View in EDS

Extrapolation to infinite model space of no-core shell model calculations using machine learning.

Saved in:
Bibliographic Details
Title: Extrapolation to infinite model space of no-core shell model calculations using machine learning.
Authors: Mazur, Aleksandr1 (AUTHOR) 000287@togudv.ru, Sharypov, Roman1 (AUTHOR) 2017104939@togudv.ru, Shirokov, Andrey2 (AUTHOR) shirokov@nucl-th.sinp.msu.ru
Source: International Journal of Modern Physics E: Nuclear Physics. May2026, Vol. 35 Issue 5, p1-11. 11p.
Subject Terms: *Artificial neural networks, *Extrapolation, *Nuclear physics, *Nucleon-nucleon interactions, *Nuclear shell theory, *Atomic nucleus, *Nuclear structure, *Machine learning
Abstract: An ensemble of neural networks is employed to extrapolate no-core shell model (NCSM) results to infinite model space for light nuclei. We present a review of our neural network extrapolations of the NCSM results obtained with the Daejeon16 N N interaction in different model spaces and with different values of the NCSM basis parameter ℏ Ω for energies of nuclear states and root-mean-square (rms) radii of proton, neutron and matter distributions in light nuclei. The method yields convergent predictions with quantifiable uncertainties. Ground-state energies for 6Li, 6He and the unbound 6Be, as well as the excited (3 + , 0) and (0 + , 1) states of 6Li, are obtained within a few hundred keV of experiment. The extrapolated radii of bound states converge well. In contrast, radii of unbound states in 6Be and 6Li do not stabilize. These results demonstrate that machine-learning extrapolations can extend the reach of ab initio nuclear structure calculations with reliable accuracy. [ABSTRACT FROM AUTHOR]
Database: Energy & Power Source
Description
Abstract:An ensemble of neural networks is employed to extrapolate no-core shell model (NCSM) results to infinite model space for light nuclei. We present a review of our neural network extrapolations of the NCSM results obtained with the Daejeon16 N N interaction in different model spaces and with different values of the NCSM basis parameter ℏ Ω for energies of nuclear states and root-mean-square (rms) radii of proton, neutron and matter distributions in light nuclei. The method yields convergent predictions with quantifiable uncertainties. Ground-state energies for 6Li, 6He and the unbound 6Be, as well as the excited (3 + , 0) and (0 + , 1) states of 6Li, are obtained within a few hundred keV of experiment. The extrapolated radii of bound states converge well. In contrast, radii of unbound states in 6Be and 6Li do not stabilize. These results demonstrate that machine-learning extrapolations can extend the reach of ab initio nuclear structure calculations with reliable accuracy. [ABSTRACT FROM AUTHOR]
ISSN:02183013
DOI:10.1142/S0218301326410144