A Kohn-Sham scheme based neural network for nuclear systems

A Kohn-Sham scheme based multi-task neural network is elaborated for the supervised learning of nuclear shell evolution. The training set is composed of the single-particle wave functions and occupation probabilities of 320 nuclei, calculated by the Skyrme density functional theory. It is found that the deduced density distributions, momentum distributions, and charge radii are in good agreements with the benchmarking results for the untrained nuclei. In particular, accomplishing shell evolution leads to a remarkable improvement in the extrapolation of nuclear density. After a further charge-radius-based calibration, the network evolves a stronger predictive capability. This opens the possibility to infer correlations among observables by combining experimental data for nuclear complex systems.(c) 2023 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons .org /licenses /by /4 .0/). Funded by SCOAP3.

Automated summary

In this study, a Kohn-Sham scheme based multi-task neural network is developed for supervised learning of nuclear shell evolution. The training set consists of single-particle wave functions and occupation probabilities of 320 nuclei obtained from Skyrme density functional theory. The deduced density distributions, momentum distributions, and charge radii show good agreements with benchmarking results for untrained nuclei. Shell evolution and charge-radius-based calibration further improve the network's predictive capability, opening up possibilities for inferring correlations among observables in nuclear complex systems.