ISSN print edition: 0366-6352 ISSN electronic edition: 1336-9075 Registr. No.: MK SR 9/7 Published monthly

Artificial intelligence in polymer chemistry: opportunities and challenges

Ch. M. Seyidova, N. T. Shikhverdiyeva, H. F. Aslanova, N. T. Rahimli, N. A. Zeynalov, D. B. Tagiyev, F. C. Amiraslanova, and I. V. Shikhverdiyev

Institute of Catalysis and Inorganic Chemistry Named After Academician M. Nagiyev, Ministry of Science and Education of the Republic of Azerbaijan, Baku, Azerbaijan

E-mail: chcicekseyidova@gmail.com

Received: 9 May 2025  Accepted: 1 September 2025

Abstract:

This review examines the transformative role of Artificial Intelligence (AI) in polymer chemistry, highlighting both the opportunities and challenges in this rapidly evolving field. The integration of AI technologies has revolutionized traditional approaches to polymer design, synthesis, and characterization, enabling more efficient and precise materials development. We discuss key applications including the optimization of synthesis processes, the prediction of polymer properties, advanced material characterization, and molecular dynamics simulations. The review emphasizes how AI-driven approaches accelerate the discovery of novel polymers and enhance our understanding of structure–property relationships. While significant advantages are noted, including accelerated material discovery, improved process optimization, and enhanced predictive capabilities, we also address critical challenges such as limited data availability, complexity in polymer representation, and the interdisciplinary knowledge gap between AI and polymer science. The paper concludes with future perspectives on emerging AI applications in polymer chemistry, highlighting potential developments in sustainable materials, personalized medicine, and advanced manufacturing. This comprehensive analysis provides insights into how AI is reshaping polymer chemistry and outlines the path toward more efficient and innovative materials development.

Keywords: Artificial intelligence; Polymer chemistry; Machine learning; Materials discovery; Property prediction; Synthesis optimization; Molecular dynamics

Full paper is available at www.springerlink.com.

DOI: 10.1007/s11696-025-04509-3

Chemical Papers 80 (3) 2021–2039 (2026)