Efficient Prediction of Polymer Glass Transition Temperatures through Machine Learning Methods

Abstract

The glass transition temperature (T_g) plays a crucial role in defining polymer properties. Despite the widespread use of machine learning for material design and property prediction, there are still challenges concerning the interpretability and model performance when predicting T_g. In this study, Simplified Molecular Input Line Entry System strings are utilised to encode the polymer structure, which are then transformed into molecular descriptors for analytical training and prediction of T_g using Artificial Neural Network and Random Forest models. Meticulous hyperparameter tuning of the Random Forest model was performed, resulting in reasonable T_g predictions. This methodology forges a connection between polymer structure and T_g, opening up new avenues for research in the field of polymers.