Nuclear masses learned from a probabilistic neural network

Abstract

Machine learning methods and uncertainty quantification have been gaining interest throughout the last several years in low-energy nuclear physics. In particular, Gaussian processes and Bayesian Neural Networks have increasingly been applied to improve mass model predictions while providing well-quantified uncertainties. In this work, we use the probabilistic Mixture Density Network (MDN) to directly predict the mass excess of the 2016 Atomic Mass Evaluation within the range of measured data, and we extrapolate the inferred models beyond available experimental data. The MDN not only provides mean values but also full posterior distributions both within the training set and extrapolated testing set. We show that the addition of physical information to the feature space increases the accuracy of the match to the training data as well as provides for more physically meaningful extrapolations beyond the the limits of experimental data.

10 pages, 3 figures, under review with Phys. Rev. C

References in corpus (11)

• Further improvements on a global nuclear mass model
• Nuclear charge radii: Density functional theory meets Bayesian neural networks
• Uncertainty Quantification for Nuclear Density Functional Theory and Information Content of New Measurements
• Global sensitivity analysis of bulk properties of an atomic nucleus
• Get on the BAND Wagon: A Bayesian Framework for Quantifying Model Uncertainties in Nuclear Dynamics
• Rigorous constraints on three-nucleon forces in chiral effective field theory from fast and accurate calculations of few-body observables
• Direct comparison between Bayesian and frequentist uncertainty quantification for nuclear reactions
• Bayesian Methods for Parameter Estimation in Effective Field Theories
• Beyond the proton drip line: Bayesian analysis of proton-emitting nuclei
• Uncertainty Quantification for Optical Model Parameters
• Optimizing multilayer Bayesian neural networks for evaluation of fission yields

Cited by in corpus (17)

• Machine Learning in Nuclear Physics
• Physically Interpretable Machine Learning for nuclear masses
• Nuclear mass predictions using machine learning models
• Nuclear mass predictions based on convolutional neural network
• Modeling Heavy-Ion Fusion Cross Section Data via a Novel Artificial Intelligence Approach
• Kolmogorov-Arnold networks in nuclear binding energy prediction
• Building Surrogate Models of Nuclear Density Functional Theory with Gaussian Processesand Autoencoders
• High Precision Binding Energies from Physics Informed Machine Learning
• Neural Network Emulation of Flow in Heavy-Ion Collisions at Intermediate Energies
• Shell quenching in nuclear charge radii based on Monte Carlo dropout Bayesian neural network
• Quantifying uncertainty in machine learning on nuclear binding energy
• Investigating the effects of precise mass measurements of Ru and Pd isotopes on machine learning mass modeling
• Iso-scalar liquid drop model
• Bayesian model mixing with multi-reference energy density functional
• Further exploration of binding energy residuals using machine learning and the development of a composite ensemble model
• Nuclear data activities for medium mass and heavy nuclei at Los Alamos
• Bayesian method for fitting the low-energy constants in chiral perturbation theory