Decoding Long-duration Gravitational Waves from Binary Neutron Stars with Machine Learning: Parameter Estimation and Equations of State

TL;DR

This paper presents a machine learning framework that rapidly estimates parameters and constrains equations of state from long-duration gravitational wave signals of binary neutron stars, addressing computational challenges for third-generation detectors.

Contribution

The authors develop a neural network-based workflow that compresses data and performs inference in seconds, enabling efficient analysis of prolonged BNS signals for future GW detectors.

Findings

Machine learning enables hours-long BNS signal analysis in seconds.

The framework provides accurate parameter estimation and EOS constraints.

Potential to transform large-scale BNS data analysis in the third-generation GW era.

Abstract

Gravitational waves (GWs) from binary neutron stars (BNSs) offer valuable understanding of the nature of compact objects and hadronic matter, and the science potential will be greatly enhanced by the third-generation (3G) GW detectors, which are expected to detect BNS signals with order-of-magnitude improvements in duration, detection rates, and signal strength. However, the resulting computational demands for analyzing such prolonged signals pose a critical challenge that existing Bayesian methods cannot feasibly address in the 3G era. To bridge this critical gap, we demonstrate a machine learning-based workflow capable of producing source parameter estimation and constraints on equations of state (EOSs) for hours-long BNS signals in seconds with minimal hardware costs. We employ efficient compression of the GW data and EOS using neural networks, based on which we build normalizing flows for inference that can deliver results in seconds. The optimized computational cost of BNS signal analysis with our framework shows that machine learning has the potential to be an indispensable tool for future catalog-level BNS analyses, paving the way for large-scale investigations of BNS-related physics across the 3G observational landscape.