Machine Learning Approaches in Polymer Science: Progress and Fundamental for a New Paradigm

ABSTRACT

Machine learning (ML), material genome, and big data approaches are highly overlapped in their strategies, algorithms, and models. They can target various definitions, distributions, and correlations of concerned physical parameters in given polymer systems, and have expanding applications as a new paradigm indispensable to conventional ones. Their inherent advantages in building quantitative multivariate correlations have largely enhanced the capability of scientific understanding and discoveries, thus facilitating mechanism exploration, target prediction, high‐throughput screening, optimization, and rational and inverse designs. This article summarizes representative progress in the recent two decades focusing on the design, preparation, application, and sustainable development of polymer materials based on the exploration of key physical parameters in the composition–process–structure–property–performance relationship. The integration of both data‐driven and physical insights through ML approaches to deepen fundamental understanding and discover novel polymer materials is categorically presented. Despite the construction and application of robust ML models, strategies and algorithms to deal with variant tasks in polymer science are still in rapid growth. The challenges and prospects are then presented. We believe that the innovation in polymer materials will thrive along the development of ML approaches, from efficient design to sustainable applications.