QPOML: A Machine Learning Approach to Detect and Characterize Quasi-Periodic Oscillations in X-ray Binaries

Abstract

Astronomy is presently experiencing profound growth in the deployment of machine learning to explore large datasets. However, transient quasi-periodic oscillations (QPOs) which appear in power density spectra of many X-ray binary system observations are an intriguing phenomena heretofore not explored with machine learning. In light of this, we propose and experiment with novel methodologies for predicting the presence and properties of QPOs to make the first ever detections and characterizations of QPOs with machine learning models. We base our findings on raw energy spectra and processed features derived from energy spectra using an abundance of data from the NICER and RXTE space telescope archives for two black hole low mass X-ray binary sources, GRS 1915+105 and MAXI J1535-571. We advance these non-traditional methods as a foundation for using machine learning to discover global inter-object generalizations between - and provide unique insights about - energy and timing phenomena to assist with the ongoing challenge of unambiguously understanding the nature and origin of QPOs. Additionally, we have developed a publicly available Python machine learning library, QPOML, to enable further Machine Learning aided investigations into QPOs.

18 pages, 12 figures, accepted by MNRAS

References in corpus (32)

• Array Programming with NumPy
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• A catalogue of low-mass X-ray binaries in the Galaxy, LMC, and SMC (Fourth edition)
• A Parallax Distance to the Microquasar GRS 1915+105 and a Revised Estimate of its Black Hole Mass
• An Empirical Background Model for the NICER X-ray Timing Instrument
• Geometrical constraints on the origin of timing signals from black holes
• Searching for Exoplanets Using Artificial Intelligence
• Coupling between the accreting corona and the relativistic jet in the micro quasar GRS 1915+105
• A two-component Comptonisation model for the type-B QPO in MAXI J1348-630
• Machine Learning Gravitational Waves from Binary Black Hole Mergers
• Time lags of the type-B QPO in MAXI J1348-630
• AstroSat view of GRS 1915+105 during the Soft State: Detection of HFQPOs and estimation of Mass and Spin
• The evolving properties of the corona of GRS 1915+105: A spectral-timing perspective through variable-Comptonisation modelling
• A persistent ultraviolet outflow from an accreting neutron star binary transient
• Broadband reflection spectroscopy of MAXI J1535-571 using AstroSat: Estimation of black hole mass and spin
• Spectro-timing analysis of MAXI J1535-571 using AstroSat
• A NICER look at the state transitions of the black hole candidate MAXI J1535-571 during its reflares
• Quasiperiodic oscillations in Cen X-3 and the long term intensity variations
• Classifying Unidentified X-ray Sources in the Chandra Source Catalog Using a Multiwavelength Machine-learning Approach
• Rapidly evolving disk-jet coupling during re-brightenings in the black hole transient MAXI J1535-571
• Exploring the Long-Term Evolution of GRS 1915+105
• On the energy dependence of the QPO phenomenon in the black hole system MAXI J1535-571
• ALMA/NICER observations of GRS 1915+105 indicate a return to a hard state
• The spins of the Galactic black holes in MAXI J1535-571 and 4U 1630-472 from Insight-HXMT
• A global study of Type B quasi-periodic oscillation in black hole X-ray binaries
• Analysis of the reflection spectra of MAXI J1535-571 in the hard and intermediate states
• High-frequency variability in neutron-star low-mass X-ray binaries
• A Machine Learning approach for classification of accretion states of Black hole binaries
• The evolution of the high-frequency variability in the black hole candidate GRS 1915+105 as seen by RXTE
• A Machine Learning Approach For Classifying Low-mass X-ray Binaries Based On Their Compact Object Nature
• A Comparative Study of Machine Learning Methods for X-ray Binary Classification
• Data Leakage in Notebooks: Static Detection and Better Processes