Systematics on ground-state energies of nuclei within the neural networks

TL;DR

This paper demonstrates that artificial neural networks can effectively model nuclear ground-state properties, such as binding energies and separation energies, based on data from Hartree-Fock-Bogolibov calculations, aiding in nuclear systematics beyond experimental data.

Contribution

The study introduces a neural network approach to predict nuclear properties from HFB data, providing a new statistical tool for nuclear systematics beyond experimental limits.

Findings

ANNs successfully modeled binding energies and separation energies.

Statistical modeling aids in exploring nuclei beyond experimental data.

The approach offers a potential tool for nuclear data systematics.

Abstract

One of the fundamental ground-state properties of nuclei is binding energy. In this study, we have employed artificial neural networks (ANNs) to obtain binding energies based on the data calculated from Hartree-Fock-Bogolibov (HFB) method with the two SLy4 and SKP Skyrme forces. Also, ANNs have been employed to obtain two-neutron and two-proton separation energies of nuclei. Statistical modeling of nuclear data using ANNs has been seen as to be successful in this study. Such a statistical model can be possible tool for searching in systematics of nuclei beyond existing experimental nuclear data.