Title: 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 » 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.« less

Authors:

Stippell, Elizabeth Louise  ^[1];

• Search DOE PAGES for author "Stippell, Elizabeth Louise"
• Search DOE PAGES for ORCID "0000-0002-7576-4764"

Alzate-Vargas, Lorena Leidy  ^[2];

• Search DOE PAGES for author "Alzate-Vargas, Lorena Leidy"
• Search DOE PAGES for ORCID "0000-0002-4223-4046"

Subedi, Kashi Nath  ^[2];

• Search DOE PAGES for author "Subedi, Kashi Nath"
• Search DOE PAGES for ORCID "0000-0002-6237-3801"

Tutchton, Roxanne M'liss  ^[2];

• Search DOE PAGES for author "Tutchton, Roxanne M'liss"
• Search DOE PAGES for ORCID "0000-0001-8521-3504"

Cooper, Michael William DOnald  ^[2];

• Search DOE PAGES for author "Cooper, Michael William DOnald"
• Search DOE PAGES for ORCID "0000-0001-8270-7947"

Tretiak, Sergei ^[2]; Gibson, Tammie Renee  ^[2];

• Search DOE PAGES for author "Gibson, Tammie Renee"
• Search DOE PAGES for ORCID "0000-0002-3173-5291"

Messerly, Richard Alma  ^[2]

• Search DOE PAGES for author "Messerly, Richard Alma"
• Search DOE PAGES for ORCID "0000-0003-1321-4246"

---

+ Show Author Affiliations

1. Los Alamos National Laboratory (LANL), Los Alamos, NM (United States); Univ. of Southern California, Los Angeles, CA (United States)
2. Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)

Publication Date:

Tue Dec 26 00:00:00 EST 2023

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