Data-driven prediction of room-temperature density for multicomponent silicate-based glasses

Abstract

Density is one of the most commonly measured or estimated material properties, especially for glasses and melts that are of significant interest to many fields, including metallurgy, geology, materials science, and sustainable cements. Here, three types of machine learning models (i.e., random forest [RF], artificial neural network [ANN], and Gaussian process regression [GPR]) have been developed to predict the room-temperature density of glasses in the compositional space of CaO–MgO–Al2O3–SiO2–TiO2–FeO–Fe2O3–Na2O–K2O–MnO (CMASTFNKM), based on ∼2100 data points mined from ∼140 literature studies. The results show that the RF, ANN, and GPR models give accurate predictions of glass density with R2 values, root mean square error (RMSE), and mean absolute percentage error (MAPE) of ∼0.95–0.97, ∼0.03–0.04 g/cm3 and ∼0.63%–0.83%, respectively, for the 15% testing set, which are more accurate compared with empirical density models based on ionic packing ratio (with R2 values, RMSE, and MAPE of ∼0.28–0.91, ∼0.05–0.15 g/cm3, and ∼1.40%–4.61%, respectively). Furthermore, glass density is shown to be a reliable reactivity indicator for a range of CaO–Al2O3–SiO2 (CAS) and volcanic glasses due to its strong correlation (R2 values above ∼0.90) with the average metal–oxygen dissociation energy (a structural descriptor) of these glasses. Analysis of the predicted density–composition relationships from these models (for selected compositional subspaces) suggests that the single-layer ANN and GPR models exhibit a certain level of transferability (i.e., ability to extrapolate to compositional spaces not [or less] covered in the database) and capture some known features, including the mixed alkaline earth (or alkali) effects.