Machine learning modeling of the atomic structure and physical properties of alkali and alkaline-earth aluminosilicate glasses and melts

The first version of the machine learning greybox model i-Melt was trained to predict latent and observed properties of K${}_2$O-Na${}_2$O-Al${}_2$O${}_3$-SiO${}_2$ melts and glasses. Here, we extend the model compositional range, which now allows accurate predictions of properties for glass-forming melts in the CaO-MgO-K${}_2$O-Na${}_2$O-Al${}_2$O${}_3$-SiO${}_2$ system, including melt viscosity (accuracy equal or better than 0.4 log${}_{10}$ Pa$\cdot$s in the 10${}^{-1}$-10${}^{15}$ log${}_{10}$ Pa$\cdot$s range), configurational entropy at glass transition ($\le$ 1 J mol${}^{-1}$ K${}^{-1}$), liquidus ($\le$ 60 K) and glass transition ($\le$ 16 K) temperatures, heat capacity ($\le$ 3 %) as well as glass density ($\le$ 0.02 g cm${}^{-3}$), optical refractive index ($\le$ 0.006), Abbe number ($\le$ 4), elastic modulus ($\le$ 6 GPa), coefficient of thermal expansion ($\le$ 1.1 10${}^{-6}$ K${}^{-1}$) and Raman spectra ($\le$ 25 %). Uncertainties on predictions also are now provided. The model offers new possibilities to explore how melt/glass properties change with composition and atomic structure.