Building a DFT+U machine learning interatomic potential for uranium dioxide
Abstract
Despite uranium dioxide (UO2) being a widely used nuclear fuel, fuel performance models rely extensively on empirical correlations of material behavior, leveraging the historical operating experience of UO2. Mechanistic models that consider an atomistic understanding of the processes governing fuel performance (such as fission gas release and creep) will enable a better description of fuel behavior under non-prototypical conditions such as in new reactor concepts or for modified UO2 fuel compositions. To this end, molecular dynamics simulation is a powerful tool for rapidly predicting physical properties of proposed fuel candidates. However, the reliability of these simulations depends largely on the accuracy of the atomic forces. Traditionally, these forces are computed using either a classical force field (FF) or density functional theory (DFT). While DFT is relatively accurate, the computational cost is burdensome, especially for f-electron elements, such as actinides. By contrast, classical FFs are computationally efficient but are less accurate. For these reasons, we report a new accurate machine learning interatomic potential (MLIP) for UO2 that provides high-fidelity reproduction of DFT forces at a similar low cost to classical FFs. We employ an active learning approach that autonomously augments the DFT training data set to iteratively refine the MLIP. Tomore »
- Authors:
-
- Los Alamos National Laboratory (LANL), Los Alamos, NM (United States); Univ. of Southern California, Los Angeles, CA (United States)
- Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
- Publication Date:
- Research Org.:
- Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
- Sponsoring Org.:
- USDOE Laboratory Directed Research and Development (LDRD) Program; USDOE National Nuclear Security Administration (NNSA)
- OSTI Identifier:
- 2290323
- Report Number(s):
- LA-UR-23-29839
Journal ID: ISSN 2949-7477
- Grant/Contract Number:
- 89233218CNA000001
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Artificial Intelligence Chemistry
- Additional Journal Information:
- Journal Volume: 2; Journal Issue: 1; Journal ID: ISSN 2949-7477
- Publisher:
- Elsevier
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS; Machine learning; Molecular dynamics; Actinides; Atomistic simulations
Citation Formats
Stippell, Elizabeth Louise, Alzate-Vargas, Lorena Leidy, Subedi, Kashi Nath, Tutchton, Roxanne M'liss, Cooper, Michael William DOnald, Tretiak, Sergei, Gibson, Tammie Renee, and Messerly, Richard Alma. Building a DFT+U machine learning interatomic potential for uranium dioxide. United States: N. p., 2023.
Web. doi:10.1016/j.aichem.2023.100042.
Stippell, Elizabeth Louise, Alzate-Vargas, Lorena Leidy, Subedi, Kashi Nath, Tutchton, Roxanne M'liss, Cooper, Michael William DOnald, Tretiak, Sergei, Gibson, Tammie Renee, & Messerly, Richard Alma. Building a DFT+U machine learning interatomic potential for uranium dioxide. United States. https://doi.org/10.1016/j.aichem.2023.100042
Stippell, Elizabeth Louise, Alzate-Vargas, Lorena Leidy, Subedi, Kashi Nath, Tutchton, Roxanne M'liss, Cooper, Michael William DOnald, Tretiak, Sergei, Gibson, Tammie Renee, and Messerly, Richard Alma. Tue .
"Building a DFT+U machine learning interatomic potential for uranium dioxide". United States. https://doi.org/10.1016/j.aichem.2023.100042. https://www.osti.gov/servlets/purl/2290323.
@article{osti_2290323,
title = {Building a DFT+U machine learning interatomic potential for uranium dioxide},
author = {Stippell, Elizabeth Louise and Alzate-Vargas, Lorena Leidy and Subedi, Kashi Nath and Tutchton, Roxanne M'liss and Cooper, Michael William DOnald and Tretiak, Sergei and Gibson, Tammie Renee and Messerly, Richard Alma},
abstractNote = {Despite uranium dioxide (UO2) being a widely used nuclear fuel, fuel performance models rely extensively on empirical correlations of material behavior, leveraging the historical operating experience of UO2. Mechanistic models that consider an atomistic understanding of the processes governing fuel performance (such as fission gas release and creep) will enable a better description of fuel behavior under non-prototypical conditions such as in new reactor concepts or for modified UO2 fuel compositions. To this end, molecular dynamics simulation is a powerful tool for rapidly predicting physical properties of proposed fuel candidates. However, the reliability of these simulations depends largely on the accuracy of the atomic forces. Traditionally, these forces are computed using either a classical force field (FF) or density functional theory (DFT). While DFT is relatively accurate, the computational cost is burdensome, especially for f-electron elements, such as actinides. By contrast, classical FFs are computationally efficient but are less accurate. For these reasons, we report a new accurate machine learning interatomic potential (MLIP) for UO2 that provides high-fidelity reproduction of DFT forces at a similar low cost to classical FFs. We employ an active learning approach that autonomously augments the DFT training data set to iteratively refine the MLIP. To further improve the quality of our predictions, we utilize transfer learning to retrain our MLIP to higher-accuracy DFT+U data. We validate our MLIPs by comparing predicted physical properties (e.g., thermal expansion and elastic properties) with those from existing classical FFs and DFT/DFT+U calculations, as well as with experimental data when available.},
doi = {10.1016/j.aichem.2023.100042},
journal = {Artificial Intelligence Chemistry},
number = 1,
volume = 2,
place = {United States},
year = {Tue Dec 26 00:00:00 EST 2023},
month = {Tue Dec 26 00:00:00 EST 2023}
}
Works referenced in this record:
Occupation matrix control of d- and f-electron localisations using DFT + U
journal, January 2014
- Allen, Jeremy P.; Watson, Graeme W.
- Phys. Chem. Chem. Phys., Vol. 16, Issue 39
Generalized Gradient Approximation Made Simple
journal, October 1996
- Perdew, John P.; Burke, Kieron; Ernzerhof, Matthias
- Physical Review Letters, Vol. 77, Issue 18, p. 3865-3868
Automated discovery of a robust interatomic potential for aluminum
journal, February 2021
- Smith, Justin S.; Nebgen, Benjamin; Mathew, Nithin
- Nature Communications, Vol. 12, Issue 1
The Rise of Neural Networks for Materials and Chemical Dynamics
journal, July 2021
- Kulichenko, Maksim; Smith, Justin S.; Nebgen, Benjamin
- The Journal of Physical Chemistry Letters, Vol. 12, Issue 26
Thermophysical properties of uranium dioxide
journal, March 2000
- Fink, J. K.
- Journal of Nuclear Materials, Vol. 279, Issue 1
ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost
journal, January 2017
- Smith, J. S.; Isayev, O.; Roitberg, A. E.
- Chemical Science, Vol. 8, Issue 4
A many-body potential approach to modelling the thermomechanical properties of actinide oxides
journal, February 2014
- Cooper, M. W. D.; Rushton, M. J. D.; Grimes, R. W.
- Journal of Physics: Condensed Matter, Vol. 26, Issue 10
Elastic properties of UO 2 at high pressure
journal, October 1976
- Fritz, I. J.
- Journal of Applied Physics, Vol. 47, Issue 10
An artificial neural network potential for uranium metal at low pressures
journal, September 2023
- Hao 郝, Maosheng 茂生; Guan 管, Pengfei 鹏飞
- Chinese Physics B, Vol. 32, Issue 9
Machine learning molecular dynamics simulations toward exploration of high-temperature properties of nuclear fuel materials: case study of thorium dioxide
journal, June 2022
- Kobayashi, Keita; Okumura, Masahiko; Nakamura, Hiroki
- Scientific Reports, Vol. 12, Issue 1
Behavior of actinide dioxides under pressure: and
journal, July 2004
- Idiri, M.; Le Bihan, T.; Heathman, S.
- Physical Review B, Vol. 70, Issue 1
A molecular dynamics study of radiation induced diffusion in uranium dioxide
journal, March 2009
- Martin, G.; Maillard, S.; Brutzel, L. Van
- Journal of Nuclear Materials, Vol. 385, Issue 2
Comparison of interatomic potentials for UO2. Part I: Static calculations
journal, June 2007
- Govers, K.; Lemehov, S.; Hou, M.
- Journal of Nuclear Materials, Vol. 366, Issue 1-2
The atomic simulation environment—a Python library for working with atoms
journal, June 2017
- Hjorth Larsen, Ask; Jørgen Mortensen, Jens; Blomqvist, Jakob
- Journal of Physics: Condensed Matter, Vol. 29, Issue 27
calculations of the ground state and metastable states of uranium dioxide
journal, June 2009
- Dorado, Boris; Amadon, Bernard; Freyss, Michel
- Physical Review B, Vol. 79, Issue 23
Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set
journal, October 1996
- Kresse, G.; Furthmüller, J.
- Physical Review B, Vol. 54, Issue 16, p. 11169-11186
From ultrasoft pseudopotentials to the projector augmented-wave method
journal, January 1999
- Kresse, G.; Joubert, D.
- Physical Review B, Vol. 59, Issue 3, p. 1758-1775
Ab initio interionic potentials for UN by multiple lattice inversion
journal, September 2010
- Chen, P. H.; Wang, X. L.; Lai, X. C.
- Journal of Nuclear Materials, Vol. 404, Issue 1
Fast Parallel Algorithms for Short-Range Molecular Dynamics
journal, March 1995
- Plimpton, Steve
- Journal of Computational Physics, Vol. 117, Issue 1
Electron-energy-loss spectra and the structural stability of nickel oxide: An LSDA+U study
journal, January 1998
- Dudarev, S. L.; Botton, G. A.; Savrasov, S. Y.
- Physical Review B, Vol. 57, Issue 3, p. 1505-1509
An atomistic approach to self-diffusion in uranium dioxide
journal, May 2010
- Dorado, Boris; Durinck, Julien; Garcia, Philippe
- Journal of Nuclear Materials, Vol. 400, Issue 2
Phonon Lifetime Investigation of Anharmonicity and Thermal Conductivity of by Neutron Scattering and Theory
journal, April 2013
- Pang, Judy W. L.; Buyers, William J. L.; Chernatynskiy, Aleksandr
- Physical Review Letters, Vol. 110, Issue 15
DFT + U investigation of charged point defects and clusters in UO 2
journal, July 2014
- Vathonne, Emerson; Wiktor, Julia; Freyss, Michel
- Journal of Physics: Condensed Matter, Vol. 26, Issue 32
First principles calculation of the elastic constants and phonon modes of UO2 using GGA+U with orbital occupancy control
journal, May 2011
- Devey, A. J.
- Journal of Nuclear Materials, Vol. 412, Issue 3
Ab initiomolecular dynamics for liquid metals
journal, January 1993
- Kresse, G.; Hafner, J.
- Physical Review B, Vol. 47, Issue 1, p. 558-561
Development of a machine-learning interatomic potential for uranium under the moment tensor potential framework
journal, October 2023
- Chen, Hongjian; Yuan, Dingwang; Geng, Huayun
- Computational Materials Science, Vol. 229
Computer simulation of defects formation and equilibrium in non-stoichiometric uranium dioxide
journal, May 2009
- Yakub, E.; Ronchi, C.; Staicu, D.
- Journal of Nuclear Materials, Vol. 389, Issue 1
Point defects in uranium dioxide: Ab initio pseudopotential approach in the generalized gradient approximation
journal, December 2005
- Freyss, Michel; Petit, Thierry; Crocombette, Jean-Paul
- Journal of Nuclear Materials, Vol. 347, Issue 1-2
DFT + U Study of Uranium Dioxide and Plutonium Dioxide with Occupation Matrix Control
journal, July 2022
- Chen, Jia-Li; Kaltsoyannis, Nikolas
- The Journal of Physical Chemistry C, Vol. 126, Issue 27
Capturing the ground state of uranium dioxide from first principles: Crystal distortion, magnetic structure, and phonons
journal, September 2022
- Zhou, Shuxiang; Ma, Hao; Xiao, Enda
- Physical Review B, Vol. 106, Issue 12
A comparative analysis of the phonon properties in UO2 using the Boltzmann transport equation coupled with DFT + U and empirical potentials
journal, May 2020
- Torres, E.; CheikNjifon, I.; Kaloni, T. P.
- Computational Materials Science, Vol. 177
Plane-wave pseudopotential study of point defects in uranium dioxide
journal, August 2001
- Crocombette, J. P.; Jollet, F.; Nga, L. Thien
- Physical Review B, Vol. 64, Issue 10
A molecular dynamics study of the heat capacity of uranium mononitride
journal, February 2000
- Kurosaki, Ken; Yano, Kimihiko; Yamada, Kazuhiro
- Journal of Alloys and Compounds, Vol. 297, Issue 1-2
Molecular dynamics simulation of premelting and melting phase transitions in stoichiometric uranium dioxide
journal, September 2007
- Yakub, Eugene; Ronchi, Claudio; Staicu, Dragos
- The Journal of Chemical Physics, Vol. 127, Issue 9
Point defects and clustering in uranium dioxide by calculations
journal, March 2008
- Geng, Hua Y.; Chen, Ying; Kaneta, Yasunori
- Physical Review B, Vol. 77, Issue 10
GGA+U study of uranium mononitride: A comparison of the U-ramping and occupation matrix schemes and incorporation energies of fission products
journal, September 2016
- Claisse, Antoine; Klipfel, Marco; Lindbom, Niclas
- Journal of Nuclear Materials, Vol. 478