To formulate a machine learning (ML) model to establish the polymer's structure-property correlation for glass transition temperature , we collect a diverse set of nearly 13,000 real homopolymers from the largest polymer database, PoLyInfo. We train the deep neural network (DNN) model with 6,923 experimental values using Morgan fingerprint representations of chemical structures for these polymers. Interestingly, the trained DNN model can reasonably predict the unknown values of polymers with distinct molecular structures, in comparison with molecular dynamics simulations and experimental results. With the validated transferability and generalization ability, the ML model is utilized for high-throughput screening of nearly one million hypothetical polymers. We identify more than 65,000 promising candidates with > 200°C, which is 30 times more than existing known high-temperature polymers (∼2,000 from PoLyInfo). The discovery of this large number of promising candidates will be of significant interest in the development and design of high-temperature polymers.
Large datasets for polymer's glass transition temperature are collected
Transferability of ML models depends on feature representations
Molecular dynamics models and experimental results validate the formulated ML model
Extensive promising candidates for high-temperature polymers are screened by ML model
The design and development of high-temperature polymers has been an experimentally driven and trial-and-error process guided by experience, intuition, and conceptual insights. However, such an Edisonian approach is often costly, slow, biased toward certain chemical space domains, and limited to relatively small-scale studies, which may easily miss promising compounds. To overcome this challenge, we formulate a data-driven machine learning (ML) approach, integrated with high-fidelity molecular dynamics simulations, for quantitatively predicting the glass transition temperature of a polymer from its chemical structure and rapid screening of promising candidates for high-temperature polymers. Our work demonstrates that ML is a powerful method for the prediction and rapid screening of high-temperature polymers, particularly with growing large sets of experimental and computational data for polymeric materials.
Polymers with outstanding high-temperature properties have been identified as promising materials for aerospace, electronics, and automotive applications. However, the current design and development of high-temperature polymers has been an experimentally driven and trial-and-error process guided by experience, intuition, and conceptual insights. Therefore, we formulate a machine learning model that can quantitatively predict the glass transition temperature of a polymer from its chemical structure, such that more promising high-temperature polymers can be efficiently filtered out through high-throughput screening.