Hybrid algorithm combining matched filtering and convolutional neural networks for searching gravitational waves from binary black hole mergers

TL;DR

This paper introduces a hybrid method combining matched filtering and neural networks to detect gravitational waves from black hole mergers, showing comparable performance to existing pipelines with efficient computation.

Contribution

The novel approach integrates matched filtering with neural networks for gravitational wave detection, demonstrating effective performance and computational efficiency.

Findings

Comparable detection performance to standard pipelines

Achieves reasonable sensitivity with practical resources

Demonstrates effectiveness on simulated black hole merger data

Abstract

Efficient searches for gravitational waves from compact binary coalescence are crucial for gravitational wave observations. We present a proof-of-concept for a method that utilizes a neural network taking an SNR map, a stack of SNR time series calculated by the matched filter, as input and predicting the presence or absence of gravitational waves in observational data. We demonstrate our algorithm by applying it to a dataset of gravitational-wave signals from stellar-mass black hole mergers injected into stationary Gaussian noise. Our algorithm exhibits comparable performance to the standard matched-filter pipeline and to the machine-learning algorithms that participated in the mock data challenge, MLGWSC-1. The demonstration also shows that our algorithm achieves reasonable sensitivity with practical computational resources.