Machine-Learning Molecular Dynamics Study on the Structure and Glass Transition of Calcium Aluminosilicate Glasses

Calcium aluminosilicate (CAS) glass systems represent an important class of materials for industrial applications due to their superior thermal and mechanical properties. Although CAS glasses have been extensively studied, the structure–property relationships--particularly in the peraluminous region (Al2O3/CaO >1)--remain insufficiently understood. Experimental studies have identified the presence of five-coordinated aluminum (Al5) depending on the Al2O3 content; however, classical molecular dynamics (CMD) simulations have struggled to accurately reproduce the aluminum coordination environment. To address this limitation, we developed a MLP tailored for CAS systems, trained on a comprehensive DFT-MD dataset and refined using a fine-tuning approach. Melt-quench simulations were then carried out to model CAS glass structures. The resulting structures from MLMD accurately reproduced both experimental glass densities and the fractions of Al5, including the observed increase in Al5 and oxygen triclusters (TBO) in the peraluminous region. In addition, we performed heating simulations to evaluate enthalpy changes and structural evolution as a function of temperature. Analogous to differential scanning calorimetry (DSC) experiments, the glass transition temperature was determined from the MLMD data. The compositional dependence of Al5 and TBO near the glass transition temperature (Tg) was quantitatively analyzed, providing insights into the role of aluminum in structural rearrangements. These findings demonstrate that MLMD enables accurate modeling of CAS glass structures and yields valuable insights into their thermal behavior. This approach offers a robust framework for understanding structure–property relationships in complex glass systems.