Nuclear mass predictions based on Bayesian neural network approach with pairing and shell effects

Abstract

Bayesian neural network (BNN) approach is employed to improve the nuclear mass predictions of various models. It is found that the noise error in the likelihood function plays an important role in the predictive performance of the BNN approach. By including a distribution for the noise error, an appropriate value can be found automatically in the sampling process, which optimizes the nuclear mass predictions. Furthermore, two quantities related to nuclear pairing and shell effects are added to the input layer in addition to the proton and mass numbers. As a result, the theoretical accuracies are significantly improved not only for nuclear masses but also for single-nucleon separation energies. Due to the inclusion of the shell effect, in the unknown region, the BNN approach predicts a similar shell-correction structure to that in the known region, e.g., the predictions of underestimation of nuclear mass around the magic numbers in the relativistic mean-field model. This manifests that better predictive performance can be achieved if more physical features are included in the BNN approach.

15 pages, 4 figures, and 3 tables

References in corpus (21)

• Relativistic Continuum Hartree Bogoliubov Theory for Ground State Properties of Exotic Nuclei
• Surface diffuseness correction in global mass formula
• Nuclear Energy Density Optimization
• Skyrme-Hartree-Fock-Bogoliubov nuclear mass formulas: Crossing the 0.6 MeV threshold with microscopically deduced pairing
• Superallowed 0+ --> 0+ nuclear beta decays: 2014 critical survey, with precise results for Vud and CKM unitarity
• Multi chiral-doublets in one single nucleus
• Masses, Deformations and Charge Radii--Nuclear Ground-State Properties in the Relativistic Mean Field Model
• Nuclear Mass Predictions for the Crustal Composition of Neutron Stars: A Bayesian Neural Network Approach
• Spin-isospin resonances: A self-consistent covariant description
• $\beta$-decay half-lives of neutron-rich nuclei and matter flow in the $r$-process
• Nuclear charge radii: Density functional theory meets Bayesian neural networks
• Isospin corrections for superallowed Fermi beta decay in self-consistent relativistic random phase approximation approaches
• Nuclear mass systematics using neural networks
• Application of the RMF mass model to the r-process and the influence of mass uncertainties
• Self-consistent relativistic quasiparticle random-phase approximation and its applications to charge-exchange excitations and $\beta$-decay half-lives
• Decoding Beta-Decay Systematics: A Global Statistical Model for Beta^- Halflives
• Influence of nuclear physics inputs and astrophysical conditions on Th/U chronometer
• Radial basis function approach in nuclear mass predictions
• Reexamining the temperature and neutron density conditions for r-process nucleosynthesis with augmented nuclear mass models
• Improved radial basis function approach with the odd-even corrections
• Toward precision mass measurements of neutron-rich nuclei relevant to $r$-process nucleosynthesis

Cited by in corpus (69)

• Machine Learning in Nuclear Physics
• Bayesian approach to model-based extrapolation of nuclear observables
• r-Process Nucleosynthesis: Connecting Rare-Isotope Beam Facilities with the Cosmos
• 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
• Machine learning the nuclear mass
• Bayesian Evaluation of Incomplete Fission Yields
• Mapping neutron star data to the equation of state using the deep neural network
• Nuclear mass predictions with machine learning reaching the accuracy required by $r$-process studies
• Quantified limits of the nuclear landscape
• 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
• Methodology study of machine learning for the neutron star equation of state
• Nuclear masses in extended kernel ridge regression with odd-even effects
• Multi-task learning on nuclear masses and separation energies with the kernel ridge regression
• Physically Interpretable Machine Learning for nuclear masses
• Beyond the proton drip line: Bayesian analysis of proton-emitting nuclei
• Extensive Studies of the Neutron Star Equation of State from the Deep Learning Inference with the Observational Data Augmentation
• Skyrme-Hartree-Fock-Bogoliubov mass models on a 3D Mesh: Effect of triaxial shape
• Nuclear energy density functionals from machine learning
• Bayesian evaluation of charge yields of fission fragments of 239U
• Nuclear mass predictions using machine learning models
• Statistical aspects of nuclear mass models
• Prediction of Nuclear Charge Density Distribution with Feedback Neural Network
• Nuclear binding energy predictions using neural networks: Application of the multilayer perceptron
• Improved phenomenological nuclear charge radius formulae with kernel ridge regression
• Sensitivity study of \emph{r}-process abundances to nuclear masses
• The description of giant dipole resonance key parameters with multitask neural networks
• Optimizing multilayer Bayesian neural networks for evaluation of fission yields
• Impact of statistical uncertainties on the composition of the outer crust of a neutron star
• Revealing the nature of hidden charm pentaquarks with machine learning
• Providing physics guides in Bayesian neural networks from input layer: case of giant dipole resonance predictions
• Decay of superheavy nuclei based on the random forest algorithm
• Bayesian evaluation of residual production cross sections in proton induced spallation reactions
• A Bayesian-Neural-Network Prediction for Fragment Production in Proton Induced Spallation Reaction
• Bayesian Data Fusion of Imperfect Fission Yields for Augmented Evaluations
• Principal components of nuclear mass models
• Calculation of $\beta$-decay half-lives with Skyrme Hartree-Fock-Bogoliubov+$pn$-QRPA and isoscalar pairing strengths optimized by a Bayesian method
• Nuclear mass predictions based on convolutional neural network
• Calibration of nuclear charge density distribution by back-propagation neural networks
• Interval Load Forecasting for Individual Households in the Presence of Electric Vehicle Charging
• Application of multilayer perceptron with data augmentation in nuclear physics
• The Neutron Star Outer Crust Equation of State: A Machine Learning approach
• Constraining the Woods-Saxon potential in fusion reactions based on the neural network
• 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
• Machine learning spectral functions in lattice QCD
• Building Surrogate Models of Nuclear Density Functional Theory with Gaussian Processesand Autoencoders
• Machine learning light hypernuclei
• Calibration of Energy Density Functionals with Deformed Nuclei
• New high-spin structure and possible chirality in ${}^{109}$In
• Statistical learnability of nuclear masses
• A Neural Network Approach for Orienting Heavy-Ion Collision Events
• Correlation between U/Th and Pb/Os abundance ratios and its application in nuclear cosmochronology
• Nuclear binding energy predictions based on BP neural network
• KIDS density functional for deformed nuclei: Examples of the even-even Nd isotopes
• From masses and radii of neutron stars to EOS of nuclear matter through neural network
• Nuclear mass predictions based on deep neural network and finite-range droplet model (2012)
• Inference of Parameters for Back-shifted Fermi Gas Model using Feedback Neural Network
• Shell quenching in nuclear charge radii based on Monte Carlo dropout Bayesian neural network
• Report from the A.I. For Nuclear Physics Workshop
• Bayesian model mixing with multi-reference energy density functional
• FRIB and the GW170817 Kilonova
• Relativistic correction of the Coulomb interaction in the local density approximation for energies and radii in doubly-magic nuclei
• Impact of the nuclear mass uncertainties on the r process
• Impact of nuclear masses on r-process nucleosynthesis: bulk properties versus shell effects
• Further exploration of the machine-learning-based nuclear mass table
• Principal Components of Nuclear Mass Model Residuals