A Kohn-Sham Scheme Based Neural Network for Nuclear Systems

TL;DR

This paper introduces a neural network model based on the Kohn-Sham scheme to predict nuclear shell evolution, improving extrapolation and predictive capabilities for nuclear properties using supervised learning on density functional theory data.

Contribution

It presents a novel multi-task neural network approach incorporating the Kohn-Sham scheme for nuclear system predictions, enhancing extrapolation and observable correlations.

Findings

Good agreement with benchmark results for untrained nuclei.

Significant improvement in nuclear density extrapolation.

Enhanced predictive capability after charge-radius calibration.

Abstract

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.