Searches for Compact Binary Coalescence Events using Neural Networks in LIGO/Virgo Second Observation Period

TL;DR

This paper investigates the use of convolutional neural networks to detect compact binary coalescence events in LIGO/Virgo O2 data, achieving performance comparable to traditional matched filtering methods without discovering new events.

Contribution

It introduces a neural network-based approach for gravitational wave detection that matches the effectiveness of established methods in the O2 data set.

Findings

Neural networks perform comparably to matched filtering in detection sensitivity.

Using data from pairs of interferometers improves neural network performance.

No new significant gravitational wave events were identified in the O2 data.

Abstract

We present results on the search for the coalescence of compact binary mergers using convolutional neural networks and the LIGO/Virgo data, corresponding to the O2 observation period. Two-dimensional images in time and frequency are used as input, and two sets of neural networks are trained separately for low mass (0.2 - 2.0 Msun) and high mass (25 - 100 Msun) compact binary coalescence events. We explored neural networks trained with input information from a single or a pair of interferometers, indicating that the use of information from pairs leads to an improved performance. A scan over the full O2 data set using the convolutional neural networks for detection demonstrates that the performance is compatible with that from canonical pipelines using matched filtering techniques. No additional events with significant signal-to-noise ratio are found in the O2 data.