Machine Learning in the Problem of No-Core Shell Model Result Extrapolations
Authors:
- 1 December 2024
- journal article
- research article
- Published by Pleiades Publishing Ltd in Physics of Atomic Nuclei
- Vol. 87 (S2) , S400-S408
Abstract
A method for extrapolating the results of variational calculations to the case of the infinite basis using an ensemble of artificial neural networks is proposed. Extrapolations of the no-core shell model results obtained with the nucleon–nucleon interaction Daejeon16 for the ground state energies, as well as for the root-mean-square (rms) point-proton, point-neutron, and point-nucleon (matter) radii of the \({}^{6}\)Li and \({}^{6}\)He nuclei, are performed.
Keywords
This publication has 25 references indexed in Scilit:
- Machine learning for the prediction of converged energies from ab initio nuclear structure calculationsPhysics Letters B, 2023
- Machine learning light hypernucleiNuclear Physics A, 2023
- Two-dimensional extrapolation procedure for an ab initio study of nuclear size parameters and the properties of the halo nucleusPhysical Review C, 2022
- Extrapolation of nuclear structure observables with artificial neural networksPhysical Review C, 2019
- Ab initio no-core solutions for 6 LiJournal of Physics G: Nuclear and Particle Physics, 2017
- N3LO NN interaction adjusted to light nuclei in ab exitu approachPhysics Letters B, 2016
- Ab initio no core shell modelProgress in Particle and Nuclear Physics, 2013
- Recent experimental progress in nuclear halo structure studiesProgress in Particle and Nuclear Physics, 2013
- Basic Statistics2009
- Energy levels of light nuclei A=5, 6, 7Nuclear Physics A, 2002