Neutron star envelopes with machine learning: a single-hidden-layer neural network application
arXiv:2509.03090 · doi:10.1051/0004-6361/202554742
Abstract
Thermal and magneto-thermal simulations are an important tool for advancing understanding of neutron stars, as they allow us to compare models of their internal structure and physical processes against observations constraining macroscopic properties such as the surface temperature. A major challenge in the simulations is in modelling of the outermost layers, known as the envelope, exhibiting a drop of many orders of magnitude in temperature and density in a geometrically thin shell. This is often addressed by constructing a separate envelope model in plane-parallel approximation that produces a relation between the temperature at the bottom of the envelope, , and the surface temperature, . Our aim is to construct a general framework for approximating the - relation that is able to include the dependencies from the strength and orientation of the magnetic field. We used standard prescriptions to calculate a large number of magnetised envelope models to be used as a training sample and employed single-hidden-layer feedforward neural networks as approximators, providing the flexibility, high accuracy, and fast evaluation necessary in neutron star simulations. We explored the optimal network architecture and hyperparameter choices and used a special holdout set designed to avoid overfitting to the structure of the input data. We find that relatively simple neural networks are sufficient for the approximation of the - relation with an accuracy . The presented workflow can be used in a wide range of problems where simulations are used to construct approximating formulae.
8 pages, 9 figures, accepted for publication in A&A; see also De Grandis, Kovlakas & Rea in press (10.1051/0004-6361/202554666)
References in corpus (21)
- Neutrino Emission from Neutron Stars
- Minimal Cooling of Neutron Stars: A New Paradigm
- ANNz: estimating photometric redshifts using artificial neural networks
- Improving galaxy morphologies for SDSS with Deep Learning
- A catalog of visual-like morphologies in the 5 CANDELS fields using deep-learning
- Neutron stars - cooling and transport
- Thermal structure and cooling of superfluid neutron stars with accreted magnetized envelopes
- On the approximation by single hidden layer feedforward neural networks with fixed weights
- Magnetic, thermal and rotational evolution of isolated neutron stars
- Deep learning for galaxy surface brightness profile fitting
- Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy
- Equation of state for magnetized Coulomb plasmas
- Heat blanketing envelopes and thermal radiation of strongly magnetized neutron stars
- 3D modelling of magneto-thermal evolution of neutron stars: method and test cases
- Sleeping beasts: strong toroidal magnetic field in quiescent magnetars explains their large pulsed fraction
- Heat blanketing envelopes of neutron stars
- Diffusive heat blanketing envelopes of neutron stars
- 3D code for MAgneto-Thermal evolution in Isolated Neutron Stars, MATINS: The Magnetic Field Formalism
- 3D code for MAgneto-Thermal evolution in Isolated Neutron Stars, MATINS: thermal evolution and lightcurves
- The hunt for new pulsating ultraluminous X-ray sources: a clustering approach
- Magnetar Outburst Models with Cooling Simulations