Machine-learning modeling of nuclear collective observables and low-lying spectra
Abstract
Potential energy surfaces and collective inertial functions are essential microscopic inputs for describing nuclear large-amplitude collective motions such as rotation, vibration, and fission. We develop the Nuclear Collective Generator (NCG), a machine-learning framework that predicts the collective potential and six collective inertial functions on the quadrupole deformation (β,γ) plane from proton and neutron numbers and shell-effect descriptors, providing the microscopic inputs for the five-dimensional collective Hamiltonian (5DCH) used to describe low-lying spectra in even-even nuclei. The NCG combines weighted supervised learning, adversarial refinement, and ensemble averaging to improve reconstruction fidelity and prediction stability. Across 568 even-even nuclei, the reconstructed collective potentials reproduce the covariant density functional theory (CDFT) results with a mean root-mean-square deviation of 0.58~MeV. When propagated through the 5DCH solver, the NCG inputs reproduce the global systematics of equilibrium deformations, low-lying excitation spectra, and electric-quadrupole transition strengths. Near the Z=82 shell closure, the NCG softens the collective potential along the γ direction, reducing the overestimated collectivity of the original CDFT+5DCH calculations and bringing the B(E2) values closer to experimental data. These results demonstrate that the NCG provides an accurate surrogate for global microscopic collective calculations while retaining their essential physical content.
Related
- Active-subspace learning reveals dominant parameter directions in nuclear observables
- Learning to Program Adaptive Non-Local Observables for Machine Learning
- Machine Learning β-decay Half-lives and Their Application to r-Process Observables
- The Information Content of Krylov Observables: A Machine Learning Approach
- Advancing Nuclear Physics with Machine Learning and Artificial Intelligence
BibTeX
@misc{shi2026machinelearning,
title = {{Machine-learning modeling of nuclear collective observables and low-lying spectra}},
author = {Dan Shi and Zu-Xing Yang and Xiao-Hua Fan and Zhi-Pan Li},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.25888},
eprint = {2609.25888},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.25888},
}
RIS
TY - UNPB
TI - Machine-learning modeling of nuclear collective observables and low-lying spectra
AU - Dan Shi
AU - Zu-Xing Yang
AU - Xiao-Hua Fan
AU - Zhi-Pan Li
PY - 2026
DA - 2026/09/22
PB - arXiv
DO - 10.48550/arxiv.2609.25888
UR - https://arxiv.org/abs/2609.25888
AB - Potential energy surfaces and collective inertial functions are essential microscopic inputs for describing nuclear large-amplitude collective motions such as rotation, vibration, and fission. We develop the Nuclear Collective Generator (NCG), a machine-learning framework that predicts the collective potential and six collective inertial functions on the quadrupole deformation (β,γ) plane from proton and neutron numbers and shell-effect descriptors, providing the microscopic inputs for the five-dimensional collective Hamiltonian (5DCH) used to describe low-lying spectra in even-even nuclei. The NCG combines weighted supervised learning, adversarial refinement, and ensemble averaging to improve reconstruction fidelity and prediction stability. Across 568 even-even nuclei, the reconstructed collective potentials reproduce the covariant density functional theory (CDFT) results with a mean root-mean-square deviation of 0.58~MeV. When propagated through the 5DCH solver, the NCG inputs reproduce the global systematics of equilibrium deformations, low-lying excitation spectra, and electric-quadrupole transition strengths. Near the Z=82 shell closure, the NCG softens the collective potential along the γ direction, reducing the overestimated collectivity of the original CDFT+5DCH calculations and bringing the B(E2) values closer to experimental data. These results demonstrate that the NCG provides an accurate surrogate for global microscopic collective calculations while retaining their essential physical content.
ER -