Deep learning inference of the neutron star equation of state

TL;DR

This paper introduces a deep learning pipeline that infers the neutron star equation of state from observational data, capable of detecting phase transitions and improving understanding of stellar interiors.

Contribution

It develops a novel deep neural network approach, including Bayesian methods, for inferring neutron star interior properties from observational data.

Findings

Deep networks accurately infer the speed of sound inside neutron stars.

The pipeline can detect QCD phase transitions in stellar cores.

Results demonstrate promising application for future stellar observations.

Abstract

We present a pipeline to infer the equation of state of neutron stars from observations based on deep neural networks. In particular, using the standard (deterministic), as well as Bayesian (probabilistic) deep networks, we explore how one can infer the interior speed of sound of the star given a set of mock observations of total stellar mass, stellar radius and tidal deformability. We discuss in detail the construction of our simulated dataset of stellar observables starting from the solution of the gravitational equations, as well as the relevant architectures for the deep networks, along with their performance and accuracy. We further explain how our pipeline is capable to detect a possible QCD phase transition in the stellar core. Our results show that deep networks offer a promising tool towards solving the inverse problem of neutron stars, and the accurate inference of their interior from future stellar observations.