A Machine Learning approach for classification of accretion states of Black hole binaries

Abstract

In this paper, we employ Machine Learning algorithms on multi-mission observations for the classification of accretion states of outbursting Black hole X-ray binaries for the first time. Archival data from RXTE, Swift, MAXI and AstroSat observatories are used to generate the hardness intensity diagrams (HIDs) for outbursts of the sources XTE J1859+226 (1999 outburst), GX 339-4 (2002, 2004, 2007 and 2010 outbursts), IGR J17091-3624 (2016 outburst), and MAXI J1535-571 (2017 outburst). Based on variation of X-ray flux, hardness ratios, presence of various types of Quasi-periodic Oscillations (QPOs), photon indices and disk temperature, we apply clustering algorithms like K-Means clustering and Hierarchical clustering to classify the accretion states (clusters) of each outburst. As multiple parameters are involved in the classification process, we show that clustering algorithms club together the observations of similar characteristics more efficiently than the `standard' method of classification. We also infer that K-Means clustering provides more reliable results than Hierarchical clustering. We demonstrate the importance of the classification based on machine learning by comparing it with results from `standard' classification.

10 pages, 9 figures, Accepted for publication in MNRAS

References in corpus (12)

• X-ray Properties of Black-Hole Binaries
• Evolution of the quasi-periodic oscillation frequency in GRO J1655-40 -- Implications for accretion disk dynamics
• AstroSat/LAXPC reveals the high energy variability of GRS 1915+105 in the chi class
• Fast variability from black-hole binaries
• Determination of mass of IGR J17091-3624 from "Spectro-Temporal" variations during onset-phase of the 2011 outburst
• AstroSat view of MAXI J1535-571: broadband spectro-temporal features
• Power-Colours: Simple X-ray Binary Variability Comparison
• AstroSat and MAXI view of the Black Hole binary 4U 1630-472 during 2016 and 2018 Outbursts
• Exploring the Long-Term Evolution of GRS 1915+105
• Spectral and Timing Properties of IGR J17091-3624 in the Rising Hard State During its 2016 Outburst
• Study of the long-term evolution of the accretion dynamics of GX 339-4
• AstroSat view of LMC X-2: Evolution of broadband X-ray spectral properties along a complete Z-track

Cited by in corpus (9)

• Unraveling the foretime of GRS 1915+105 using AstroSat observations: Wide-band spectral and temporal characteristics
• Accretion Scenario of MAXI J1820+070 during 2018 Outbursts with Multi-mission Observations
• A Dependable Distance Estimator to Black Hole Low-Mass X-ray Binaries
• Broadband X-ray properties of black holes GRS 1758-258 and 1E 1740.7-2942: AstroSat and NuSTAR results
• X-ray Variability in the Symbiotic Binary RT Cru: Principal Component Analysis
• A Temporal Scale to Track the Spectral Transitions in Low-Mass X-ray Binaries
• QPOML: A Machine Learning Approach to Detect and Characterize Quasi-Periodic Oscillations in X-ray Binaries
• Multimission Observations of GS 1354-64 during the 2025-2026 Outburst: First Results
• IGR J12580+0134: The Nearest Tidal Disruption Event and its Faint Resurrection