Development and Validation of Neural Network Potentials for Multicomponent Oxide Glasses

10 July 2024, Version 2
This content is a preprint and has not undergone peer review at the time of posting.

Abstract

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 ({\MLMD}) with the developed {\MLP}. The accuracy of {\MLMD} 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 \ce{Na2O}--\ce{SiO2} and \ce{Na2O}--\ce{B2O3} glass systems was well reproduced for the {\MLMD}-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 {\MLMD} results using {\MLP} developed with and without pre-training. Although better metric scores for {\MLP} 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 {\MLP} for glasses. Finally, the developed {\MLMD} was applied to the modeling of the reference nuclear waste glass (60.1{\Si}--3.84{\Al}--15.97{\B}--12.65{\Na}--2.87{\Ca}--2.86{\Mg}--1.72{\Zr}), and the charge compensation mechanism of the cations was discussed.

Keywords

Molecular Dynamics
Oxide Glasss
Machine Leaning Potentials
Neural Network Potentials

Supplementary materials

Title
Description
Actions
Title
Supporting information
Description
- Table of the oxide compositions for DFT-MD to generate training data. - Detailed parameter sets for developing MLP. - Behavior of the loss function during pre- and fine-tuning of the developed MLP. - Comparison of energy, force, and virial data between DFT and MLP predictions. - Comparison of the NB00 glass structure derived from MLP with and without pre-training. - Loss functions and test results of MLP with and without pre-training.
Actions

Comments

Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.