Nuclear binding energies in artificial neural networks

TL;DR

This paper demonstrates that artificial neural networks can accurately predict nuclear binding energies with better precision than traditional models, highlighting the importance of feature engineering for physical systems with limited data.

Contribution

The study introduces a neural network approach with optimized feature engineering to improve nuclear binding energy predictions beyond existing models.

Findings

ANN achieves RMSD around 0.2 MeV for all nuclei in AME2020

ANN outperforms traditional models like FRDM and WS4

ANN shows strong extrapolation ability for inaccessible nuclei

Abstract

The binding energy (BE) or mass is one of the most fundamental properties of an atomic nucleus. Precise binding energies are vital inputs for many nuclear physics and nuclear astrophysics studies. However, due to the complexity of atomic nuclei and of the non-perturbative strong interaction, up to now, no conventional physical model can describe nuclear binding energies with a precision below 0.1 MeV, the accuracy needed by nuclear astrophysical studies. In this work, artificial neural networks (ANNs), the so called ``universal approximators", are used to calculate nuclear binding energies. We show that the ANN can describe all the nuclei in AME2020 with a root-mean-square deviation (RMSD) around 0.2 MeV, which is better than the best macroscopic-microscopic models, such as FRDM and WS4. The success of the ANN is mainly due to the proper and essential input features we identify, which contain the most relevant physical information, i.e., shell, paring, and isospin-asymmetry effects. We show that the well-trained ANN has excellent extrapolation ability and can predict binding energies for those nuclei so far inaccessible experimentally. In particular, we highlight the important role played by ``feature engineering'' for physical systems where data are relatively scarce, such as nuclear binding energies.