Deep generative models of gravitational waveforms via conditional autoencoder

We construct few deep generative models of gravitational waveforms based on the semisupervising scheme of conditional autoencoders and its variational extensions. Once the training is done, we find that our best waveform model can generate the inspiral-merger waveforms of binary black hole coalescen...

Full description

Saved in:
Bibliographic Details
Published in:Physical review. D Vol. 103; no. 12; p. 1
Main Authors: Liao, Chung-Hao, Lin, Feng-Li
Format: Journal Article
Language:English
Published: College Park American Physical Society 15.06.2021
Subjects:
Accuracy
Algorithms
Coalescing
Gravitational waves
Mathematical models
Numerical relativity
Parameter estimation
Relativity
Training
Waveforms
ISSN:2470-0010, 2470-0029
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We construct few deep generative models of gravitational waveforms based on the semisupervising scheme of conditional autoencoders and its 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 effective-one-body-numerical-relativity 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 improvement of the accuracy in the 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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2470-0010
2470-0029
DOI:10.1103/PhysRevD.103.124051