Taming nucleon density distributions with deep neural network method

Abstract

We investigate the density distributions of finite nuclei employing a well-designed deep neural network method. We calculate the target nucleon density distributions with Skyrme density functional theories, which are used to train the networks. We find that the training with only about $10\%$ nuclei ($300-400$) is sufficient to describe the nucleon density distributions of all the nuclear chart within 2\% relative error. The relative error comes to 5\% when about 200 proton(neutron) density distributions are used for training. We obtained very similar results for different Skyrme density functional theories. Therefore the ability to train networks is weakly dependent on the theoretical model. Moreover, in the process of machine learning, there is a turning point showing the transition from the Fermi-like distribution to the realistic Skyrme distribution, which provides significant properties of convergence process.

arXiv comment7 pages, 6 figures

References in corpus (20)

• Ab initio limits of atomic nuclei
• Equivariant flow-based sampling for lattice gauge theory
• Importance Truncation for Large-Scale Configuration Interaction Approaches
• Collective Modes in Light Nuclei from First Principles
• Mapping neutron star data to the equation of state using the deep neural network
• A proton density bubble in the doubly magic ${}^{34}$Si nucleus
• Evidence for Symplectic Symmetry in Ab Initio No-Core Shell Model Results for Light Nuclei
• Taming nuclear complexity with a committee of multilayer neural networks
• Deep learning: Extrapolation tool for ab initio nuclear theory
• Machine learning the deuteron
• Short-range correlations in nuclei with similarity renormalization group transformations
• Three-body force effect on nucleon momentum distributions in asymmetric nuclear matter within the framework of the extended BHF approach
• Two-neutron halo structure of ${}^{31}$F
• Neutron rich matter in the laboratory and in the heavens after GW170817
• Neutron skins as laboratory constraints on properties of neutron stars and on what we can learn from heavy ion fragmentation reactions
• Nucleon momentum distributions in asymmetric nuclear matter
• Coulomb exchange functional with generalized gradient approximation for self-consistent Skyrme Hartree-Fock calculations
• Influence of pairing correlations on the radius of neutron-rich nuclei
• Investigation of neutron density distribution of ${}^{208}$Pb nucleus when the proton density is constrained to its experimental distribution
• The influence of the neutron skin and the asymmetry energy on the ${\pi }^{-}/{\pi }^{+}$ ratio

Cited by in corpus (5)

• Global prediction of nuclear charge density distributions using deep neural network
• Calibration of nuclear charge density distribution by back-propagation neural networks
• A Kohn-Sham Scheme Based Neural Network for Nuclear Systems
• Impact of quadrupole deformation on intermediate-energy heavy-ion collisions
• Inference of Parameters for Back-shifted Fermi Gas Model using Feedback Neural Network