Adapting to noise distribution shifts in flow-based gravitational-wave inference

TL;DR

This paper introduces a probabilistic model to forecast future noise spectral densities, enabling flow-based gravitational-wave inference networks to adapt to changing detector noise characteristics over extended periods.

Contribution

The authors develop a probabilistic PSD forecasting model that allows DINGO networks to perform accurate inference across multiple observing runs without prior knowledge of all noise conditions.

Findings

Successfully trained DINGO on O2 and early O3 PSDs

Achieved accurate inference on 37 real O3 events

Enhanced the temporal scope of deep learning in gravitational-wave analysis

Abstract

Deep learning techniques for gravitational-wave parameter estimation have emerged as a fast alternative to standard samplers $\unicode{x2013}$ producing results of comparable accuracy. These approaches (e.g., DINGO) enable amortized inference by training a normalizing flow to represent the Bayesian posterior conditional on observed data. By conditioning also on the noise power spectral density (PSD) they can even account for changing detector characteristics. However, training such networks requires knowing in advance the distribution of PSDs expected to be observed, and therefore can only take place once all data to be analyzed have been gathered. Here, we develop a probabilistic model to forecast future PSDs, greatly increasing the temporal scope of DINGO networks. Using PSDs from the second LIGO-Virgo observing run (O2) $\unicode{x2013}$ plus just a single PSD from the beginning of the third (O3) $\unicode{x2013}$ we show that we can train a DINGO network to perform accurate inference throughout O3 (on 37 real events). We therefore expect this approach to be a key component to enable the use of deep learning techniques for low-latency analyses of gravitational waves.