Using supervised learning algorithms as a follow-up method in the search of gravitational waves from core-collapse supernovae

We present a follow-up method based on supervised machine learning (ML) to improve the performance in the search of gravitational wave (GW) bursts from core-collapse supernovae (CCSNe) using the coherent WaveBurst (cWB) pipeline. The ML model discriminates noise from signal events by using a set of reconstruction parameters provided by cWB as features. Detected noise events are discarded yielding a reduction in the false alarm rate (FAR) and the false alarm probability thus enhancing the statistical significance. We tested the proposed method using strain data from the first half of the third observing run of advanced LIGO, and CCSNe GW signals extracted from 3D simulations. The ML model is tuned using a dataset of noise and signal events, and then used to identify and discard noise events in the cWB analyses. Noise and signal reduction levels were examined in single (L1 and H1) and two detector network (L1H1). The FAR was reduced by a factor of-10 to-100 resulting in an enhancement in the statistical significance of-1?? to-2??, while not impacting the detection efficiencies.

Automated summary

This study presents a supervised machine learning method to improve the performance in searching for gravitational wave bursts from core-collapse supernovae. By identifying and discarding noise events, the method reduces the false alarm rate and enhances the statistical significance. The method was tested using strain data from advanced LIGO and simulated CCSNe signals.