Exploring X-ray variability with unsupervised machine learning I. Self-organizing maps applied to XMM-Newton data

Abstract

XMM-Newton provides unprecedented insight into the X-ray Universe, recording variability information for hundreds of thousands of sources. Manually searching for interesting patterns in light curves is impractical, requiring an automated data-mining approach for the characterization of sources. Straightforward fitting of temporal models to light curves is not a sure way to identify them, especially with noisy data. We used unsupervised machine learning to distill a large data set of light-curve parameters, revealing its clustering structure in preparation for anomaly detection and subsequent searches for specific source behaviors (e.g., flares, eclipses). Self-organizing maps (SOMs) achieve dimensionality reduction and clustering within a single framework. They are a type of artificial neural network trained to approximate the data with a two-dimensional grid of discrete interconnected units, which can later be visualized on the plane. We trained our SOM on temporal-only parameters computed from more than 100,000 detections from the EXTraS catalog. The resulting map reveals that about 2500 most variable sources are clustered based on temporal characteristics. We find distinctive regions of the SOM map associated with flares, eclipses, dips, linear light curves, and others. Each group contains sources that appear similar by eye. We single out a handful of interesting sources for further study. The condensed view of our dataset provided by SOMs allowed us to identify groups of similar sources, speeding up manual characterization by orders of magnitude. Our method also highlights problems with fitting simple temporal models to light curves and can be used to mitigate them to an extent. This will be crucial for fully exploiting the high data volume expected from upcoming X-ray surveys, and may also help with interpreting supervised classification models.

arXiv commentAccepted in Astronomy & Astrophysics (A&A). Main part: 12 pages, 12 figures, 1 video (appendix: 5 pages and 4 figures)

References in corpus (44)

• The European Photon Imaging Camera on XMM-Newton: The MOS Cameras
• An accreting pulsar with extreme properties drives an ultraluminous x-ray source in NGC 5907
• Data Mining and Machine Learning in Astronomy
• Discovery of a 0.42-s pulsar in the ultraluminous X-ray source NGC 7793 P13
• Mapping the Galaxy Color-Redshift Relation: Optimal Photometric Redshift Calibration Strategies for Cosmology Surveys
• The discovery of weak coherent pulsations in the ultraluminous X-ray source NGC 1313 X-2
• Discovery of a 2.8 s pulsar in a 2 d orbit High-Mass X-ray Binary powering the Ultraluminous X-ray source ULX-7 in M51
• Dynamical Relics of the Ancient Galactic Halo
• Machine Learning in Astronomy: a practical overview
• The weirdest SDSS galaxies: results from an outlier detection algorithm
• K2 Variable Catalogue II: Machine Learning Classification of Variable Stars and Eclipsing Binaries in K2 Fields 0-4
• A highly-ionized absorber in the X-ray binary 4U 1323-62: a new explanation for the dipping phenomenon
• Unsupervised self-organised mapping: a versatile empirical tool for object selection, classification and redshift estimation in large surveys
• Finding outlier light-curves in catalogs of periodic variable stars
• A survey of stellar X-ray flares from the XMM-Newton serendipitous source catalogue: Hipparcos-Tycho cool stars
• A deep XMM-Newton observation of the ultraluminous X-ray source HoII X-1 : the case against a 1000 solar mass black hole
• StarGO: A New Method to Identify the Galactic Origins of Halo Stars
• The automated classification of astronomical lightcurves using Kohonen self-organising maps
• Different Fates of Young Star Clusters After Gas Expulsion
• Detecting outliers and learning complex structures with large spectroscopic surveys - a case study with APOGEE stars
• A large sample of Kohonen-selected SDSS quasars with weak emission lines: selection effects and statistical properties
• A Supernova Candidate at z=0.092 in XMM-Newton Archival Data
• Probabilistic classification of X-ray sources applied to Swift-XRT and XMM-Newton catalogs
• The serendipituous discovery of a short-period eclipsing polar in 2XMMp
• The EXTraS Project: Exploring the X-ray transient and variable sky
• CG X-1: an eclipsing Wolf-Rayet ULX in the Circinus galaxy
• EXTraS discovery of an X-ray superflare from an L dwarf
• Exploratory Spectroscopy of Magnetic Cataclysmic Variables Candidates and Other Variable Objects
• How to Find Variable Active Galactic Nuclei with Machine Learning
• XMM-Newton observations of the eclipsing polar V2301 Oph
• Discovery of a Highly Variable Dipping Ultraluminous X-ray source in M94
• Broadband X-ray spectral variability of the pulsing ULX NGC 1313 X-2
• An XMM-Newton view of the dipping low-mass X-ray binary XTE J1710-281
• Density Based Outlier Scoring on Kepler Data
• A precessing accretion disc in the intermediate polar XY Ari?
• X-Ray Eclipse Time Delays in 4U2129+47
• Discovery of a 23.8h QPO in the SWIFT light curve of XMMU J134736.6+173403
• RX J004717.4-251811: The first eclipsing X-ray binary outside the Local Group
• XMM-Newton observations of the eclipsing polar EP Dra
• Discovery of periodic dips in the brightest hard X-ray source of M31 with EXTraS
• The X-ray eclipse geometry of CAL 87
• Clustering clusters: unsupervised machine learning on globular cluster structural parameters
• XMMSL1J063045.9-603110: a tidal disruption event fallen into the back burner
• XMMU J134736.6+173403: an eclipsing LMXB in quiescence or a peculiar AGN?

Cited by in corpus (4)

• Supernova search with active learning in ZTF DR3
• Representation Learning for Time-Domain High-Energy Astrophysics: Discovery of Extragalactic Fast X-ray Transient XRT 200515
• Quantum Machine Learning for Identifying Transient Events in X-ray Light Curves
• Searching for outliers in the Chandra Source Catalog