Interpreting Molecular Descriptors for Glass Transition Temperature Prediction and Design of Polyimides

The rational design of polyimides (PIs) with targeted glass transition temperature (T_g) is crucial for advanced microelectronics applications. While data-driven approaches offer promise, there is a pressing need for models that are not only predictive but also physically interpretable, especially with limited datasets. Herein, we present a highly interpretable Quantitative Structure-Property Relationship (QSPR) model for accurate T_g prediction of PIs. Employing a Genetic Algorithm combined with Multiple Linear Regression (GA-MLR), we identified an optimal set of seven molecular descriptors from a curated dataset. The model demonstrates robust predictive performance and strong generalization ability, validated through rigorous statistical tests. Crucially, we provide a deep physicochemical interpretation of the descriptors, unifying their influence under the framework of free volume theory. We show that key descriptors govern T_g by modulating the fractional free volume through distinct mechanisms: descriptors like Chi0n increase free volume by introducing molecular branching that disrupts chain packing, while MinPartialCharge influences T_g through its effect on intermolecular interactions. This mechanistic understanding is translated into clear molecular design guidelines, distinguishing strategies for achieving high-T_g versus processable, low-T_g polymers. Our work establishes a reliable and transparent computational tool that bridges data-driven prediction with fundamental chemical insight for accelerating PIs development.