Neutron Star Equation of State via Physics Informed Neural Network

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bezerra, Gabriel, Dexheimer, Veronica, Negreiros, Rodrigo
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914616569757696
author Bezerra, Gabriel
Dexheimer, Veronica
Negreiros, Rodrigo
author_facet Bezerra, Gabriel
Dexheimer, Veronica
Negreiros, Rodrigo
contents We present the first application, to the best of our knowledge, of Physics-Informed Neural Networks (PINNs) to the neutron star equation-of-state (EOS) inverse problem. Two interacting networks -- one representing the EOS $P(\varepsilon)$ as a continuous, non-parametric function, the other solving the Tolman-Oppenheimer-Volkoff (TOV) equations -- are trained jointly on NICER X-ray timing posteriors and pulsar mass measurements. The TOV equations enter as a mean-square ODE residual enforced via automatic differentiation at every training step, rooted in the Neural Differential Equation framework. The inferred EOS satisfies nuclear saturation properties, causality, and perturbative QCD bounds simultaneously; $χ$EFT consistency at $1$--$2\rhoz$ emerges without explicit enforcement, providing a non-trivial self-consistency check. Across $N=15$ independent training runs, we find a neutron star maximum mass $M_\mathrm{max}=2.06^{+0.07}_{-0.09}$ and radius and tidal deformability of a 1.4 $M_\odot$ star $R_{1.4}=12.85^{+0.03}_{-0.06}$~km and $Λ_{1.4}=684$, respectively, with 68\% CI, in agreement with recent Bayesian analyses. Most interestingly, the speed of sound exhibits a reproducible softening at $2$--$4\,\rhoz$, consistent with a quark-hadron crossover.
format Preprint
id arxiv_https___arxiv_org_abs_2605_31198
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Neutron Star Equation of State via Physics Informed Neural Network
Bezerra, Gabriel
Dexheimer, Veronica
Negreiros, Rodrigo
High Energy Astrophysical Phenomena
We present the first application, to the best of our knowledge, of Physics-Informed Neural Networks (PINNs) to the neutron star equation-of-state (EOS) inverse problem. Two interacting networks -- one representing the EOS $P(\varepsilon)$ as a continuous, non-parametric function, the other solving the Tolman-Oppenheimer-Volkoff (TOV) equations -- are trained jointly on NICER X-ray timing posteriors and pulsar mass measurements. The TOV equations enter as a mean-square ODE residual enforced via automatic differentiation at every training step, rooted in the Neural Differential Equation framework. The inferred EOS satisfies nuclear saturation properties, causality, and perturbative QCD bounds simultaneously; $χ$EFT consistency at $1$--$2\rhoz$ emerges without explicit enforcement, providing a non-trivial self-consistency check. Across $N=15$ independent training runs, we find a neutron star maximum mass $M_\mathrm{max}=2.06^{+0.07}_{-0.09}$ and radius and tidal deformability of a 1.4 $M_\odot$ star $R_{1.4}=12.85^{+0.03}_{-0.06}$~km and $Λ_{1.4}=684$, respectively, with 68\% CI, in agreement with recent Bayesian analyses. Most interestingly, the speed of sound exhibits a reproducible softening at $2$--$4\,\rhoz$, consistent with a quark-hadron crossover.
title Neutron Star Equation of State via Physics Informed Neural Network
topic High Energy Astrophysical Phenomena
url https://arxiv.org/abs/2605.31198