Machine learning approach to pattern recognition in nuclear dynamics from the ab initio symmetry-adapted no-core shell model
Abstract
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 structuremore »
- Authors:
-
[1];
[1];
[1];
- Louisiana State Univ., Baton Rouge, LA (United States)
- Louisiana State Univ., Baton Rouge, LA (United States); Yale Univ., New Haven, CT (United States). Sloane Physics Laboratory
- Louisiana State Univ., Baton Rouge, LA (United States); Academy of Sciences of the Czech Republic (Czech Republic)
- Publication Date:
- Research Org.:
- Yale Univ., New Haven, CT (United States); Univ. of California, Oakland, CA (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC); National Science Foundation (NSF); Czech Science Foundation
- OSTI Identifier:
- 1979864
- Grant/Contract Number:
- SC0019521; AC02-05CH11231; PHY-1913728; 16-16772S; OAC-1818253
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Physical Review. C
- Additional Journal Information:
- Journal Volume: 105; Journal Issue: 3; Journal ID: ISSN 2469-9985
- Publisher:
- American Physical Society (APS)
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 73 NUCLEAR PHYSICS AND RADIATION PHYSICS; Physics; machine learning; nucleon distribution; ab initio calculations; shell model
Citation Formats
Molchanov, O. M., Launey, K. D., Mercenne, A., Sargsyan, G. H., Dytrych, T., and Draayer, J. P. Machine learning approach to pattern recognition in nuclear dynamics from the ab initio symmetry-adapted no-core shell model. United States: N. p., 2022.
Web. doi:10.1103/physrevc.105.034306.
Molchanov, O. M., Launey, K. D., Mercenne, A., Sargsyan, G. H., Dytrych, T., & Draayer, J. P. Machine learning approach to pattern recognition in nuclear dynamics from the ab initio symmetry-adapted no-core shell model. United States. https://doi.org/10.1103/physrevc.105.034306
Molchanov, O. M., Launey, K. D., Mercenne, A., Sargsyan, G. H., Dytrych, T., and Draayer, J. P. Thu .
"Machine learning approach to pattern recognition in nuclear dynamics from the ab initio symmetry-adapted no-core shell model". United States. https://doi.org/10.1103/physrevc.105.034306. https://www.osti.gov/servlets/purl/1979864.
@article{osti_1979864,
title = {Machine learning approach to pattern recognition in nuclear dynamics from the ab initio symmetry-adapted no-core shell model},
author = {Molchanov, O. M. and Launey, K. D. and Mercenne, A. and Sargsyan, G. H. and Dytrych, T. and Draayer, J. P.},
abstractNote = {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.},
doi = {10.1103/physrevc.105.034306},
journal = {Physical Review. C},
number = 3,
volume = 105,
place = {United States},
year = {Thu Mar 03 00:00:00 EST 2022},
month = {Thu Mar 03 00:00:00 EST 2022}
}
Free Publicly Available Full Text
Publisher's Version of Record
Other availability
Search WorldCat to find libraries that may hold this journal
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.
Works referenced in this record:
Physics-informed machine learning
journal, May 2021
- Karniadakis, George Em; Kevrekidis, Ioannis G.; Lu, Lu
- Nature Reviews Physics, Vol. 3, Issue 6
Symmetry-guided large-scale shell-model theory
journal, July 2016
- Launey, Kristina D.; Dytrych, Tomas; Draayer, Jerry P.
- Progress in Particle and Nuclear Physics, Vol. 89
Multilayer feedforward networks are universal approximators
journal, January 1989
- Hornik, Kurt; Stinchcombe, Maxwell; White, Halbert
- Neural Networks, Vol. 2, Issue 5
Two- and three-nucleon contact interactions and ground-state energies of light- and medium-mass nuclei
journal, May 2021
- Schiavilla, R.; Girlanda, L.; Gnech, A.
- Physical Review C, Vol. 103, Issue 5
Isospin symmetry in values: Coulomb excitation study of
journal, May 2019
- Ruotsalainen, P.; Henderson, J.; Hackman, G.
- Physical Review C, Vol. 99, Issue 5
Extrapolation of nuclear structure observables with artificial neural networks
journal, November 2019
- Jiang, W. G.; Hagen, G.; Papenbrock, T.
- Physical Review C, Vol. 100, Issue 5
Ab initio folding potentials for nucleon-nucleus scattering based on no-core shell-model one-body densities
journal, April 2019
- Burrows, M.; Elster, Ch.; Weppner, S. P.
- Physical Review C, Vol. 99, Issue 4
White paper: from bound states to the continuum
journal, November 2020
- Johnson, Calvin W.; Launey, Kristina D.; Auerbach, Naftali
- Journal of Physics G: Nuclear and Particle Physics, Vol. 47, Issue 12
Clustering and -capture reaction rate from ab initio symmetry-adapted descriptions of
journal, October 2020
- Dreyfuss, A. C.; Launey, K. D.; Escher, J. E.
- Physical Review C, Vol. 102, Issue 4
Nuclear Dynamics and Reactions in the Ab Initio Symmetry-Adapted Framework
journal, September 2021
- Launey, Kristina D.; Mercenne, Alexis; Dytrych, Tomas
- Annual Review of Nuclear and Particle Science, Vol. 71, Issue 1
SU(3)-guided realistic nucleon-nucleon interactions for large-scale calculations
journal, April 2021
- Sargsyan, G. H.; Launey, K. D.; Baker, R. B.
- Physical Review C, Vol. 103, Issue 4
Shape variables and the shell model
journal, March 1988
- Casta∼nos, O.; Draayer, J. P.; Leschber, Y.
- Zeitschrift für Physik A Atomic Nuclei, Vol. 329, Issue 1
The impact of individual nuclear properties on -process nucleosynthesis
journal, January 2016
- Mumpower, M. R.; Surman, R.; McLaughlin, G. C.
- Progress in Particle and Nuclear Physics, Vol. 86
A.I. for nuclear physics
journal, March 2021
- Bedaque, Paulo; Boehnlein, Amber; Cromaz, Mario
- The European Physical Journal A, Vol. 57, Issue 3
Triaxial quadrupole deformation dynamics in -shell nuclei around
journal, January 2011
- Hinohara, Nobuo; Kanada-En’yo, Yoshiko
- Physical Review C, Vol. 83, Issue 1
Hoyle state and rotational features in Carbon-12 within a no-core shell-model framework
journal, December 2013
- Dreyfuss, Alison C.; Launey, Kristina D.; Dytrych, Tomáš
- Physics Letters B, Vol. 727, Issue 4-5
Deep learning: Extrapolation tool for ab initio nuclear theory
journal, May 2019
- Negoita, Gianina Alina; Vary, James P.; Luecke, Glenn R.
- Physical Review C, Vol. 99, Issue 5
Benchmark calculations of electromagnetic sum rules with a symmetry-adapted basis and hyperspherical harmonics
journal, July 2020
- Baker, R. B.; Launey, K. D.; Bacca, S.
- Physical Review C, Vol. 102, Issue 1
Medium-Mass Nuclei from Chiral Nucleon-Nucleon Interactions
journal, August 2008
- Hagen, G.; Papenbrock, T.; Dean, D. J.
- Physical Review Letters, Vol. 101, Issue 9
Physics of Nuclei: Key Role of an Emergent Symmetry
journal, January 2020
- Dytrych, T.; Launey, K. D.; Draayer, J. P.
- Physical Review Letters, Vol. 124, Issue 4
Structure of and influence of the neutron shell
journal, July 2019
- Williams, J.; Ball, G. C.; Chester, A.
- Physical Review C, Vol. 100, Issue 1
Accurate nuclear radii and binding energies from a chiral interaction
journal, May 2015
- Ekström, A.; Jansen, G. R.; Wendt, K. A.
- Physical Review C, Vol. 91, Issue 5
Machine-learning-based inversion of nuclear responses
journal, March 2021
- Raghavan, Krishnan; Balaprakash, Prasanna; Lovato, Alessandro
- Physical Review C, Vol. 103, Issue 3
SU(3) quasi-dynamical symmetry as an organizational mechanism for generating nuclear rotational motions
journal, January 2000
- Bahri, C.; Rowe, D. J.
- Nuclear Physics A, Vol. 662, Issue 1-2
Investigations of rotational nuclei via the pseudo-symplectic model
journal, September 1994
- Troltenier, D.; Draayer, J. P.; Hess, P. O.
- Nuclear Physics A, Vol. 576, Issue 3
The fundamental role of symmetry in nuclear models
conference, January 2013
- Rowe, D. J.
- LA RABIDA 2012 INTERNATIONAL SCIENTIFIC MEETING ON NUCLEAR PHYSICS: Basic Concepts in Nuclear Physics: Theory, Experiments, and Applications, AIP Conference Proceedings
How machine learning conquers the unitary limit
journal, February 2021
- Kaspschak, Bastian; Meißner, Ulf-G
- Communications in Theoretical Physics, Vol. 73, Issue 3