Conditional Noise Deep Learning for Parameter Estimation of Gravitational Wave Events

TL;DR

This paper introduces a deep learning Bayesian inference model for gravitational wave parameter estimation that accounts for detector noise variations, achieving results comparable to traditional methods and enabling faster analysis.

Contribution

The paper presents a novel conditional variational autoencoder-based deep Bayesian machine that incorporates ASD variations for improved and accelerated gravitational wave parameter estimation.

Findings

Achieves posterior distributions similar to nested sampling methods.

Outperforms models without ASD conditioning.

Successfully applied to LIGO/Virgo O3 events with compatible results.

Abstract

We construct a Bayesian inference deep learning machine for parameter estimation of gravitational wave events of binaries of black hole coalescence. The structure of our deep Bayesian machine adopts the conditional variational autoencoder scheme by conditioning on both the gravitational wave strains and the variations of the amplitude spectral density (ASD) of the detector noise. We show that our deep Bayesian machine is capable of yielding posteriors compatible with the ones from the nested sampling method and better than the one without conditioning on the ASD. Our result implies that the process of parameter estimation can be accelerated significantly by deep learning even with large ASD drifting/variation. We also apply our deep Bayesian machine to the LIGO/Virgo O3 events, the result is compatible with the one by the traditional Bayesian inference method for the gravitational wave events with signal-to-noise ratios higher than typical threshold value. We also discuss some possible ways for future improvement.