Calibration of nuclear charge density distribution by back-propagation neural networks

Abstract

Based on the back-propagation neural networks and density functional theory, a supervised learning is performed firstly to generate the nuclear charge density distributions. The charge density is further calibrated to the experimental charge radii by a composite loss function. It is found that, when the parity, pairing, and shell effects are taken into account, about $96\%$ of the nuclei in the validation set fall within two standard deviations of the predicted charge radii. The calibrated charge density is then mapped to the matter density, and further mapped to the binding energies according to the Hohenberg-Kohn theorem. It provides an improved description of some nuclei in both binding energies and charge radii. Moreover, the anomalous overbinding in ${}^{48}$Ca implies the existence of an indispensable beyond-mean-field effect.

References in corpus (36)

• Nuclear mass predictions based on Bayesian neural network approach with pairing and shell effects
• Nuclear Mass Predictions for the Crustal Composition of Neutron Stars: A Bayesian Neural Network Approach
• Importance Truncation for Large-Scale Configuration Interaction Approaches
• Neutron drip line in the Ca region from Bayesian model averaging
• Predictions of nuclear $\beta$-decay half-lives with machine learning and their impacts on $r$ process
• Nuclear charge radii: Density functional theory meets Bayesian neural networks
• Collective Modes in Light Nuclei from First Principles
• Deep Learning and Density Functional Theory
• Bayesian Evaluation of Incomplete Fission Yields
• 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
• Neutron skin thickness of heavy nuclei with $\alpha$-particle correlations and the slope of the nuclear symmetry energy
• Quantified limits of the nuclear landscape
• Nuclear mass systematics using neural networks
• Taming nuclear complexity with a committee of multilayer neural networks
• Study of Charge Radii with Neural Networks
• Laser spectroscopy of neutron-rich ${}^{207,208}$Hg isotopes: Illuminating the kink and odd-even staggering in charge radii across the $N=126$ shell closure
• Novel Bayesian neural network based approach for nuclear charge radii
• Deep learning the Hohenberg-Kohn maps of Density Functional Theory
• Charge radii in covariant density functional theory: a global view
• Deep learning: Extrapolation tool for ab initio nuclear theory
• Neural Networks for Impact Parameter Determination
• Bayesian evaluation of charge yields of fission fragments of 239U
• Short-range correlations in nuclei with similarity renormalization group transformations
• Application Of Support Vector Machines To Global Prediction Of Nuclear Properties
• Comparative study on charge radii and their kinks at magic numbers
• 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
• Taming nucleon density distributions with deep neural network method
• Influence of pairing correlations on the radius of neutron-rich nuclei
• Coulomb exchange functional with generalized gradient approximation for self-consistent Skyrme Hartree-Fock calculations
• Probing nuclear bubble configuration by proton induced reaction
• Comment on "Ab Initio study of 40-Ca with an importance-truncated no-core shell model"
• A Kohn-Sham Scheme Based Neural Network for Nuclear Systems
• Confinement in Nuclei and the Expanding Proton
• Charge radii of Ca isotopes and correlations

Cited by in corpus (6)

• Nuclear charge radius predictions by kernel ridge regression with odd-even effects
• Global prediction of nuclear charge density distributions using deep neural network
• Nuclear mass predictions based on convolutional neural network
• A Kohn-Sham Scheme Based Neural Network for Nuclear Systems
• Inference of Parameters for Back-shifted Fermi Gas Model using Feedback Neural Network
• Implication of shell quenching in scandium isotopes around N=20