Predicting the dissolution kinetics of silicate glasses by topology-informed machine learning

TLDR

Machine‑learning regression methods are promising for predicting material properties, yet they often lack reliable extrapolation and can violate physical laws. This study introduces a topology‑informed ML paradigm that uses network‑topology features as fingerprints to predict the forward (stage I) dissolution rate of silicate glasses. The authors apply this approach by feeding topological descriptors of the atomic network into ML models to forecast stage I dissolution rates for a series of silicate glasses. The results show that topology‑informed ML improves prediction accuracy, simplifies models, reduces required training data, and enhances extrapolation, thereby overcoming the accuracy–simplicity trade‑off of traditional ML.

Abstract

Abstract Machine learning (ML) regression methods are promising tools to develop models predicting the properties of materials by learning from existing databases. However, although ML models are usually good at interpolating data, they often do not offer reliable extrapolations and can violate the laws of physics. Here, to address the limitations of traditional ML, we introduce a “topology-informed ML” paradigm—wherein some features of the network topology (rather than traditional descriptors) are used as fingerprint for ML models—and apply this method to predict the forward (stage I) dissolution rate of a series of silicate glasses. We demonstrate that relying on a topological description of the atomic network (i) increases the accuracy of the predictions, (ii) enhances the simplicity and interpretability of the predictive models, (iii) reduces the need for large training sets, and (iv) improves the ability of the models to extrapolate predictions far from their training sets. As such, topology-informed ML can overcome the limitations facing traditional ML (e.g., accuracy vs. simplicity tradeoff) and offers a promising route to predict the properties of materials in a robust fashion.