Decoding Neutron Star Observations: Revealing Composition through Bayesian Neural Networks

Abstract

We exploit the great potential offered by Bayesian Neural Networks (BNNs) to directly decipher the internal composition of neutron stars (NSs) based on their macroscopic properties. By analyzing a set of simulated observations, namely NS radius and tidal deformability, we leverage BNNs as effective tools for inferring the proton fraction and sound speed within NS interiors. To achieve this, several BNNs models were developed upon a dataset of $\sim$ 25K nuclear EoS within a relativistic mean-field framework, obtained through Bayesian inference that adheres to minimal low-density constraints. Unlike conventional neural networks, BNNs possess an exceptional quality: they provide a prediction uncertainty measure. To simulate the inherent imperfections present in real-world observations, we have generated four distinct training and testing datasets that replicate specific observational uncertainties. Our initial results demonstrate that BNNs successfully recover the composition with reasonable levels of uncertainty. Furthermore, using mock data prepared with the DD2, a different class of relativistic mean-field model utilized during training, the BNN model effectively retrieves the proton fraction and speed of sound for neutron star matter.

arXiv comment16 pages, 15 figures, published version

References in corpus (53)

• Shapiro delay measurement of a two solar mass neutron star
• A Massive Pulsar in a Compact Relativistic Binary
• GW190814: Gravitational Waves from the Coalescence of a 23 M${}_{\odot }$ Black Hole with a 2.6 M${}_{\odot }$ Compact Object
• PSR J0030+0451 Mass and Radius from NICER Data and Implications for the Properties of Neutron Star Matter
• A NICER View of PSR J0030+0451: Millisecond Pulsar Parameter Estimation
• X-ray spectral modelling of the AGN obscuring region in the CDFS: Bayesian model selection and catalogue
• Properties of the binary neutron star merger GW170817
• A NICER View of the Massive Pulsar PSR J0740+6620 Informed by Radio Timing and XMM-Newton Spectroscopy
• Refined Mass and Geometric Measurements of the High-Mass PSR J0740+6620
• Composition and thermodynamics of nuclear matter with light clusters
• Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users
• Equation of state and neutron star properties constrained by nuclear physics and observation
• Neutron-Rich Nuclei in Heaven and Earth
• Evidence for quark-matter cores in massive neutron stars
• The NANOGrav Nine-year Data Set: Mass and Geometric Measurements of Binary Millisecond Pulsars
• The NANOGrav 11-year Data Set: High-precision timing of 45 Millisecond Pulsars
• Relativistic Mean-Field Hadronic Models under Nuclear Matter Constraints
• Neutron star radii and crusts: uncertainties and unified equations of state
• The enhanced X-ray Timing and Polarimetry mission - eXTP
• On the Sound Speed in Neutron Stars
• Astrophysical Constraints on the Symmetry Energy and the Neutron Skin of ${}^{208}$Pb with Minimal Modeling Assumptions
• Dense matter with eXTP
• Direct Astrophysical Tests of Chiral Effective Field Theory at Supranuclear Densities
• PSR J1810+1744: Companion Darkening and a Precise High Neutron Star Mass
• Ab-initio QCD calculations impact the inference of the neutron-star-matter equation of state
• Mapping neutron star data to the equation of state using the deep neural network
• Nested Sampling Methods
• Strong correlations of neutron star radii with the slopes of nuclear matter incompressibility and symmetry energy at saturation
• A Detailed Examination of Astrophysical Constraints on the Symmetry Energy and the Neutron Skin of ${}^{208}$Pb with Minimal Modeling Assumptions
• Relativistic description of dense matter equation of state and compatibility with neutron star observables: a Bayesian approach
• Methodology study of machine learning for the neutron star equation of state
• Investigating Signatures of Phase Transitions in Neutron-Star Cores
• Neural networks reconstruction of the dense-matter equation of state from neutron-star parameters
• Extensive Studies of the Neutron Star Equation of State from the Deep Learning Inference with the Observational Data Augmentation
• Spanning the full range of neutron star properties within a microscopic description
• Deep-Learning Jets with Uncertainties and More
• Neural network reconstruction of the dense matter equation of state from neutron star observables
• Reconstructing the neutron star equation of state from observational data via automatic differentiation
• Bayesian nonparametric inference of neutron star equation of state via neural network
• Unveiling the nuclear matter EoS from neutron star properties: a supervised machine learning approach
• Detection of Gravitational Waves Using Bayesian Neural Networks
• Thermal evolution of relativistic hyperonic compact stars with calibrated equations of state
• Translating neutron star observations to nuclear symmetry energy via artificial neural networks
• Bayesian reconstruction of nuclear matter parameters from the equation of state of neutron star matter
• Empirical constraints on the high-density equation of state from multi-messenger observables
• Extracting nuclear matter properties from the neutron star matter equation of state using deep neural networks
• Deducing Neutron Star Equation of State Parameters Directly From Telescope Spectra with Uncertainty-Aware Machine Learning
• Structure of Quark Star: A Comparative Analysis of Bayesian Inference and Neural Network Based Modeling
• Determination of the symmetry energy from the neutron star equation of state
• Nonparametric model for the equations of state of neutron star from deep neural network
• The Neutron Star Outer Crust Equation of State: A Machine Learning approach
• Nonparametric Representation of Neutron Star Equation of State Using Variational Autoencoder
• Detecting dense-matter phase transition signatures in neutron star mass-radius measurements as data anomalies using normalising flows

Cited by in corpus (14)

• Physics-Driven Learning for Inverse Problems in Quantum Chromodynamics
• Dense Matter in Neutron Stars with eXTP
• Applications of machine learning in gravitational wave research with current interferometric detectors
• Towards Uncovering Dark Matter Effects on Neutron Star Properties: A Machine Learning Approach
• From NS observations to nuclear matter properties: a machine learning approach
• Implications of latest NICER data for the neutron star equation of state
• Neural Simulation-Based Inference of the Neutron Star Equation of State directly from Telescope Spectra
• Deep learning inference of the neutron star equation of state
• Inferring the Equation of State from Neutron Star Observables via Machine Learning
• Mass and tidal parameter extraction from gravitational waves of binary neutron stars mergers using deep learning
• Detecting Hyperons in neutron stars -- a machine learning approach
• Insights Into Neutron Stars From Gravitational Redshifts and Universal Relations
• Conditional variational autoencoder inference of neutron star equation of state from astrophysical observations
• Detecting the third family of compact stars with normalizing flows