A Machine Learning Approach For Classifying Low-mass X-ray Binaries Based On Their Compact Object Nature

Abstract

Low Mass X-ray binaries (LMXBs) are binary systems where one of the components is either a black hole or a neutron star and the other is a less massive star. It is challenging to unambiguously determine whether a LMXB hosts a black hole or a neutron star. In the last few decades, multiple observational works have tried, with different levels of success, to address this problem. In this paper, we explore the use of machine learning to tackle this observational challenge. We train a random forest classifier to identify the type of compact object using the energy spectrum in the energy range 5-25 keV obtained from the Rossi X-ray Timing Explorer archive. We report an average accuracy of 87±13% in classifying the spectra of LMXB sources. We further use the trained model for predicting the classes for LMXB systems with unknown or ambiguous classification. With the ever-increasing volume of astronomical data in the X-ray domain from present and upcoming missions (e.g., SWIFT, XMM-Newton, XARM, ATHENA, NICER), such methods can be extremely useful for faster and robust classification of X-ray sources and can also be deployed as part of the data reduction pipeline.

Cosmology Intertwined: A Review of the Particle Physics, Astrophysics, and Cosmology Associated with the Cosmological Tensions and Anomalies

“…problems, in order to estimate the main cosmological parameters of the standard model and beyond [180,181,2240], detect gravitational lens systems and detect low-mass binaries on X-rays [2241,2242]. In this subsection, we will deal with regression problems with ML (mainly focused on Gaussian Processes -GP, and Genetic Algorithms -GA) and deep learning (DL), being a subset of ML in which multilayered neural networks learn from the vast amount of data and what we will deal with in the BNNs paragraph.…”

Light-curve fingerprints: an automated approach to the extraction of X-ray variability patterns with feature aggregation – an example application to GRS 1915+105

“…For example, similarity in the variability of IGR J17091-3624 (Court et al 2017), and the Rapid Burster, MXB 1730-335 (Bagnoli & In't Zand 2015) could point to accretion physics which are independent of the nature of the accretor. Pattnaik et al (2021) attempted machine learning classification of compact objects in low mass X-ray binaries based on energyspectral features, and found that fairly accurate classification was possible. The presence of a black hole or neutron star in the binary system can have a significant impact on the physical interpretation of the observed phenomenology.…”

A Comparative Study of Machine-learning Methods for X-Ray Binary Classification

“…As a step toward understanding the physical mechanisms behind the separation seen by VB13, Gopalan et al (2015, hereafter GP15) developed a probabilistic (Bayesian) model that uses a supervised-learning approach (unknown classifications are predicted using known classifications) to quantify the accuracy of predicting the type of an unknown XRB using the VB13 representation. Pattnaik et al (2021) tested the ability of six machinelearning (ML) methods to accurately classify the compact objects in LMXBs, with CC and CI diagrams using data from the Proportional Counter Array (PCA) on RXTE (Glasser et al 1994). They found that the Random Forest (RF) and K-nearest Neighbors (KNN) methods gave the highest accuracies and specifically evaluated the performance of the RF.…”

“…As demonstrated by Islam et al (2021), CCI has the advantage over CC and CI individually, in that the geometric patterns it produces translate consistently to data from different instruments. The ML techniques we use-BGP, similar to GP15; KNN as used by Pattnaik et al (2021); and Support Vector Machines (SVM)-are widely used and particularly suitable for capturing spatial patterns in three-dimensional data. We use data from the Monitor of All Sky X-ray Image (MAXI; Matsuoka et al 2009) in the energy bands that Islam et al (2021) demonstrated most clearly show the separation of systems containing different types of compact objects.…”