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 search of gravitational wave (GW) burts from core-collapse supernovae (CCSNe) using coherent WaveBurst (cWB) pipeline. The ML model discriminates noise signal events as features set reconstruction parameters provided by cWB. Detected are discarded yielding reduction false alarm rate (FAR) and probability (FAP) thus enhancing statistical significance. tested proposed strain data first half third observing run advanced LIGO, CCSNe GW signals extracted 3D simulations. is learned dataset events, then it used identify discard cWB analyses. Noise levels were examined single detector networks (L1 H1) two network (L1H1). FAR was reduced factor $\sim10$ $\sim100$, there an enhancement significance $\sim1$ $\sim2\sigma$, while no impact detection efficiencies.