Optimization of model independent gravitational wave search for binary black hole mergers using machine learning

The Coherent WaveBurst (cWB) search algorithm identifies generic gravitational wave (GW) signals in the LIGO-Virgo strain data. We propose a machine learning (ML) method to optimize pipeline sensitivity special class of GW known as binary black hole (BBH) mergers. Here, we test ML-enhanced cWB on data from first and second observing runs Advanced LIGO successfully recover all BBH events previously reported by cWB, with higher significance. For simulated found false alarm rate less than $1\,\mathrm{yr}^{-1}$, demonstrate improvement detection efficiency 26% for stellar-mass mergers 16% intermediate mass To robustness signals, show that it has increased spin precessing or eccentric events, even when trained quasi-circular aligned spins.