Predicting Properties of Oxide Glasses Using Informed Neural Networks

TL;DR

This paper introduces an informed neural network model that integrates scientific knowledge to improve the prediction and extrapolation of properties for oxide glasses, outperforming traditional blind neural networks.

Contribution

The paper presents a novel informed neural network approach that enhances extrapolation capabilities in predicting oxide glass properties, leveraging prior scientific knowledge.

Findings

Informed neural networks outperform blind models in property extrapolation.

The model accurately predicts glass transition temperature, Young's modulus, and shear modulus.

Ensemble methods further improve prediction accuracy.

Abstract

Many modern-day applications require the development of new materials with specific properties. In particular, the design of new glass compositions is of great industrial interest. Current machine learning methods for learning the composition-property relationship of glasses promise to save on expensive trial-and-error approaches. Even though quite large datasets on the composition of glasses and their properties already exist (i.e., with more than 350,000 samples), they cover only a very small fraction of the space of all possible glass compositions. This limits the applicability of purely data-driven models for property prediction purposes and necessitates the development of models with high extrapolation power. In this paper, we propose a neural network model which incorporates prior scientific and expert knowledge in its learning pipeline. This informed learning approach leads to an improved extrapolation power compared to blind (uninformed) neural network models. To demonstrate this, we train our models to predict three different material properties, that is, the glass transition temperature, the Young's modulus (at room temperature), and the shear modulus of binary oxide glasses which do not contain sodium. As representatives for conventional blind neural network approaches we use five different feed-forward neural networks of varying widths and depths. For each property, we set up model ensembles of multiple trained models and show that, on average, our proposed informed model performs better in extrapolating the three properties of previously unseen sodium borate glass samples than all five conventional blind models.