Building surrogate models of nuclear density functional theory with Gaussian processes and autoencoders
From the lightest Hydrogen isotopes up to the recently synthesized Oganesson (Z = 118), it is estimated that as many as about 8,000 atomic nuclei could exist in nature. Most of these nuclei are too short-lived to be occurring on Earth, but they play an essential role in astrophysical events such as...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2022-11-01
|
Series: | Frontiers in Physics |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fphy.2022.1028370/full |
_version_ | 1811221476819337216 |
---|---|
author | Marc Verriere Nicolas Schunck Irene Kim Irene Kim Petar Marević Petar Marević Petar Marević Kevin Quinlan Michelle N. Ngo Michelle N. Ngo David Regnier David Regnier Raphael David Lasseri |
author_facet | Marc Verriere Nicolas Schunck Irene Kim Irene Kim Petar Marević Petar Marević Petar Marević Kevin Quinlan Michelle N. Ngo Michelle N. Ngo David Regnier David Regnier Raphael David Lasseri |
author_sort | Marc Verriere |
collection | DOAJ |
description | From the lightest Hydrogen isotopes up to the recently synthesized Oganesson (Z = 118), it is estimated that as many as about 8,000 atomic nuclei could exist in nature. Most of these nuclei are too short-lived to be occurring on Earth, but they play an essential role in astrophysical events such as supernova explosions or neutron star mergers that are presumed to be at the origin of most heavy elements in the Universe. Understanding the structure, reactions, and decays of nuclei across the entire chart of nuclides is an enormous challenge because of the experimental difficulties in measuring properties of interest in such fleeting objects and the theoretical and computational issues of simulating strongly-interacting quantum many-body systems. Nuclear density functional theory (DFT) is a fully microscopic theoretical framework which has the potential of providing such a quantitatively accurate description of nuclear properties for every nucleus in the chart of nuclides. Thanks to high-performance computing facilities, it has already been successfully applied to predict nuclear masses, global patterns of radioactive decay like β or γ decay, and several aspects of the nuclear fission process such as, e.g., spontaneous fission half-lives. Yet, predictive simulations of nuclear spectroscopy—the low-lying excited states and transitions between them—or of nuclear fission, or the quantification of theoretical uncertainties and their propagation to basic or applied nuclear science applications, would require several orders of magnitude more calculations than currently possible. However, most of this computational effort would be spent into generating a suitable basis of DFT wavefunctions. Such a task could potentially be considerably accelerated by borrowing tools from the field of machine learning and artificial intelligence. In this paper, we review different approaches to applying supervised and unsupervised learning techniques to nuclear DFT. |
first_indexed | 2024-04-12T07:59:57Z |
format | Article |
id | doaj.art-985f448c06ac48fbb97b6034b5c48bbe |
institution | Directory Open Access Journal |
issn | 2296-424X |
language | English |
last_indexed | 2024-04-12T07:59:57Z |
publishDate | 2022-11-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Physics |
spelling | doaj.art-985f448c06ac48fbb97b6034b5c48bbe2022-12-22T03:41:20ZengFrontiers Media S.A.Frontiers in Physics2296-424X2022-11-011010.3389/fphy.2022.10283701028370Building surrogate models of nuclear density functional theory with Gaussian processes and autoencodersMarc Verriere0Nicolas Schunck1Irene Kim2Irene Kim3Petar Marević4Petar Marević5Petar Marević6Kevin Quinlan7Michelle N. Ngo8Michelle N. Ngo9David Regnier10David Regnier11Raphael David Lasseri12Nuclear and Data Theory Group, Nuclear and Chemical Science Division, Lawrence Livermore National Laboratory, Livermore, CA, United StatesNuclear and Data Theory Group, Nuclear and Chemical Science Division, Lawrence Livermore National Laboratory, Livermore, CA, United StatesMachine Intelligence Group, Center for Applied Scientific Computing, Lawrence Livermore National Laboratory, Livermore, CA, United StatesSensing and Intelligent Systems Group, Global Security Computing Applications Division, Lawrence Livermore National Laboratory, Livermore, CA, United StatesNuclear and Data Theory Group, Nuclear and Chemical Science Division, Lawrence Livermore National Laboratory, Livermore, CA, United StatesCentre Borelli, ENS Paris-Saclay, Université Paris-Saclay, Cachan, FrancePhysics Department, Faculty of Science, University of Zagreb, Zagreb, CroatiaApplied Statistics Group, Lawrence Livermore National Laboratory, Livermore, CA, United StatesApplied Statistics Group, Lawrence Livermore National Laboratory, Livermore, CA, United StatesCenter for Complex Biological Systems, University of California Irvine, Irvine, CA, United StatesUniversité Paris-Saclay, CEA, Laboratoire Matière en Conditions Extrêmes, Bruyères-le-Châtel, FranceCEA, DAM, DIF, Bruyères-le-Châtel, FranceCentre Borelli, ENS Paris-Saclay, Université Paris-Saclay, Cachan, FranceFrom the lightest Hydrogen isotopes up to the recently synthesized Oganesson (Z = 118), it is estimated that as many as about 8,000 atomic nuclei could exist in nature. Most of these nuclei are too short-lived to be occurring on Earth, but they play an essential role in astrophysical events such as supernova explosions or neutron star mergers that are presumed to be at the origin of most heavy elements in the Universe. Understanding the structure, reactions, and decays of nuclei across the entire chart of nuclides is an enormous challenge because of the experimental difficulties in measuring properties of interest in such fleeting objects and the theoretical and computational issues of simulating strongly-interacting quantum many-body systems. Nuclear density functional theory (DFT) is a fully microscopic theoretical framework which has the potential of providing such a quantitatively accurate description of nuclear properties for every nucleus in the chart of nuclides. Thanks to high-performance computing facilities, it has already been successfully applied to predict nuclear masses, global patterns of radioactive decay like β or γ decay, and several aspects of the nuclear fission process such as, e.g., spontaneous fission half-lives. Yet, predictive simulations of nuclear spectroscopy—the low-lying excited states and transitions between them—or of nuclear fission, or the quantification of theoretical uncertainties and their propagation to basic or applied nuclear science applications, would require several orders of magnitude more calculations than currently possible. However, most of this computational effort would be spent into generating a suitable basis of DFT wavefunctions. Such a task could potentially be considerably accelerated by borrowing tools from the field of machine learning and artificial intelligence. In this paper, we review different approaches to applying supervised and unsupervised learning techniques to nuclear DFT.https://www.frontiersin.org/articles/10.3389/fphy.2022.1028370/fullnuclear density functional theoryGaussian processdeep learningautoencodersresnet |
spellingShingle | Marc Verriere Nicolas Schunck Irene Kim Irene Kim Petar Marević Petar Marević Petar Marević Kevin Quinlan Michelle N. Ngo Michelle N. Ngo David Regnier David Regnier Raphael David Lasseri Building surrogate models of nuclear density functional theory with Gaussian processes and autoencoders Frontiers in Physics nuclear density functional theory Gaussian process deep learning autoencoders resnet |
title | Building surrogate models of nuclear density functional theory with Gaussian processes and autoencoders |
title_full | Building surrogate models of nuclear density functional theory with Gaussian processes and autoencoders |
title_fullStr | Building surrogate models of nuclear density functional theory with Gaussian processes and autoencoders |
title_full_unstemmed | Building surrogate models of nuclear density functional theory with Gaussian processes and autoencoders |
title_short | Building surrogate models of nuclear density functional theory with Gaussian processes and autoencoders |
title_sort | building surrogate models of nuclear density functional theory with gaussian processes and autoencoders |
topic | nuclear density functional theory Gaussian process deep learning autoencoders resnet |
url | https://www.frontiersin.org/articles/10.3389/fphy.2022.1028370/full |
work_keys_str_mv | AT marcverriere buildingsurrogatemodelsofnucleardensityfunctionaltheorywithgaussianprocessesandautoencoders AT nicolasschunck buildingsurrogatemodelsofnucleardensityfunctionaltheorywithgaussianprocessesandautoencoders AT irenekim buildingsurrogatemodelsofnucleardensityfunctionaltheorywithgaussianprocessesandautoencoders AT irenekim buildingsurrogatemodelsofnucleardensityfunctionaltheorywithgaussianprocessesandautoencoders AT petarmarevic buildingsurrogatemodelsofnucleardensityfunctionaltheorywithgaussianprocessesandautoencoders AT petarmarevic buildingsurrogatemodelsofnucleardensityfunctionaltheorywithgaussianprocessesandautoencoders AT petarmarevic buildingsurrogatemodelsofnucleardensityfunctionaltheorywithgaussianprocessesandautoencoders AT kevinquinlan buildingsurrogatemodelsofnucleardensityfunctionaltheorywithgaussianprocessesandautoencoders AT michellenngo buildingsurrogatemodelsofnucleardensityfunctionaltheorywithgaussianprocessesandautoencoders AT michellenngo buildingsurrogatemodelsofnucleardensityfunctionaltheorywithgaussianprocessesandautoencoders AT davidregnier buildingsurrogatemodelsofnucleardensityfunctionaltheorywithgaussianprocessesandautoencoders AT davidregnier buildingsurrogatemodelsofnucleardensityfunctionaltheorywithgaussianprocessesandautoencoders AT raphaeldavidlasseri buildingsurrogatemodelsofnucleardensityfunctionaltheorywithgaussianprocessesandautoencoders |