Extrapolation of nuclear structure observables with artificial neural networks

Jiang, W. G.; Hagen, G.; Papenbrock, T.

doi:10.1103/physrevc.100.054326

Title: Extrapolation of nuclear structure observables with artificial neural networks

Journal Article · Thu Nov 21 00:00:00 EST 2019 · Physical Review. C

DOI:https://doi.org/10.1103/physrevc.100.054326· OSTI ID:1649099

^[1]; Hagen, G. ^[1];

^[1]

Univ. of Tennessee, Knoxville, TN (United States); Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)

Calculations of nuclei are often carried out in finite model spaces. Thus, finite-size corrections enter, and it is necessary to extrapolate the computed observables to infinite model spaces. In this work, we employ extrapolation methods based on artificial neural networks for observables such as the ground-state energy and the point-proton radius. We extrapolate results from no-core shell model and coupled-cluster calculations to very large model spaces and estimate uncertainties. Training the network on different data typically yields extrapolation results that cluster around distinct values. We show that a preprocessing of input data, and the inclusion of correlations among the input data, reduces the problem of multiple solutions and yields more stable extrapolated results and consistent uncertainty estimates. We perform extrapolations for ground-state energies and radii in ⁴He, ⁶Li, and ¹⁶O, and compare the predictions from neural networks with results from infrared extrapolations.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States); Univ. of Tennessee, Knoxville, TN (United States)

Sponsoring Organization:: USDOE Office of Science (SC), Nuclear Physics (NP)

Grant/Contract Number:: AC05-00OR22725; FG02-96ER40963; SC0018223

OSTI ID:: 1649099

Alternate ID(s):: OSTI ID: 1593553

Journal Information:: Physical Review. C, Vol. 100, Issue 5; ISSN 2469-9985

Publisher:: American Physical Society (APS)Copyright Statement

Country of Publication:: United States

Language:: English

Citation Metrics:

Cited by: 22 works

Citation information provided by
Web of Science

References (74)

Volume dependence of the energy spectrum in massive quantum field theories: I. Stable particle states Lüscher, M. Communications in Mathematical Physics, Vol. 104, Issue 2 https://doi.org/10.1007/BF01211589	journal	June 1986
Large-scale exact diagonalizations reveal low-momentum scales of nuclei Forssén, C.; Carlsson, B. D.; Johansson, H. T. Physical Review C, Vol. 97, Issue 3 https://doi.org/10.1103/PhysRevC.97.034328	journal	March 2018
Ab initio no core shell model Barrett, Bruce R.; Navrátil, Petr; Vary, James P. Progress in Particle and Nuclear Physics, Vol. 69 https://doi.org/10.1016/j.ppnp.2012.10.003	journal	March 2013
Convergence in the no-core shell model with low-momentum two-nucleon interactions Bogner, S. K.; Furnstahl, R. J.; Maris, P. Nuclear Physics A, Vol. 801, Issue 1-2 https://doi.org/10.1016/j.nuclphysa.2007.12.008	journal	March 2008
A recipe for EFT uncertainty quantification in nuclear physics Furnstahl, R. J.; Phillips, D. R.; Wesolowski, S. Journal of Physics G: Nuclear and Particle Physics, Vol. 42, Issue 3 https://doi.org/10.1088/0954-3899/42/3/034028	journal	February 2015
Optimized Chiral Nucleon-Nucleon Interaction at Next-to-Next-to-Leading Order Ekström, A.; Baardsen, G.; Forssén, C. Physical Review Letters, Vol. 110, Issue 19 https://doi.org/10.1103/PhysRevLett.110.192502	journal	May 2013
Systematic expansion for infrared oscillator basis extrapolations Furnstahl, R. J.; More, S. N.; Papenbrock, T. Physical Review C, Vol. 89, Issue 4 https://doi.org/10.1103/PhysRevC.89.044301	journal	April 2014
Medium-Mass Nuclei with Normal-Ordered Chiral $N N + 3 N$ Interactions Roth, Robert; Binder, Sven; Vobig, Klaus Physical Review Letters, Vol. 109, Issue 5 https://doi.org/10.1103/PhysRevLett.109.052501	journal	July 2012
Infrared length scale and extrapolations for the no-core shell model Wendt, K. A.; Forssén, C.; Papenbrock, T. Physical Review C, Vol. 91, Issue 6 https://doi.org/10.1103/PhysRevC.91.061301	journal	June 2015
Ab initio coupled-cluster approach to nuclear structure with modern nucleon-nucleon interactions Hagen, G.; Papenbrock, T.; Dean, D. J. Physical Review C, Vol. 82, Issue 3 https://doi.org/10.1103/PhysRevC.82.034330	journal	September 2010
The Calculation of Posterior Distributions by Data Augmentation Tanner, Martin A.; Wong, Wing Hung Journal of the American Statistical Association, Vol. 82, Issue 398 https://doi.org/10.1080/01621459.1987.10478458	journal	June 1987
Regularization and variable selection via the elastic net Zou, Hui; Hastie, Trevor Journal of the Royal Statistical Society: Series B (Statistical Methodology), Vol. 67, Issue 2 https://doi.org/10.1111/j.1467-9868.2005.00503.x	journal	April 2005
Chaotic Wave Functions and Exponential Convergence of Low-Lying Energy Eigenvalues Horoi, Mihai; Volya, Alexander; Zelevinsky, Vladimir Physical Review Letters, Vol. 82, Issue 10 https://doi.org/10.1103/PhysRevLett.82.2064	journal	March 1999
Deep learning: Extrapolation tool for ab initio nuclear theory Negoita, Gianina Alina; Vary, James P.; Luecke, Glenn R. Physical Review C, Vol. 99, Issue 5 https://doi.org/10.1103/PhysRevC.99.054308	journal	May 2019
Recent developments in no-core shell-model calculations Navrátil, Petr; Quaglioni, Sofia; Stetcu, Ionel Journal of Physics G: Nuclear and Particle Physics, Vol. 36, Issue 8 https://doi.org/10.1088/0954-3899/36/8/083101	journal	May 2009
miRNALoc: predicting miRNA subcellular localizations based on principal component scores of physico-chemical properties and pseudo compositions of di-nucleotides Meher, Prabina Kumar; Satpathy, Subhrajit; Rao, Atmakuri Ramakrishna Scientific Reports, Vol. 10, Issue 1 https://doi.org/10.1038/s41598-020-71381-4	journal	September 2020
Coupled-cluster computations of atomic nuclei Hagen, G.; Papenbrock, T.; Hjorth-Jensen, M. Reports on Progress in Physics, Vol. 77, Issue 9 https://doi.org/10.1088/0034-4885/77/9/096302	journal	September 2014
Collective Modes in Light Nuclei from First Principles Dytrych, T.; Launey, K. D.; Draayer, J. P. Physical Review Letters, Vol. 111, Issue 25 https://doi.org/10.1103/PhysRevLett.111.252501	journal	December 2013
Ultraviolet extrapolations in finite oscillator bases König, S.; Bogner, S. K.; Furnstahl, R. J. Physical Review C, Vol. 90, Issue 6 https://doi.org/10.1103/PhysRevC.90.064007	journal	December 2014
Solving the quantum many-body problem with artificial neural networks Carleo, Giuseppe; Troyer, Matthias Science, Vol. 355, Issue 6325 https://doi.org/10.1126/science.aag2302	journal	February 2017
Extrapolation method for the no-core shell model Zhan, H.; Nogga, A.; Barrett, B. R. Physical Review C, Vol. 69, Issue 3 https://doi.org/10.1103/PhysRevC.69.034302	journal	March 2004
On the approximate realization of continuous mappings by neural networks Funahashi, Ken-Ichi Neural Networks, Vol. 2, Issue 3 https://doi.org/10.1016/0893-6080(89)90003-8	journal	January 1989
Benchmark calculations for ${}^{3}H$ , ${}^{4}{He}$ , ${}^{16}O$ , and ${}^{40}{Ca}$ with ab initio coupled-cluster theory Hagen, G.; Dean, D. J.; Hjorth-Jensen, M. Physical Review C, Vol. 76, Issue 4 https://doi.org/10.1103/PhysRevC.76.044305	journal	October 2007
Learning representations by back-propagating errors Rumelhart, David E.; Hinton, Geoffrey E.; Williams, Ronald J. Nature, Vol. 323, Issue 6088 https://doi.org/10.1038/323533a0	journal	October 1986
Automatic early stopping using cross validation: quantifying the criteria Prechelt, Lutz Neural Networks, Vol. 11, Issue 4 https://doi.org/10.1016/S0893-6080(98)00010-0	journal	June 1998
Bayesian methods for parameter estimation in effective field theories Schindler, M. R.; Phillips, D. R. Annals of Physics, Vol. 324, Issue 3 https://doi.org/10.1016/j.aop.2008.09.003	journal	March 2009
Universal properties of infrared oscillator basis extrapolations More, S. N.; Ekström, A.; Furnstahl, R. J. Physical Review C, Vol. 87, Issue 4 https://doi.org/10.1103/PhysRevC.87.044326	journal	April 2013
Learning Deep Architectures for AI Bengio, Y. Foundations and Trends® in Machine Learning, Vol. 2, Issue 1 https://doi.org/10.1561/2200000006	journal	January 2009
Nuclear charge radii: density functional theory meets Bayesian neural networks Utama, R.; Chen, Wei-Chia; Piekarewicz, J. Journal of Physics G: Nuclear and Particle Physics, Vol. 43, Issue 11 https://doi.org/10.1088/0954-3899/43/11/114002	journal	October 2016
Volume Dependence of N-Body Bound States König, Sebastian; Lee, Dean GSI Helmholtzzentrum fuer Schwerionenforschung, GSI, Darmstadt https://doi.org/10.15120/gsi-2019-00697	text	January 2018
The In-Medium Similarity Renormalization Group: A novel ab initio method for nuclei Hergert, H.; Bogner, S. K.; Morris, T. D. Physics Reports, Vol. 621 https://doi.org/10.1016/j.physrep.2015.12.007	journal	March 2016
An artificial neural network application on nuclear charge radii Akkoyun, S.; Bayram, T.; Kara, S. O. Journal of Physics G: Nuclear and Particle Physics, Vol. 40, Issue 5 https://doi.org/10.1088/0954-3899/40/5/055106	journal	March 2013
Lattice simulations for few- and many-body systems Lee, Dean Progress in Particle and Nuclear Physics, Vol. 63, Issue 1 https://doi.org/10.1016/j.ppnp.2008.12.001	journal	July 2009
Self-consistent Green's function method for nuclei and nuclear matter Dickhoff, W. H.; Barbieri, C. Progress in Particle and Nuclear Physics, Vol. 52, Issue 2 https://doi.org/10.1016/j.ppnp.2004.02.038	journal	April 2004
How many hidden layers and nodes? Stathakis, D. International Journal of Remote Sensing, Vol. 30, Issue 8 https://doi.org/10.1080/01431160802549278	journal	April 2009
Convergence properties of ab initio calculations of light nuclei in a harmonic oscillator basis Coon, S. A.; Avetian, M. I.; Kruse, M. K. G. Physical Review C, Vol. 86, Issue 5 https://doi.org/10.1103/PhysRevC.86.054002	journal	November 2012
Decoding $β$ -decay systematics: A global statistical model for $β^{-}$ half-lives Costiris, N. J.; Mavrommatis, E.; Gernoth, K. A. Physical Review C, Vol. 80, Issue 4 https://doi.org/10.1103/PhysRevC.80.044332	journal	October 2009
Bayesian approach to model-based extrapolation of nuclear observables Neufcourt, Léo; Cao, Yuchen; Nazarewicz, Witold Physical Review C, Vol. 98, Issue 3 https://doi.org/10.1103/PhysRevC.98.034318	journal	September 2018
Corrections to nuclear energies and radii in finite oscillator spaces Furnstahl, R. J.; Hagen, G.; Papenbrock, T. Physical Review C, Vol. 86, Issue 3 https://doi.org/10.1103/PhysRevC.86.031301	journal	September 2012
Approximation by superpositions of a sigmoidal function Cybenko, G. Mathematics of Control, Signals, and Systems, Vol. 5, Issue 4 https://doi.org/10.1007/bf02134016	journal	December 1992
Nuclear mass systematics using neural networks Athanassopoulos, S.; Mavrommatis, E.; Gernoth, K. A. Nuclear Physics A, Vol. 743, Issue 4 https://doi.org/10.1016/j.nuclphysa.2004.08.006	journal	November 2004
Volume dependence of N -body bound states König, Sebastian; Lee, Dean Physics Letters B, Vol. 779 https://doi.org/10.1016/j.physletb.2018.01.060	journal	April 2018
Uncertainty Analysis and Order-by-Order Optimization of Chiral Nuclear Interactions Carlsson, B. D.; Ekström, A.; Forssén, C. Physical Review X, Vol. 6, Issue 1 https://doi.org/10.1103/PhysRevX.6.011019	journal	February 2016
Deep Representational Similarity Learning for Analyzing Neural Signatures in Task-based fMRI Dataset Yousefnezhad, Muhammad; Sawalha, Jeffrey; Selvitella, Alessandro Neuroinformatics, Vol. 19, Issue 3 https://doi.org/10.1007/s12021-020-09494-4	journal	October 2020
Automatic early stopping using cross validation: quantifying the criteria Prechelt, Lutz Karlsruhe https://doi.org/10.5445/ir/7398	text	January 1998
Quantum Monte Carlo methods for nuclear physics Carlson, J.; Gandolfi, S.; Pederiva, F. Reviews of Modern Physics, Vol. 87, Issue 3 https://doi.org/10.1103/RevModPhys.87.1067	journal	September 2015
Infrared extrapolations of quadrupole moments and transitions Odell, D.; Papenbrock, T.; Platter, L. Physical Review C, Vol. 93, Issue 4 https://doi.org/10.1103/PhysRevC.93.044331	journal	April 2016
Random Forests Breiman, Leo Machine Learning, Vol. 45, Issue 1, p. 5-32 https://doi.org/10.1023/A:1010933404324	journal	January 2001
Convergence in the no-core shell model with low-momentum two-nucleon interactions Bogner, S. K.; Furnstahl, R. J.; Maris, P. arXiv https://doi.org/10.48550/arxiv.0708.3754	text	January 2007
Lattice simulations for few- and many-body systems Lee, Dean arXiv https://doi.org/10.48550/arxiv.0804.3501	text	January 2008
Bayesian Methods for Parameter Estimation in Effective Field Theories Schindler, Matthias R.; Phillips, Daniel R. arXiv https://doi.org/10.48550/arxiv.0808.3643	text	January 2008
Recent developments in no-core shell-model calculations Navratil, Petr; Quaglioni, Sofia; Stetcu, Ionel arXiv https://doi.org/10.48550/arxiv.0904.0463	text	January 2009
Ab initio coupled-cluster approach to nuclear structure with modern nucleon-nucleon interactions Hagen, G.; Papenbrock, T.; Dean, D. J. arXiv https://doi.org/10.48550/arxiv.1005.2627	text	January 2010
Corrections to nuclear energies and radii in finite oscillator spaces Furnstahl, R. J.; Hagen, G.; Papenbrock, T. arXiv https://doi.org/10.48550/arxiv.1207.6100	text	January 2012
Coupled-cluster computations of atomic nuclei Hagen, G.; Papenbrock, T.; Hjorth-Jensen, M. arXiv https://doi.org/10.48550/arxiv.1312.7872	text	January 2013
Ultraviolet extrapolations in finite oscillator bases König, S.; Bogner, S. K.; Furnstahl, R. J. arXiv https://doi.org/10.48550/arxiv.1409.5997	text	January 2014
Infrared length scale and extrapolations for the no-core shell model Wendt, K. A.; Forssén, C.; Papenbrock, T. arXiv https://doi.org/10.48550/arxiv.1503.07144	text	January 2015
The In-Medium Similarity Renormalization Group: A Novel Ab Initio Method for Nuclei Hergert, H.; Bogner, S. K.; Morris, T. D. arXiv https://doi.org/10.48550/arxiv.1512.06956	text	January 2015
Nuclear charge radii: Density functional theory meets Bayesian neural networks Utama, Raditya; Chen, Wei-Chia; Piekarewicz, Jorge arXiv https://doi.org/10.48550/arxiv.1608.03020	text	January 2016
Refining mass formulas for astrophysical applications: a Bayesian neural network approach Utama, Raditya; Piekarewicz, Jorge arXiv https://doi.org/10.48550/arxiv.1704.06632	text	January 2017
Validating neural-network refinements of nuclear mass models Utama, R.; Piekarewicz, J. arXiv https://doi.org/10.48550/arxiv.1709.09502	text	January 2017
Large-scale exact diagonalizations reveal low-momentum scales of nuclei Forssén, C.; Carlsson, B. D.; Johansson, H. T. arXiv https://doi.org/10.48550/arxiv.1712.09951	text	January 2017
Bayesian approach to model-based extrapolation of nuclear observables Neufcourt, Léo; Cao, Yuchen; Nazarewicz, Witold arXiv https://doi.org/10.48550/arxiv.1806.00552	text	January 2018
Deep learning: Extrapolation tool for ab initio nuclear theory Negoita, Gianina Alina; Vary, James P.; Luecke, Glenn R. arXiv https://doi.org/10.48550/arxiv.1810.04009	text	January 2018
Extrapolation Method for the No-Core Shell Model Zhan, H.; Nogga, A.; Barrett, B. R. arXiv https://doi.org/10.48550/arxiv.nucl-th/0401047	text	January 2004
Self-consistent Green's function method for nuclei and nuclear matter Dickhoff, W. H.; Barbieri, C. arXiv https://doi.org/10.48550/arxiv.nucl-th/0402034	text	January 2004
Chaotic wave functions and exponential convergence of low-lying energy eigenvalues Horoi, Mihai; Volya, Alexander; Zelevinsky, Vladimir arXiv https://doi.org/10.48550/arxiv.nucl-th/9806015	text	January 1998
Approximation capabilities of multilayer feedforward networks Hornik, Kurt Neural Networks, Vol. 4, Issue 2 https://doi.org/10.1016/0893-6080(91)90009-t	journal	January 1991
Converging sequences in the ab initio no-core shell model Forssén, C.; Vary, J. P.; Caurier, E. Physical Review C, Vol. 77, Issue 2 https://doi.org/10.1103/physrevc.77.024301	journal	February 2008
Conversational speech transcription using context-dependent deep neural networks Seide, Frank; Li, Gang; Yu, Dong Interspeech 2011 https://doi.org/10.21437/interspeech.2011-169	conference	August 2011
Universal properties of infrared oscillator basis extrapolations More, S. N.; Ekstrom, A.; Furnstahl, R. J. arXiv https://doi.org/10.48550/arxiv.1302.3815	text	January 2013
An optimized chiral nucleon-nucleon interaction at next-to-next-to-leading order Ekström, A.; Baardsen, G.; Forssén, C. arXiv https://doi.org/10.48550/arxiv.1303.4674	text	January 2013
Collective Modes in Light Nuclei from First Principles Dytrych, T.; Launey, K. D.; Draayer, J. P. arXiv https://doi.org/10.48550/arxiv.1312.0969	text	January 2013
Statistical Modeling of Nuclear Systematics Clark, J. W.; Mavrommatis, E.; Athanassopoulos, S. arXiv https://doi.org/10.48550/arxiv.nucl-th/0109081	text	January 2001

Cited By (3)

Beyond the proton drip line: Bayesian analysis of proton-emitting nuclei Neufcourt, Léo; Cao, Yuchen; Giuliani, Samuel arXiv https://doi.org/10.48550/arxiv.1910.12624	text	January 2019
Ab initio models of atomic nuclei: challenges and new ideas Ekström, Andreas arXiv https://doi.org/10.48550/arxiv.1912.02227	preprint	January 2019
Report from the A.I. For Nuclear Physics Workshop Bedaque, Paulo; Boehnlein, Amber; Cromaz, Mario arXiv https://doi.org/10.48550/arxiv.2006.05422	preprint	January 2020

Similar Records

Consideration for the application of artificial neural networks to criticality code validation - 14270

Conference · Tue Sep 15 00:00:00 EDT 2015 · OSTI ID:1649099

Angelo, Peter L.; Hollenbach, Daniel F.; Baker, James S.

Deep learning: Extrapolation tool for ab initio nuclear theory

Journal Article · Fri May 10 00:00:00 EDT 2019 · Physical Review C · OSTI ID:1649099

Negoita, Gianina Alina; Vary, James P.; Luecke, Glenn R.; +8 more

Effect of spatial sampling from European flux towers for estimating carbon and water fluxes with artificial neural networks

Journal Article · Fri Oct 09 00:00:00 EDT 2015 · Journal of Geophysical Research. Biogeosciences · OSTI ID:1649099

Papale, Dario; Black, T. Andrew; Carvalhais, Nuno; +16 more

Related Subjects

73 NUCLEAR PHYSICS AND RADIATION PHYSICS
Nuclear structure & decays
artificial neural networks
tensor network methods

Title: Extrapolation of nuclear structure observables with artificial neural networks

Citation Formats

References (74)

Cited By (3)

Similar Records

Related Subjects