Nuclear masses in extended kernel ridge regression with odd-even effects

Abstract

The kernel ridge regression (KRR) approach is extended to include the odd-even effects in nuclear mass predictions by remodulating the kernel function without introducing new weight parameters and inputs in the training network. By taking the WS4 mass model as an example, the mass for each nucleus in the nuclear chart is predicted with the extended KRR network, which is trained with the mass model residuals, i.e., deviations between experimental and calculated masses, of other nuclei with known masses. The resultant root-mean-square mass deviation from the available experimental data for the 2353 nuclei with $Z\ge 8$ and $N\ge 8$ can be reduced to 128 keV, which provides the most precise mass model from machine learning approaches so far. Moreover, the extended KRR approach can avoid the risk of worsening the mass predictions for nuclei at large extrapolation distances, and meanwhile, it provides a smooth extrapolation behavior with respect to the odd and even extrapolation distances.

arXiv comment6 pages,3 figures

References in corpus (21)

• Nuclear ground-state masses and deformations: FRDM(2012)
• New parametrization for the nuclear covariant energy density functional with point-coupling interaction
• Surface diffuseness correction in global mass formula
• The impact of individual nuclear properties on $r$-process nucleosynthesis
• Nuclear mass predictions based on Bayesian neural network approach with pairing and shell effects
• The limits of the nuclear landscape explored by the relativistic continuum Hatree-Bogoliubov theory
• 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
• Bayesian approach to model-based extrapolation of nuclear observables
• Direct mapping of nuclear shell effects in the heaviest elements
• Nuclear mass predictions with radial basis function approach
• Mapping the proton drip-line up to A=70
• Nuclear landscape in covariant density functional theory
• Refining mass formulas for astrophysical applications: a Bayesian neural network approach
• Global study of beyond-mean-field correlation energies in covariant energy density functional theory using a collective Hamiltonian method
• Nuclear masses set bounds on quantum chaos
• Radial basis function approach in nuclear mass predictions
• Crucial test for covariant density functional theory with new and accurate mass measurements from Sn to Pa
• High precision nuclear mass predictions towards a hundred kilo-electron-volt accuracy
• Improved radial basis function approach with the odd-even corrections
• Nuclear chart in covariant density functional theory with dynamical correlations: From Oxygen to Tin

Cited by in corpus (14)

• Machine Learning in Nuclear Physics
• Machine learning the nuclear mass
• Multi-task learning on nuclear masses and separation energies with the kernel ridge regression
• Nuclear energy density functionals from machine learning
• Improved phenomenological nuclear charge radius formulae with kernel ridge regression
• Nuclear charge radius predictions by kernel ridge regression with odd-even effects
• Principal components of nuclear mass models
• Nuclear mass predictions based on convolutional neural network
• Machine learning light hypernuclei
• High Precision Binding Energies from Physics Informed Machine Learning
• Correlation between U/Th and Pb/Os abundance ratios and its application in nuclear cosmochronology
• Nuclear mass predictions based on deep neural network and finite-range droplet model (2012)
• Exploratory study on the masses of odd-$Z$ nuclei and $r$-process simulation based on the deformed relativistic Hartree-Bogoliubov theory in continuum
• Principal Components of Nuclear Mass Model Residuals