Deep learning: Extrapolation tool for ab initio nuclear theory

Abstract

Ab initio approaches in nuclear theory, such as the no-core shell model (NCSM), have been developed for approximately solving finite nuclei with realistic strong interactions. The NCSM and other approaches require an extrapolation of the results obtained in a finite basis space to the infinite basis space limit and assessment of the uncertainty of those extrapolations. Each observable requires a separate extrapolation and most observables have no proven extrapolation method. We propose a feed-forward artificial neural network (ANN) method as an extrapolation tool to obtain the ground state energy and the ground state point-proton root-mean-square (rms) radius along with their extrapolation uncertainties. The designed ANNs are sufficient to produce results for these two very different observables in ${}^6$Li from the ab initio NCSM results in small basis spaces that satisfy the following theoretical physics condition: independence of basis space parameters in the limit of extremely large matrices. Comparisons of the ANN results with other extrapolation methods are also provided.

arXiv comment13 pages, 6 figures. Some typos were fixed, e.g., replaced MSE units for the observables with observables' square units. arXiv admin note: text overlap with arXiv:1803.03215

References in corpus (31)

• Accurate Charge-Dependent Nucleon-Nucleon Potential at Fourth Order of Chiral Perturbation Theory
• From low-momentum interactions to nuclear structure
• Similarity Renormalization Group for Nucleon-Nucleon Interactions
• Nuclear Mass Predictions for the Crustal Composition of Neutron Stars: A Bayesian Neural Network Approach
• Ab initio no-core full configuration calculations of light nuclei
• Accurate Nucleon-Nucleon Potential Based upon Chiral Perturbation Theory
• Bayesian approach to model-based extrapolation of nuclear observables
• Covariant spectator theory of np scattering: Phase shifts obtained from precision fits to data below 350 MeV
• Nuclear charge radii: Density functional theory meets Bayesian neural networks
• N3LO NN interaction adjusted to light nuclei in ab exitu approach
• Corrections to nuclear energies and radii in finite oscillator spaces
• Convergence properties of {\itshape ab initio} calculations of light nuclei in a harmonic oscillator basis
• Universal properties of infrared oscillator basis extrapolations
• Refining mass formulas for astrophysical applications: a Bayesian neural network approach
• Nuclear mass systematics using neural networks
• Nucleon-nucleon interaction in the $J$-matrix inverse scattering approach and few-nucleon systems
• An artificial neural network application on nuclear charge radii
• Infrared length scale and extrapolations for the no-core shell model
• Decoding Beta-Decay Systematics: A Global Statistical Model for Beta^- Halflives
• Coulomb-Sturmian basis for the nuclear many-body problem
• Neural Networks for Impact Parameter Determination
• Ab initio no-core solutions for ${}^6$Li
• Validating neural-network refinements of nuclear mass models
• {\it Ab initio} nuclear structure - the large sparse matrix eigenvalue problem
• Large-scale exact diagonalizations reveal low-momentum scales of nuclei
• Halo nuclei 6He and 8He with the Coulomb-Sturmian basis
• Loosely bound three-body nuclear systems in the J-matrix approach
• Infrared extrapolations of quadrupole moments and transitions
• Natural orbital description of the halo nucleus 6He
• Empirical physical formula for potential energy curves of 38-66Ti isotopes by using neural networks
• Corrections to nucleon capture cross sections computed in truncated Hilbert spaces

Cited by in corpus (26)

• Machine Learning in Nuclear Physics
• Variational Monte Carlo calculations of $\mathbf{A}\le 4$ nuclei with an artificial neural-network correlator ansatz
• Multi-task learning on nuclear masses and separation energies with the kernel ridge regression
• Machine learning the deuteron
• Extrapolation of nuclear structure observables with artificial neural networks
• Physically Interpretable Machine Learning for nuclear masses
• Nuclear energy density functionals from machine learning
• Machine learning-based inversion of nuclear responses
• Machine learning approach to pattern recognition in nuclear dynamics from the ab initio symmetry-adapted no-core shell model
• Machine Learning for the Prediction of Converged Energies from Ab Initio Nuclear Structure Calculations
• Precise neural network predictions of energies and radii from the no-core shell model
• Taming nucleon density distributions with deep neural network method
• Calibration of nuclear charge density distribution by back-propagation neural networks
• Non-parametric Bayesian approach to extrapolation problems in configuration interaction methods
• Ground-state properties of light $4n$ self-conjugate nuclei in $ab$ $initio$ no-core Monte Carlo shell model calculations with nonlocal $NN$ interactions
• Machine learning light hypernuclei
• Spectroscopic factors of resonance states with the Gamow shell model
• Hyperon-Nucleon Interaction Constrained by Light Hypernuclei
• Classical-Quantum Noise Mitigation for NISQ Hardware
• Machine-learning approach to finite-size effects in systems with strongly interacting fermions
• Uncertainties in ab initio nuclear structure calculations with chiral interactions
• Spectroscopic factor calculations in the \textit{ab initio} no-core shell model
• High-Precision Ab Initio Radius Calculations of Boron Isotopes
• Daejeon16 interaction with contact-term corrections for heavy nuclear systems
• Report from the A.I. For Nuclear Physics Workshop
• Ab initio models of atomic nuclei: challenges and new ideas