Nuclear charge radii: Density functional theory meets Bayesian neural networks

Abstract

The distribution of electric charge in atomic nuclei is fundamental to our understanding of the complex nuclear dynamics and a quintessential observable to validate nuclear structure models. We explore a novel approach that combines sophisticated models of nuclear structure with Bayesian neural networks (BNN) to generate predictions for the charge radii of thousands of nuclei throughout the nuclear chart. A class of relativistic energy density functionals is used to provide robust predictions for nuclear charge radii. In turn, these predictions are refined through Bayesian learning for a neural network that is trained using residuals between theoretical predictions and the experimental data. Although predictions obtained with density functional theory provide a fairly good description of experiment, our results show significant improvement (better than 40%) after BNN refinement. Moreover, these improved results for nuclear charge radii are supplemented with theoretical error bars. We have successfully demonstrated the ability of the BNN approach to significantly increase the accuracy of nuclear models in the predictions of nuclear charge radii. However, as many before us, we failed to uncover the underlying physics behind the intriguing behavior of charge radii along the calcium isotopic chain.

arXiv comment14 pages, 6 figures

References in corpus (27)

• Nuclear Ground-State Masses and Deformations
• A New Parameterization for the Lagrangian Density of Relativistic Mean Field Theory
• Neutron Star Structure and the Neutron Radius of 208Pb
• Recent Progress in Quantum Hadrodynamics
• Neutron-Rich Nuclei in Heaven and Earth
• Microscopic mass formulae
• Further explorations of Skyrme-Hartree-Fock-Bogoliubov mass formulas. XII: Stiffness and stability of neutron-star matter
• Nuclear Energy Density Optimization
• Relativistic Mean-Field Theory and the High-Density Nuclear Equation of State
• The impact of individual nuclear properties on $r$-process nucleosynthesis
• Unexpectedly large charge radii of neutron-rich calcium isotopes
• Nuclear isotope shifts within the local energy-density functional approach
• Building relativistic mean field models for finite nuclei and neutron stars
• Evolution of shell structure in neutron-rich calcium isotopes
• Nuclear Mass Predictions for the Crustal Composition of Neutron Stars: A Bayesian Neural Network Approach
• Searching for isovector signatures in the neutron-rich oxygen and calcium isotopes
• Shell Model Description of Isotope Shifts in Calcium
• Energy density functional for nuclei and neutron stars
• Nuclear mass systematics using neural networks
• Systematics on ground-state energies of nuclei within the neural networks
• An artificial neural network application on nuclear charge radii
• Nuclear masses set bounds on quantum chaos
• Decoding Beta-Decay Systematics: A Global Statistical Model for Beta^- Halflives
• Garvey-Kelson Relations for Nuclear Charge Radii
• New charge radius relations for atomic nuclei
• Neutron Skins and Halo Orbits in the $sd$ and $pf$ shells
• Application Of Support Vector Machines To Global Prediction Of Nuclear Properties

Cited by in corpus (54)

• Machine Learning in Nuclear Physics
• Nuclear mass predictions based on Bayesian neural network approach with pairing and shell effects
• Bayesian approach to model-based extrapolation of nuclear observables
• Laser Spectroscopy for the Study of Exotic Nuclei
• Towards the global description of nuclear charge radii: exploring the Fayans energy density functional
• Refining mass formulas for astrophysical applications: a Bayesian neural network approach
• Taming nuclear complexity with a committee of multilayer neural networks
• Study of Charge Radii with Neural Networks
• Novel Bayesian neural network based approach for nuclear charge radii
• Charge radii in covariant density functional theory: a global view
• Deep learning: Extrapolation tool for ab initio nuclear theory
• Nuclear charge radii in Bayesian neural networks revisited
• Nuclear masses learned from a probabilistic neural network
• Identifying the nature of the QCD transition in relativistic collision of heavy nuclei with deep learning
• Extrapolation of nuclear structure observables with artificial neural networks
• Nuclear energy density functionals from machine learning
• Validating neural-network refinements of nuclear mass models
• Bayesian evaluation of charge yields of fission fragments of 239U
• Constraining Transfer Cross Sections Using Bayes' Theorem
• Prediction of Nuclear Charge Density Distribution with Feedback Neural Network
• Improved phenomenological nuclear charge radius formulae with kernel ridge regression
• Magnetars and Axion-like Particles: Probes with the Hard X-ray Spectrum
• Machine learning-based inversion of nuclear responses
• Recent advances in the quantification of uncertainties in reaction theory
• Electroweak probes of ground state densities
• Nuclear charge radius predictions by kernel ridge regression with odd-even effects
• Optimizing multilayer Bayesian neural networks for evaluation of fission yields
• Odd-even staggering and shell effects of charge radii for nuclei with even $Z$ from $36$ to $38$ and from $52$ to $62$
• Decay of superheavy nuclei based on the random forest algorithm
• Providing physics guides in Bayesian neural networks from input layer: case of giant dipole resonance predictions
• A Bayesian-Neural-Network Prediction for Fragment Production in Proton Induced Spallation Reaction
• Global prediction of nuclear charge density distributions using deep neural network
• Machine Learning for the Prediction of Converged Energies from Ab Initio Nuclear Structure Calculations
• Bayesian Data Fusion of Imperfect Fission Yields for Augmented Evaluations
• Finding quark content of neutron stars in light of GW170817
• Nuclear mass predictions based on convolutional neural network
• First Excited 2+ Energy State Estimations of Even-even Nuclei by Using Artificial Neural Networks
• Calibration of nuclear charge density distribution by back-propagation neural networks
• Application of multilayer perceptron with data augmentation in nuclear physics
• The Neutron Star Outer Crust Equation of State: A Machine Learning approach
• A Kohn-Sham Scheme Based Neural Network for Nuclear Systems
• Optimization of generator coordinate method with machine-learning techniques for nuclear spectra and neutrinoless double-beta decay: ridge regression for nuclei with axial deformation
• Local variations of charge radii for nuclei with even $Z$ from 84 to 120
• Machine learning light hypernuclei
• Evolution of nuclear charge radii in copper and indium isotopes
• Emergence of low-energy monopole strength in the neutron-rich calcium isotopes
• A Neural Network Approach for Orienting Heavy-Ion Collision Events
• From masses and radii of neutron stars to EOS of nuclear matter through neural network
• Inference of Parameters for Back-shifted Fermi Gas Model using Feedback Neural Network
• Maximum mass of hybrid star formed via shock induced phase transition in cold neutron stars
• Shell quenching in nuclear charge radii based on Monte Carlo dropout Bayesian neural network
• Implication of shell quenching in scandium isotopes around N=20
• Bayesian model mixing with multi-reference energy density functional
• Finding signatures of the nuclear symmetry energy in heavy-ion collisions with deep learning