Explainable autoencoder for neutron star dense matter parameter estimation
arXiv:2501.15222 · doi:10.1088/2632-2153/add3bd
Abstract
We present a physics-informed autoencoder designed to encode the equation of state of neutron stars into an interpretable latent space. In particular the input will be encoded in the mass, radius, and tidal deformability values of a neutron star. Unlike traditional black-box models, our approach incorporates additional loss functions to enforce explainability in the encoded representations. This method enhances the transparency of machine learning models in physics, providing a robust proof-of-concept tool to study compact stars data. Our results demonstrate that the proposed autoencoder not only accurately estimates the EoS parameters and central density/pressure but also offers insights into the physical connection between equation of state and observable physical quantities. This framework conceptualizes the physical differential equations themselves as the ``encoders", allowing interpretability of the latent space.
References in corpus (40)
- GW170817: Observation of Gravitational Waves from a Binary Neutron Star Inspiral
- Shapiro delay measurement of a two solar mass neutron star
- GW170817: Measurements of Neutron Star Radii and Equation of State
- Masses, Radii, and Equation of State of Neutron Stars
- A unified equation of state of dense matter and neutron star structure
- Properties of the binary neutron star merger GW170817
- Tidal deformability of neutron stars with realistic equations of state and their gravitational wave signatures in binary inspiral
- Composition and thermodynamics of nuclear matter with light clusters
- Constraints on a phenomenologically parameterized neutron-star equation of state
- The role of explainability in creating trustworthy artificial intelligence for health care: a comprehensive survey of the terminology, design choices, and evaluation strategies
- Neutron-Rich Nuclei in Heaven and Earth
- Relativistic Mean-Field Hadronic Models under Nuclear Matter Constraints
- Measuring the neutron star tidal deformability with equation-of-state-independent relations and gravitational waves
- Was GW190814 a black hole -- strange quark star system?
- New relativistic effective interaction for finite nuclei, infinite nuclear matter and neutron stars
- Mapping neutron star data to the equation of state using the deep neural network
- Binary Love Relations
- Methodology study of machine learning for the neutron star equation of state
- 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
- Neural network reconstruction of the dense matter equation of state from neutron star observables
- Updated universal relations for tidal deformabilities of neutron stars from phenomenological equations of state
- Reconstructing the neutron star equation of state from observational data via automatic differentiation
- Unveiling the nuclear matter EoS from neutron star properties: a supervised machine learning approach
- Bayesian nonparametric inference of neutron star equation of state via neural network
- A review of unsupervised learning in astronomy
- Reliability and Interpretability in Science and Deep Learning
- Upper limit set by causality on the tidal deformability of a neutron star
- Translating neutron star observations to nuclear symmetry energy via artificial neural networks
- Is the compact object associated with HESS J1731-347 a strange quark star?
- Extracting nuclear matter properties from the neutron star matter equation of state using deep neural networks
- Why can hadronic stars convert into strange quark stars with larger radii
- Tidal Deformability Doppelgangers: Implications of a low-density phase transition in the neutron star equation of state
- Detecting dense-matter phase transition signatures in neutron star mass-radius measurements as data anomalies using normalising flows
- Realizing the potential of deep neural network for analyzing neutron star observables and dense matter equation of state
- Merger of a Neutron Star with a Black Hole: one-family vs. two-families scenario
- Conditional variational autoencoder inference of neutron star equation of state from astrophysical observations
- Thermal fluctuations of matter composition and quark nucleation in compact stars
- Detecting the third family of compact stars with normalizing flows
- -mode oscillations of compact stars with realistic equations of state in dynamical spacetime