Exploring X-ray variability with unsupervised machine learning

I. Self-organizing maps applied to XMM-Newton data^★

¹ Istituto di Astrofisica Spaziale e Fisica Cosmica (INAF IASF-MI), 20133 Milano, Italy
e-mail: milos.kovacevic@inaf.it; milosh.kovacevic@gmail.com
² Center for Astro, Particle and Planetary Physics (CAP 3), New York University, Abu Dhabi, UAE
e-mail: mp5757@nyu.edu
³ Physics and Astronomy Department Galileo Galilei, University of Padova, Vicolo dell’Osservatorio 3, 35122, Padova, Italy
⁴ Département de Physique, Université de Montréal, Montreal, Quebec H3T 1J4, Canada
⁵ Istituto Nazionale di Fisica Nucleare - Sezione di Padova, Via Marzolo 8, 35131 Padova, Italy
⁶ INFN, Sezione di Pavia, via A. Bassi 6, 27100 Pavia, Italy

Received: 14 October 2021
Accepted: 26 January 2022

Abstract

Context. 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.

Aims. 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).

Methods. 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 ⪆10⁵ detections from the Exploring the X-ray Transient and variable Sky catalog.

Results. The resulting map reveals that the ≈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.

Conclusions. 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.