Machine Learning Forcefield for Silicate Glasses
arXiv:1902.03486
Abstract
Developing accurate, transferable, and computationally-efficient interatomic forcefields is key to facilitate the modeling of silicate glasses. However, the high number of forcefield parameters that need to be optimized render traditional parameterization methods poorly efficient or potentially subject to bias. Here, we present a new forcefield parameterization methodology based on ab initio molecular dynamics simulations, Gaussian process regression, and Bayesian optimization. By taking the example of glassy silica, we show that our methodology yields a new interatomic forcefield that offers an unprecedented description of the atomic structure of silica. This methodology offers a new route to efficiently parameterize new empirical interatomic forcefields for silicate glasses with very limited need for intuition.
References in corpus (8)
- ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
- Cooling rate effects in amorphous Silica: A Computer Simulation Study
- Machine-learning based interatomic potential for amorphous carbon
- Machine learning a general purpose interatomic potential for silicon
- Bayesian optimization for materials design
- A New Transferable Interatomic Potential for Molecular Dynamics Simulations of Borosilicate Glasses
- Cooling-Rate Effects in Sodium Silicate Glasses: Bridging the Gap between Molecular Dynamics Simulations and Experiments
- Structural properties of a calcium aluminosilicate glass from molecular-dynamics simulations: A finite size effects study