Validation and extrapolation of atomic mass with physics-informed fully connected neural network

TL;DR

This paper develops a physics-informed neural network approach for atomic mass prediction, achieving high accuracy and good extrapolation by integrating nuclear physics insights and sensitivity analysis.

Contribution

It introduces a novel neural network method that incorporates theoretical nuclear physics to improve atomic mass prediction and extrapolation performance.

Findings

Achieves a root-mean-square deviation of 0.122 MeV on AME2020 data.

Exhibits superior extrapolation with a deviation of 0.191 MeV from AME2016.

Reproduces key nuclear phenomena such as magic numbers and nucleon pairing.

Abstract

Machine learning offers a powerful framework for validating and predicting atomic mass. We compare three improved neural network methods for representation and extrapolation for atomic mass prediction. The powerful method, adopting a macroscopic-microscopic approach and treating complex nuclear effects as output labels, achieves superior accuracy in AME2020, yielding a much lower root-mean-square deviation of 0.122 MeV in the test set, significantly lower than alternative methods. It also exhibits a better extrapolation performance when predicting AME2020 from AME2016, with a root-mean-square deviation of 0.191 MeV. We further conduct sensitivity analyses against the model inputs to verify interpretable alignment beyond statistical metrics. Incorporating theoretical predictions of magic numbers and masses, our fully connected neural networks reproduce key nuclear phenomena including nucleon pairing correlation and magic number effects. The extrapolation capability of the framework is discussed and the accuracy of predicting new mass measurements for isotope chains has also been tested.