Development and Validation of Neural Network Potentials for Multicomponent Oxide Glasses

A neural network potential (MLP) for molecular dynamics simulation (MD) of multicomponent oxide glasses was developed with special consideration of structural reproducibility. The MLP was constructed through pre-training using the dataset of density functional theory (DFT) data provided by the Open Catalysis project and fine-tuning for the dataset of nine-component glasses. A thorough validation based on previous experimental and DFT-MD data was performed for the glass structure derived from neural network molecular dynamics simulation ({}) with the developed {}. The accuracy of {} was investigated in terms of the local structure of the glass, comparing it to the glass derived from MD with conventional potentials. The composition dependence of the local structure in {Na2O}--{SiO2} and {Na2O}--{B2O3} glass systems was well reproduced for the {}-derived glass. The ability to reproduce the glass structure was demonstrated in the population of four-coordinated boron population and formation of superstructures in alkali borate glasses, and the Al local structure in the novel Al-rich binary aluminoborosilicate glass. The importance of pre-training was revealed by comparing {} results using {} developed with and without pre-training. Although better metric scores for {} without pre-training can be achieved, the resultant structure was not realistic. This is an important lesson that the metric score alone is inadequate to construct accurate {} for glasses. Finally, the developed {} was applied to the modeling of the reference nuclear waste glass (60.1{}--3.84{}--15.97{}--12.65{}--2.87{}--2.86{}--1.72{}), and the charge compensation mechanism of the cations was discussed.