Answers are grounded in this paper and cite their sources.
Borosilicate glasses are extensively used in a variety of applications from kitchenware to nuclear waste immobilization due to the strong network formed by the Si─O─B bond that makes it resistant to chemical corrosion and gives it a low thermal expansion. Boron, however, exists in both trigonal BO 3 and tetrahedral BO 4 bonds in glass systems, which impacts the chemical durability and thermal resistance of the glass, among other properties. The fraction of four‐coordinated boron (N 4 = BO 4 /[BO 3 + BO 4 ]) within a glass may aid in predicting these properties, but it is difficult to derive without experimental data due to the complexity of impacts from varied glass compositions and processing factors. For this reason, compositional models have been developed to predict N 4 , but the models typically include a limited number (< 5) of components. To help fill this gap in the models, in this work, a diverse multicomponent glass dataset of 809 glasses is compiled from a literature search, and then a number of analytical and machine learning (ML) models are trained on the dataset. Previously developed modified Bernstein and modified Du and Stebbins (MDS) analytical models were fitted to update parameters with the new dataset. Then, partially Bayesian neural networks, Gaussian process regression, and heteroskedastic deterministic neural networks were evaluated. The ML models examined all have different strategies to overcome the potential for overfitting as a result of a limited training dataset, and return results that account for model uncertainty, which can be valuable for understanding model reliability. For the first time, cooling rate is introduced as an input parameter for ML models, showing consistent improvements in performance and solidifying the importance of including parameters outside of composition alone for N 4 prediction. The ML models examined here show promise in accurate predictions of N 4 in borosilicate glasses, all achieving R 2 values of 0.91. These accurate predictions can be used to inform glass design around specific structural properties, accelerating the speed of scientific development.
No takes yet. Share an insight, caveat, or question.
Curry et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: