Glass Transition Prediction of Binary Copolymers Across Large Chemical Spaces Using Machine Learning and Physics-Based Modeling

Abstract

The glass transition temperature (Tg) is a pivotal design parameter for polymer performance across diverse applications, yet its rapid prediction within expansive chemical spaces remains a challenge. We present a machine learning (ML) framework for the high-throughput prediction of Tg in binary copolymers, trained on experimental datasets encompassing both homopolymers and copolymers. We evaluate various ML architectures, including graph-based algorithms, to effectively capture non-linear composition–property relationships. The optimized model achieves high predictive accuracy with an RMSE of ~14K and an R2 of ~0.98. Crucially, the framework accounts for the chemical diversity of monomeric units by integrating structural descriptors with molar composition ratios, enabling the model to capture complex dependencies of thermal stability on chemical structure and composition. We validate the model’s robustness using physics-based molecular dynamics (MD) simulations. To showcase the platform’s scalability, we generated a library of approximately 148,000 binary copolymer compositions and predicted their Tg, facilitating the rapid mapping of vast design spaces. This extensive virtual library enables the identification of optimal monomer pairings that would be experimentally inaccessible through traditional trial-and-error methods. Through these large-scale exploration studies, we demonstrate the ability to design copolymers for targeted applications, including a specific case study on elastomeric systems. This integrated approach, combining experimental data, ML modeling, and physics-based validation, offers a transformative path for the accelerated discovery and multi-property optimization of functional copolymers.