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.

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

References in corpus (18)

• An accreting pulsar with extreme properties drives an ultraluminous x-ray source in NGC 5907
• Discovery of a 0.42-s pulsar in the ultraluminous X-ray source NGC 7793 P13
• The discovery of weak coherent pulsations in the ultraluminous X-ray source NGC 1313 X-2
• Machine Learning in Astronomy: a practical overview
• The weirdest SDSS galaxies: results from an outlier detection algorithm
• Different Fates of Young Star Clusters After Gas Expulsion
• 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
• The serendipituous discovery of a short-period eclipsing polar in 2XMMp
• 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
• Broadband X-ray spectral variability of the pulsing ULX NGC 1313 X-2
• A precessing accretion disc in the intermediate polar XY Ari?
• X-Ray Eclipse Time Delays in 4U2129+47
• Discovery of periodic dips in the brightest hard X-ray source of M31 with EXTraS
• The X-ray eclipse geometry of CAL 87
• XMMU J134736.6+173403: an eclipsing LMXB in quiescence or a peculiar AGN?