Detecting the early inspiral of a gravitational-wave signal with convolutional neural networks

TL;DR

This paper presents a new early warning system for gravitational waves using short convolutional neural networks trained on early inspiral signals from binary neutron star mergers, enabling rapid detection from limited waveform data.

Contribution

The study introduces a novel CNN-based method for early gravitational wave detection focusing on compact binary inspirals, demonstrating effective detection from partial waveforms.

Findings

CNNs can detect early inspiral signals from limited waveform data

The method works across different binary neutron star masses

It offers a potential rapid alert system for gravitational wave events

Abstract

We introduce a novel methodology for the operation of an early %warning alert system for gravitational waves. It is based on short convolutional neural networks. We focus on compact binary coalescences, for light, intermediate and heavy binary-neutron-star systems. The signals are 1-dimensional time series $-$ the whitened time-strain $-$ injected in Gaussian noise built from the power-spectral density of the LIGO detectors at design sensitivity. We build short 1-dimensional convolutional neural networks to detect these types of events by training them on part of the early inspiral. We show that such networks are able to retrieve these signals from a small portion of the waveform.