Designing new glasses requires a priori knowledge of how the composition of a glass dictates its properties such as stiffness, density, or processability. Developing multi-property design charts, namely, glass selection charts, using deep learning can enable discovery of novel glasses with targeted properties.

Machine learning (ML) methods are becoming popular tools for the prediction and design of novel materials. In particular, neural network (NN) is a promising ML method, which can be used to identify hidden trends in the data. However, these methods rely on large datasets and often exhibit overfitting when used with sparse dataset. Further, assessing the uncertainty in predictions for a new dataset or an extrapolation of the present dataset is challenging. Herein, using Gaussian process regression (GPR), we predict Young's modulus for silicate glasses having sparse dataset. We show that GPR significantly outperforms NN for sparse dataset, while ensuring no overfitting. Further, thanks to the nonparametric nature, GPR provides quantitative bounds for the reliability of predictions while extrapolating. Overall, GPR presents an advanced ML methodology for accelerating the development of novel functional materials such as glasses.

Scalable Gaussian process for predicting composition–property of glasses with large datasets.

No abstract

No abstract