Long Short-Term Memory for Early Warning Detection of Gravitational Waves

TL;DR

This paper demonstrates a deep learning approach using LSTM networks to provide early warnings of gravitational wave events from black hole mergers, potentially enabling pre-merger detection in real-time.

Contribution

It introduces a novel LSTM-based method for pre-merger gravitational wave detection, showing competitive performance with traditional techniques at early warning times.

Findings

Early warning alerts up to four seconds before merger

LSTM model performance comparable to matched filtering

Potential for real-time pre-merger detection in gravitational wave astronomy

Abstract

The pre-merger detection of gravitational waves from the early inspiral phase of compact binary coalescence events would allow the observation of the earlier stages of the merger in the electromagnetic band. This would significantly impact multi-messenger astronomy, giving astronomers potential access to rich new information. Here, we introduce a proof-of-concept deep-learning-based approach to produce pre-merger early-warning alerts for binary black hole systems. We show the possibility of using a Long Short-Term Memory network trained on the whitened detector strain in the time domain to detect and classify compact binary events. In this work, we consider a single advanced Laser Interferometer Gravitational-Wave Observatory detector at design sensitivity and make approximate sensitivity and early warning capability comparisons with approximations to traditional matched filtering approaches. We find that our model is competitive in both aspects, and when applied to a simulated test dataset was able to produce an early alert up to four seconds before the merger.