This paper introduces a physics-informed machine learning approach to predict the non-linear composition-structure relations in oxide glasses. The combined model, integrating statistical mechanics and a multilayer perceptron neural network (MLP-NN), shows improved prediction accuracy compared to models using either method individually, accurately interpolating and extrapolating the structure of Na₂O-SiO₂ glasses, even predicting the structure of a previously unseen Na₂O-P₂O₅-SiO₂ glass system.
Publisher
npj Computational Materials
Published On
Sep 09, 2022
Authors
Mikkel L. Bødker, Mathieu Bauchy, Tao Du, John C. Mauro, Morten M. Smedskjaer
Tags
machine learning
oxide glasses
structure prediction
multilayer perceptron
Na₂O-SiO₂
composition-structure relations
statistical mechanics
Related Publications
Explore these studies to deepen your understanding of the subject.
