Detection of Gravitational Waves Using Bayesian Neural Networks

TL;DR

This paper introduces a Bayesian Neural Network model that detects gravitational wave events and their full duration, including inspiral, with high accuracy and near real-time alert capability, enhancing GW data analysis.

Contribution

The novel integration of Bayesian approach with CNN-LSTM architecture enables uncertainty estimation and detection of unknown signal types in gravitational wave data.

Findings

Successfully detected all seven BBH events in LIGO O2 data.

Achieved 90% detection rate for signals with SNR >7.

Latency of about 20 seconds for alert generation.

Abstract

We propose a new model of Bayesian Neural Networks to not only detect the events of compact binary coalescence in the observational data of gravitational waves (GW) but also identify the full length of the event duration including the inspiral stage. This is achieved by incorporating the Bayesian approach into the CLDNN classifier, which integrates together the Convolutional Neural Network (CNN) and the Long Short-Term Memory Recurrent Neural Network (LSTM). Our model successfully detect all seven BBH events in the LIGO Livingston O2 data, with the periods of their GW waveforms correctly labeled. The ability of a Bayesian approach for uncertainty estimation enables a newly defined `awareness' state for recognizing the possible presence of signals of unknown types, which is otherwise rejected in a non-Bayesian model. Such data chunks labeled with the awareness state can then be further investigated rather than overlooked. Performance tests with 40,960 training samples against 512 chunks of 8-second real noise mixed with mock signals of various optimal signal-to-noise ratio $0 \leq \rho_\text{opt} \leq 18$ show that our model recognizes 90% of the events when $\rho_\text{opt} >7$ (100% when $\rho_\text{opt} >8.5$) and successfully labels more than 95% of the waveform periods when $\rho_\text{opt} >8$. The latency between the arrival of peak signal and generating an alert with the associated waveform period labeled is only about 20 seconds for an unoptimized code on a moderate GPU-equipped personal computer. This makes our model possible for nearly real-time detection and for forecasting the coalescence events when assisted with deeper training on a larger dataset using the state-of-art HPCs.