Predicting the dissolution kinetics of silicate glasses using machine learning

TL;DR

This paper explores machine learning models, especially neural networks, to accurately predict the complex dissolution rates of aluminosilicate glasses across various pH conditions, aiming to aid in designing tailored glass materials.

Contribution

It demonstrates that neural networks outperform traditional linear models in predicting glass dissolution kinetics, highlighting the potential of data-driven approaches in materials science.

Findings

Linear models fail to predict dissolution rates accurately.

Artificial neural networks provide excellent predictive performance.

Machine learning can accelerate the design of novel glasses.

Abstract

Predicting the dissolution rates of silicate glasses in aqueous conditions is a complex task as the underlying mechanism(s) remain poorly understood and the dissolution kinetics can depend on a large number of intrinsic and extrinsic factors. Here, we assess the potential of data-driven models based on machine learning to predict the dissolution rates of various aluminosilicate glasses exposed to a wide range of solution pH values, from acidic to caustic conditions. Four classes of machine learning methods are investigated, namely, linear regression, support vector machine regression, random forest, and artificial neural network. We observe that, although linear methods all fail to describe the dissolution kinetics, the artificial neural network approach offers excellent predictions, thanks to its inherent ability to handle non-linear data. Overall, we suggest that a more extensive use of machine learning approaches could significantly accelerate the design of novel glasses with tailored properties.