Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Machine learning approach to pattern recognition in nuclear dynamics from the ab initio symmetry-adapted no-core shell model

Journal Article · · Physical Review. C
 [1];  [2];  [3];  [2];  [4];  [2]
  1. Louisiana State Univ., Baton Rouge, LA (United States); OSTI
  2. Louisiana State Univ., Baton Rouge, LA (United States)
  3. Louisiana State Univ., Baton Rouge, LA (United States); Yale Univ., New Haven, CT (United States). Sloane Physics Laboratory
  4. Louisiana State Univ., Baton Rouge, LA (United States); Academy of Sciences of the Czech Republic (Czech Republic)
+ Show Author Affiliations
A novel machine learning approach is used to provide further insight into atomic nuclei and to detect orderly patterns amid a vast data of large-scale calculations. The method utilizes a neural network that is trained on ab initio results from the symmetry-adapted no-core shell model (SA-NCSM) for light nuclei. We show that the SA-NCSM, which expands ab initio applications up to medium-mass nuclei by using dominant symmetries of nuclear dynamics, can reach heavier nuclei when coupled with the machine learning approach. In particular, we find that a neural network trained on probability amplitudes for s- and p-shell nuclear wave functions not only predicts dominant configurations for heavier nuclei but in addition, when tested for the 20Ne ground state, accurately reproduces the probability distribution. The non-negligible configurations predicted by the network provide an important input to the SA-NCSM for reducing ultralarge model spaces to manageable sizes that can be, in turn, utilized in SA-NCSM calculations to obtain accurate observables. The neural network is capable of describing nuclear deformation and is used to track the shape evolution along the 20-42Mg isotopic chain, suggesting a shape coexistence that is more pronounced toward the very neutron-rich isotopes. We provide first descriptions of the structure and deformation of 24Si and 40Mg of interest to x-ray burst nucleosynthesis, and even of the extremely heavy nuclei such as 166,168Er and 236U, that build on first-principles considerations.
Research Organization:
Univ. of California, Oakland, CA (United States); Yale Univ., New Haven, CT (United States)
Sponsoring Organization:
Czech Science Foundation; National Science Foundation (NSF); USDOE Office of Science (SC)
Grant/Contract Number:
AC02-05CH11231; SC0019521
OSTI ID:
1979864
Journal Information:
Physical Review. C, Journal Name: Physical Review. C Journal Issue: 3 Vol. 105; ISSN 2469-9985
Publisher:
American Physical Society (APS)Copyright Statement
Country of Publication:
United States
Language:
English

References (30)

Shape variables and the shell model journal March 1988
Investigations of rotational nuclei via the pseudo-symplectic model journal September 1994
Multilayer feedforward networks are universal approximators journal January 1989
SU(3) quasi-dynamical symmetry as an organizational mechanism for generating nuclear rotational motions journal January 2000
Hoyle state and rotational features in Carbon-12 within a no-core shell-model framework journal December 2013
The impact of individual nuclear properties on r -process nucleosynthesis journal January 2016
Symmetry-guided large-scale shell-model theory journal July 2016
Physics-informed machine learning journal May 2021
Rare isotopes in the cosmos journal November 2008
The fundamental role of symmetry in nuclear models
  • Rowe, D. J.
  • LA RABIDA 2012 INTERNATIONAL SCIENTIFIC MEETING ON NUCLEAR PHYSICS: Basic Concepts in Nuclear Physics: Theory, Experiments, and Applications, AIP Conference Proceedings https://doi.org/10.1063/1.4810815
conference January 2013
White paper: from bound states to the continuum journal November 2020
How machine learning conquers the unitary limit journal February 2021
Structure of Mg 28 and influence of the neutron p f shell journal July 2019
Extrapolation of nuclear structure observables with artificial neural networks journal November 2019
Benchmark calculations of electromagnetic sum rules with a symmetry-adapted basis and hyperspherical harmonics journal July 2020
Clustering and α -capture reaction rate from ab initio symmetry-adapted descriptions of Ne 20 journal October 2020
Machine-learning-based inversion of nuclear responses journal March 2021
SU(3)-guided realistic nucleon-nucleon interactions for large-scale calculations journal April 2021
Two- and three-nucleon contact interactions and ground-state energies of light- and medium-mass nuclei journal May 2021
Triaxial quadrupole deformation dynamics in sd -shell nuclei around Mg 26 journal January 2011
Accurate nuclear radii and binding energies from a chiral interaction journal May 2015
Bayesian approach to model-based extrapolation of nuclear observables journal September 2018
Ab initio folding potentials for nucleon-nucleus scattering based on no-core shell-model one-body densities journal April 2019
Isospin symmetry in B ( E 2 ) values: Coulomb excitation study of Mg 21 journal May 2019
Deep learning: Extrapolation tool for ab initio nuclear theory journal May 2019
Medium-Mass Nuclei from Chiral Nucleon-Nucleon Interactions journal August 2008
Optimized Chiral Nucleon-Nucleon Interaction at Next-to-Next-to-Leading Order journal May 2013
Physics of Nuclei: Key Role of an Emergent Symmetry journal January 2020
A.I. for nuclear physics journal March 2021
Nuclear Dynamics and Reactions in the Ab Initio Symmetry-Adapted Framework journal September 2021

Similar Records

Light Nuclei in the Framework of the Symplectic No-Core Shell Model
Conference · Mon Apr 02 00:00:00 EDT 2007 · OSTI ID:901844
Ab initio translationally invariant nucleon-nucleus optical potentials
Journal Article · Mon Jan 15 19:00:00 EST 2024 · Physical Review. C · OSTI ID:2879336

Related Subjects

73 NUCLEAR PHYSICS AND RADIATION PHYSICS
Physics
ab initio calculations
machine learning
nucleon distribution
shell model