Development of a machine-learning interatomic potential for uranium under the moment tensor potential framework

HJ Chen and DW Yuan and HY Geng and WY Hu and BW Huang, COMPUTATIONAL MATERIALS SCIENCE, 229, 112376 (2023).

DOI: 10.1016/j.commatsci.2023.112376

Uranium is attracting growing interest across fundamental science and nuclear research, where atomistic sim-ulations remain challenging. In this study, we developed a novel uranium interatomic potential based on a machine-learning approach embedded in the moment tensor potential package. An active learning framework was utilized in the potential training, using density-functional theory plus Hubbard U (DFT+U) modified data. The potential accurately reproduced the lattice parameters, cohesive energy, elastic, vibrational, and thermo-dynamic properties of & alpha;-U compared to DFT+U calculations and experimental results. The basic properties of other phases, including fl, & gamma;, HCP, and FCC phases, were also validated. In addition, molecular dynamics sim-ulations were used to reproduce the temperature-induced allotropic transformation from & alpha;-U to & gamma;-U, which agrees with experimental observations. Our potential provides a computationally efficient means to study the physical behavior of uranium with nearly DFT accuracy.

Return to Publications page