Informatics Modeling of High Tg Polymers: Assessing the Role of Processing versus Chemistry

Abstract

Despite the advances in structure-based modeling of polymer properties, accurately predicting glass transition temperature (Tg) is still challenging for polymers whose behavior is strongly influenced by intermolecular interactions and processing conditions. We previously developed a machine-learning model based on polymer topological descriptors to predict Tg. The model performed well and was based solely on the chemistry and structure of the polymer without any inclusion of processing parameters. In this work, we have extended that work by first applying that same model to a larger range of polymers and second by integrating processing parameters into the feature set. The chemistry-based model still demonstrates consistent predictive performance for most polymers, indicating that Tg is indeed primarily chemistry and structure driven and not strongly impacted by processing. However, several polymers exhibited deviations between predicted and experimental Tg values. Detailed analysis reveals that these differences are related to strong intermolecular interactions and processing-dependent factors, particularly for polymers prepared by solution casting and high temperature annealing. These results demonstrate that molecular topology provides a strong foundation for Tg prediction; however, this approach also screens out those classes of polymers for with processing conditions play an important role.