Deep Generative Models of Gravitational Waveforms via Conditional Autoencoder

TL;DR

This paper develops deep generative models using conditional autoencoders to efficiently produce accurate gravitational waveforms, significantly speeding up waveform generation for gravitational wave detection and analysis.

Contribution

The paper introduces a novel application of conditional autoencoders and variational extensions to generate gravitational waveforms with high accuracy and speed, enabling faster data analysis.

Findings

Achieves over 97% overlap accuracy in waveform generation.

Generates waveforms in about 1 millisecond, much faster than traditional methods.

Capable of producing high-mass-ratio waveforms from low-mass-ratio training data.

Abstract

We construct few deep generative models of gravitational waveforms based on the semi-supervising scheme of conditional autoencoders and their variational extensions. Once the training is done, we find that our best waveform model can generate the inspiral-merger waveforms of binary black hole coalescence with more than $97\%$ average overlap matched filtering accuracy for the mass ratio between $1$ and $10$. Besides, the generation time of a single waveform takes about one millisecond, which is about $10$ to $100$ times faster than the EOBNR algorithm running on the same computing facility. Moreover, these models can also help to explore the space of waveforms. That is, with mainly the low-mass-ratio training set, the resultant trained model is capable of generating large amount of accurate high-mass-ratio waveforms. This result implies that our generative model can speed up the waveform generation for the low latency search of gravitational wave events. With the improvement of the accuracy in future work, the generative waveform model may also help to speed up the parameter estimation and can assist the numerical relativity in generating the waveforms of higher mass ratio by progressively self-training.