Improving the background of gravitational-wave searches for core collapse supernovae: A machine learning approach

Abstract

Based on the priorO1-O2observing runs, about30%of the data collected by Advanced LIGO andVirgo inthenext observingruns are expected tobe single-interferometer data, i.e. theywill be collected at times when only one detector in the network is operating in observingmode. Searches for gravitational-wave signals from supernova events do not rely on matched filtering techniques because of the stochastic nature of the signals. If a Galactic supernova occurs during single-interferometer times, separation of its unmodelled gravitational-wave signal from noisewill be evenmore difficult due to lack of coherence between detectors.We present a novel machine learningmethod to performsingle-interferometer supernova searches based on the standard LIGO-Virgo coherentWaveBurst pipeline.We show that the methodmay be used to discriminateGalactic gravitational-wave supernova signals from noise transients, decrease the false alarmrate of the search, and improve the supernova detection reach of the detectors.