Machine learning discovery of high-temperature polymers

Summary

To formulate a machine learning (ML) model to establish the polymer's structure-property correlation for glass transition temperature $T_g$ , 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 $T_g$ values using Morgan fingerprint representations of chemical structures for these polymers. Interestingly, the trained DNN model can reasonably predict the unknown $T_g$ 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 $T_g$ > 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.

Graphical abstract

Highlights

• •

  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 bigger picture

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.

Abstract

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.