Predicting Pair Correlation Functions of Glasses using Machine Learning

Abstract

Glasses offer a broad range of tunable thermophysical properties that are linked to their compositions. However, it is challenging to establish a universal composition-property relation of glasses due to their enormous composition and chemical space. Here, we address this problem and develop a metamodel of composition-atomistic structure relation of a class of glassy material via a machine learning (ML) approach. Within this ML framework, an unsupervised deep learning technique, viz. convolutional neural network (CNN) autoencoder, and a regression algorithm, viz. random forest (RF), are integrated into a fully automated pipeline to predict the spatial distribution of atoms in a glass. The RF regression model predicts the pair correlation function of a glass in a latent space. Subsequently, the decoder of the CNN converts the latent space representation to the actual pair correlation function of the given glass. The atomistic structures of silicate (SiO2) and sodium borosilicate (NBS) based glasses with varying compositions and dopants are collected from molecular dynamics (MD) simulations to establish and validate this ML pipeline. The model is found to predict the atom pair correlation function for many unknown glasses very accurately. This method is very generic and can accelerate the design, discovery, and fundamental understanding of composition-atomistic structure relations of glasses and other materials.