Searching for Quasi-Periodic Eruptions using machine learning

Abstract

Quasi-Periodic Eruptions (QPEs) are a rare phenomenon in which the X-ray emission from the nuclei of galaxies shows a series of large amplitude flares. Only a handful of QPEs have been observed but the possibility remains that there are as yet undetected sources in archival data. Given the volume of data available a manual search is not feasible, and so we consider an application of machine learning to archival data to determine whether a set of time-domain features can be used to identify further lightcurves containing eruptions. Using a neural network and 14 variability measures we are able to classify lightcurves with accuracies of greater than $94{{\%}}$ with simulated data and greater than $98{{\%}}$ with observational data on a sample consisting of 12 lightcurves with QPEs and 52 lightcurves without QPEs. An analysis of 83,531 X-ray detections from the XMM Serendipitous Source Catalogue allowed us to recover lightcurves of known QPE sources and examples of several categories of variable stellar objects.