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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Huang, Yiming, Chen, Jinhui, Jia, Jiangyong, Liu, Lu-Meng, Ma, Yu-Gang, Zhang, Chunjian
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917957767004160
author Huang, Yiming
Chen, Jinhui
Jia, Jiangyong
Liu, Lu-Meng
Ma, Yu-Gang
Zhang, Chunjian
author_facet Huang, Yiming
Chen, Jinhui
Jia, Jiangyong
Liu, Lu-Meng
Ma, Yu-Gang
Zhang, Chunjian
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_01352
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Validation and extrapolation of atomic mass with physics-informed fully connected neural network
Huang, Yiming
Chen, Jinhui
Jia, Jiangyong
Liu, Lu-Meng
Ma, Yu-Gang
Zhang, Chunjian
Nuclear Theory
Nuclear Experiment
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.
title Validation and extrapolation of atomic mass with physics-informed fully connected neural network
topic Nuclear Theory
Nuclear Experiment
url https://arxiv.org/abs/2501.01352