AI Application Potential and Prospects in Materials Science: A Focus on Polymers

Authors

Raphael Kpoghomou
University of Toulouse, France
Valerie Nassiet
University of Toulouse, France
Bernard Kamsu-Foguem
Tarbes Technological University, France

Keywords:

Artificial Intelligence, Polymers, Materials Science, Predictive Models, Recycling, Intelligent Polymers, Machine Learning, Multimodal Approaches, Quality Control, Energy Reduction, Sustainable Development

Synopsis

This is a Chapter in:

Book:
Intelligent and Sustainable Solutions

Print ISBN 978-1-6692-0012-3
Online ISBN 978-1-6692-0011-6

 

Series:
Chronicle of Computing

Chapter Abstract:

The integration of artificial intelligence (AI) into materials science is profoundly transforming polymer discovery, manufacturing and quality control. This study explores the potential of AI-based approaches in three key areas: (1) prediction of polymer properties using advanced models such as PolymerGNN and PolyBERT, (2) optimization of industrial processes via reinforcement learning to improve energy efficiency and material quality, and (3) automatic defect detection using computer vision models such as YOLOv8 and Faster R-CNN. Experimental results show significant improvements in terms of prediction accuracy, energy consumption reduction (10-25%) and defect identification efficiency. Despite these advances, challenges remain, notably data quality, model interpretability and integration into industrial processes. This study highlights the transformative impact of AI on polymer science, and provides an analysis of the performance of applied models.

About this Paper

Cite this paper as:
Kpoghomou R., Nassiet V., Kamsu-Foguem B. (2025). AI Application Potential and Prospects in Materials Science: A Focus on Polymers. In: Tiako P.F. (ed) Intelligent and Sustainable Solutions. Chronicle of Computing. OkIP. CAIF25#12. https://doi.org/10.55432/978-1-6692-0011-6_2


Presented at:
The 2025 OkIP International Conference on Artificial Intelligence Frontiers (CAIF) in Oklahoma City, Oklahoma, USA, and Online, on April 2, 2025

Contact:
Raphael Kpoghomou
raphaelkpogomou@gmail.com

 

References

Ferrari, B. S., Manica, M., Giro, R., Laino, T., & Steiner, M. B. "Predicting Polymerization Reactions via Transfer Learning Using Chemical Language Models." ArXiv [Submitted on 17 Oct 2023].https://arxiv.org/abs/2310.11423

Zhang, Y., et al. Machine learning approaches for polymer property prediction. Advanced Materials, 2022.https://doi.org/10.1002/adma.202202345

Sharma, N., & Liu, Y. A. "Applications of Machine Learning to Optimizing Polyolefin Manufacturing." ArXiv, 2024. : https://arxiv.org/abs/2401.09753

Aldeghi, M., & Coley, C. W. "A Graph Representation of Molecular Ensembles for Polymer Property Prediction." ArXiv, 2022. https://arxiv.org/abs/2205.08619

Agrawal, A., & Choudhary, A. "Deep Materials Informatics: Applications of Deep Learning in Materials Science." MRS Communications, 2019. https://link.springer.com/article/10.1557/mrc.2019.73

Chen, G., Ma, Y., Wang, L., & Zhu, X. "A deep learning-based method for detecting and identifying surface defects in polyimide foam." IET Image Processing, 2023. https://ietresearch.onlinelibrary.wiley.com/doi/10.1049/ipr2.13323

Duan, Y., Hong, Y., Meeker, W. Q., Stanley, D. L., & Gu, X. "Development of an Accelerated Test Methodology to Predict Service Life of Polymeric Materials Subject to Outdoor Weathering." arXiv preprint arXiv:1705.03050, 2017. https://arxiv.org/abs/1705.03050

Oviedo, F., Lavista Ferres, J., Buonassisi, T., & Butler, K. "Interpretable and Explainable Machine Learning for Materials Science and Chemistry." arXiv preprint arXiv:2111.01037, 2021. https://arxiv.org/abs/2111.01037

Queen, O., Tabor, S., Brown, C. L., Maroulas, V., & Vogiatzis, K. D. (2023). Polymer graph neural networks for multitask property learning. npj Computational Materials, 9(1), 90. https://www.nature.com/articles/s41524-023-01034-3.pdf.

Zhou, Z., Li, X., & Zare, R. N. (2017). Optimizing Chemical Reactions with Deep Reinforcement Learning. ACS Central Science, 3(12), 1337-1344. https://pubs.acs.org/doi/10.1021/acscentsci.7b00492

Kuenneth, C., & Ramprasad, R. (2022). polyBERT: A Chemical Language Model to Enable Fully Machine-Driven Ultrafast Polymer Informatics. arXiv preprint arXiv:2209.14803.https://arxiv.org/pdf/2209.14803

Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. Advances in Neural Information Processing Systems, 28, 91-99.https://arxiv.org/pdf/1506.01497

AI Application Potential and Prospects in Materials Science: A Focus on Polymers

Published

March 24, 2025

Online ISSN

2831-350X

Print ISSN

2831-3496