Real-Time Gravitational Wave Science with Neural Posterior Estimation

Dax, Maximilian; Green, Stephen R.; Gair, Jonathan; Macke, Jakob H.; Buonanno, Alessandra; Schölkopf, Bernhard

Abstract

We demonstrate unprecedented accuracy for rapid gravitational wave parameter estimation with deep learning. Using neural networks as surrogates for Bayesian posterior distributions, we analyze eight gravitational wave events from the first LIGO-Virgo Gravitational-Wave Transient Catalog and find very close quantitative agreement with standard inference codes, but with inference times reduced from 𝑂(day) to 20 s per event. Our networks are trained using simulated data, including an estimate of the detector noise characteristics near the event. This encodes the signal and noise models within millions of neural-network parameters and enables inference for any observed data consistent with the training distribution, accounting for noise nonstationarity from event to event. Our algorithm—called “DINGO”—sets a new standard in fast and accurate inference of physical parameters of detected gravitational wave events, which should enable real-time data analysis without sacrificing accuracy.

Citation

Dax, M., Green, S. R., Gair, J., Macke, J. H., Buonanno, A., & Schölkopf, B. (2021). Real-Time Gravitational Wave Science with Neural Posterior Estimation. Physical Review Letters, 127(24), Article 241103. https://doi.org/10.1103/physrevlett.127.241103

• Journal Article Type: Article
• Acceptance Date: Nov 17, 2021
• Online Publication Date: Dec 8, 2021
• Publication Date: Dec 8, 2021
• Deposit Date: Mar 31, 2025
• Publicly Available Date: Apr 4, 2025
• Journal: Physical Review Letters
• Print ISSN: 0031-9007
• Electronic ISSN: 1079-7114
• Publisher: American Physical Society
• Peer Reviewed: Peer Reviewed
• Volume: 127
• Issue: 24
• Article Number: 241103
• DOI: https://doi.org/10.1103/physrevlett.127.241103
• Public URL: https://nottingham-repository.worktribe.com/output/21645896
• Publisher URL: https://journals.aps.org/prl/abstract/10.1103/PhysRevLett.127.241103