Nuclear mass predictions based on deep neural network and finite-range droplet model (2012)

Abstract

A neural network with two hidden layers is developed for nuclear mass prediction, based on the finite-range droplet model (FRDM12). Different hyperparameters, including the number of hidden units, the choice of activation functions, the initializers, and the learning rates, are adjusted explicitly and systematically. The resulting mass predictions are achieved by averaging the predictions given by several different sets of hyperparameters with different regularizers and seed numbers. It can provide us not only the average values of mass predictions but also reliable estimations in the mass prediction uncertainties. The overall root-mean-square deviations of nuclear mass have been reduced from $0.603$ MeV for the FRDM12 model to $0.200$ MeV and $0.232$ MeV for the training set and validation set, respectively.

arXiv comment12 pages, 12 figures, and 1 table

References in corpus (20)

• 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
• Skyrme-Hartree-Fock-Bogoliubov nuclear mass formulas: Crossing the 0.6 MeV threshold with microscopically deduced pairing
• The impact of individual nuclear properties on $r$-process nucleosynthesis
• Machine Learning in Nuclear Physics
• Nuclear mass predictions based on Bayesian neural network approach with pairing and shell effects
• Predictions of nuclear $\beta$-decay half-lives with machine learning and their impacts on $r$ process
• Machine learning and density functional theory
• Machine learning the nuclear mass
• Nuclear mass predictions with machine learning reaching the accuracy required by $r$-process studies
• Impact of nuclear mass uncertainties on the $r$-process
• 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
• Radial basis function approach in nuclear mass predictions
• Nuclear masses in extended kernel ridge regression with odd-even effects
• Nuclear binding energy predictions using neural networks: Application of the multilayer perceptron
• Application Of Support Vector Machines To Global Prediction Of Nuclear Properties
• Calculation of $\beta$-decay half-lives with Skyrme Hartree-Fock-Bogoliubov+$pn$-QRPA and isoscalar pairing strengths optimized by a Bayesian method

Cited by in corpus (1)

• Further exploration of the machine-learning-based nuclear mass table