Recent Advances in Polymer Design through Machine Learning: A Short Review

Polymers are widely used across diverse industries, including medicine, energy storage, construction, aerospace, agriculture, transportation, and electronics. However, the complexity and variability of polymer chemical compositions and structures present significant challenges for their development. The integration of machine learning (ML) algorithms with large datasets has opened new avenues for advancements in polymer science. Polymer informatics focuses on predicting polymer performance and optimizing synthesis conditions using ML models. With the growing availability of comprehensive datasets and ongoing improvements in ML techniques, polymer informatics can now be applied more effectively and systematically. This study provides a concise overview of the application of various ML approaches, including supervised learning, unsupervised learning, and artificial neural networks (ANNs), for predicting and classifying the properties of different polymers.