Review Article: Transformative Application of AI Potential in Materials Science

Khurram  Iqbal; Syed Saad Ali; Mansoor Ebrahim; Hamid Saeed Khan; Muhammad Ayaz Shirazi; Muhammad Imran Saeed

Authors

Khurram Iqbal Department of Computing, Faculty of Engineering Sciences and Technology, Hamdard University Karachi, Sindh, Pakistan
Syed Saad Ali Department of Electrical Engineering, Nazeer Hussain University Karachi, Sindh, Pakistan
Mansoor Ebrahim Faculty of Engineering Science and Technology, Iqra University, Karachi, Sindh, Pakistan
Hamid Saeed Khan Faculty of Engineering Science and Technology, Iqra University, Karachi, Sindh, Pakistan
Muhammad Ayaz Shirazi Faculty of Engineering Science and Technology, Iqra University, Karachi, Sindh, Pakistan
Muhammad Imran Saeed Department of Computer Science, Institute of Business Management Karachi, Sindh, Pakistan

Keywords:

Artificial Intelligence, Artificial Intelligence, Machine Learning, Machine Learning, Materials, Materials, Data Analytics, Data Analytics, Materials Detection, Materials Detection, Analytical Modeling, Analytical Modeling

Abstract

The identification tools and techniques in materials engineering using AI, computer vision, and natural language processing have advanced significantly to address limitations in traditional systems. Modern and advanced studies have emerged to drive innovation in the field of materials science. This contemporary shift enhances conventional methods by integrating AI-based techniques. This study emphasizes carbon fiber reinforced polymer (CFRP) composites, which are extensively used in aerospace, automotive, and structural applications. The identification of surface cracks and internal defects, such as delamination and voids, is essential for assessing structural integrity, performance, and service life. The methodology suggested is based on image processing and machine learning algorithms using computer vision to detect defects, extract features, and classify them, and provide automated analysis of the material conditions. AI provides algorithms and statistical pattern recognition techniques used for data analytics in materials science. AI rapidly enables the detection and analysis of defects, thereby transforming the field of materials engineering. Predictions and parameter estimations are dependent on data quality and material informatics. It has been shown through experiments that AI-based methods are effective in measuring structural integrity and performance evaluation due to enhanced detection accuracy, shorter processing time, and dependable defect classification measures in comparison to traditional inspection processes. Future studies are expected to incorporate quantum computing and AI systems for faster and more precise predictions and identifications. Prospective directions include improving material property predictions and optimizing simulations for computational analyses.

References

Simone Perrotta, Ciro Giuseppe De Vita, Gennaro Mellone, Marco Edoardo Santimaria, Massimo Torquati, Javier Garcia Blas, Raffaele Montella, “Streaming I/O for scientific workflow engine acceleration,” Futur. Gener. Comput. Syst., vol. 175, p. 107978, 2026, [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0167739X25002730

Xiaopeng Bai, Xingcai Zhang, “Artificial Intelligence-Powered Materials Science,” Nano-Micro Lett., vol. 17, no. 135, 2025, doi: https://pmc.ncbi.nlm.nih.gov/articles/PMC11803041/.

L. M. Edward O. Pyzer-Knapp, Matteo Manica, Peter Staar, “Foundation models for materials discovery – current state and future directions,” npj Comput. Mater., vol. 11, no. 61, 2025, [Online]. Available: https://www.nature.com/articles/s41524-025-01538-0

Claudio Zeni, Robert Pinsler, Daniel Zügner, Andrew Fowler, Matthew Horton, “MatterGen: a generative model for inorganic materials design,” arXiv:2312.03687, 2023, [Online]. Available: https://arxiv.org/abs/2312.03687

R. R. Christopher Kuenneth, “polyBERT: a chemical language model to enable fully machine-driven ultrafast polymer informatics,” Nat. Commun., vol. 14, 2023, [Online]. Available: https://www.nature.com/articles/s41467-023-39868-6

Yue Liu, Zhengwei Yang, Zhenyao Yu, Zitu Liu, Dahui Liu, Hailong Lin, Mingqing Li, Shuchang Ma, Maxim Avdeev, “Generative artificial intelligence and its applications in materials science: Current situation and future perspectives,” J. Math., vol. 9, no. 4, pp. 798–816, 2023, doi: https://doi.org/10.1016/j.jmat.2023.05.001.

Songlin Yu, Nian Ran, Jianjun Liu, “Large-language models: The game-changers for materials science research,” Artif. Intell. Chem., vol. 2, no. 2, p. 100076, 2024, [Online]. Available: https://www.sciencedirect.com/science/article/pii/S2949747724000344

Amil Merchant, Simon Batzner, Samuel S. Schoenholz, Muratahan Aykol, Gowoon Cheon, Ekin Dogus Cubuk, “Scaling deep learning for materials discovery,” Nature, vol. 624, pp. 80–85, 2023, [Online]. Available: https://www.nature.com/articles/s41586-023-06735-9

Victor Fung, Jiaxin Zhang, Guoxiang Hu, P. Ganesh, “Inverse design of two-dimensional materials with invertible neural networks,” npj Comput. Mater., vol. 7, 2021, [Online]. Available: https://www.nature.com/articles/s41524-021-00670-x

Anubhav Jain, “Machine learning in materials research: Developments over the last decade and challenges for the future,” Curr. Opin. Solid State Mater. Sci., vol. 33, p. 101189, 2024, [Online]. Available: https://www.sciencedirect.com/science/article/pii/S135902862400055X

Jonathan Sullivan, Arman Mirhashemi, Jaeho Lee, “Deep learning based analysis of microstructured materials for thermal radiation control,” Sci. Rep., vol. 12, 2022, [Online]. Available: https://www.nature.com/articles/s41598-022-13832-8

Alkmini Michaloglou, Ioannis Papadimitriou, Ilias Gialampoukidis, Stefanos Vrochidis, “Physics-Informed Neural Networks in Materials Modeling and Design: A Review,” Arch. Comput. Methods Eng., 2025, [Online]. Available: https://link.springer.com/article/10.1007/s11831-025-10448-9

G. E. Karniadakis, I. G. Kevrekidis, L. Lu, P. Perdikaris, S. Wang, and L. Yang, “Physics-informed machine learning,” Nat. Rev. Phys. 2021 36, vol. 3, no. 6, pp. 422–440, May 2021, doi: 10.1038/s42254-021-00314-5.

K. M. Jablonka, D. Ongari, S. M. Moosavi, and B. Smit, “Using collective knowledge to assign oxidation states of metal cations in metal–organic frameworks,” Nat. Chem. 2021 138, vol. 13, no. 8, pp. 771–777, Jul. 2021, doi: 10.1038/s41557-021-00717-y.

Eric Stach, Brian DeCost, “Autonomous experimentation systems for materials development: A community perspective,” Matter, vol. 4, no. 9, 2021, [Online]. Available: https://www.researchgate.net/publication/353475009_Autonomous_experimentation_systems_for_materials_development_A_community_perspective

Sungwon Kim, Juhwan Noh, “Generative Adversarial Networks for Crystal Structure Prediction,” ACS Cent. Sci., vol. 6, no. 8, 2020, [Online]. Available: https://pubs.acs.org/doi/10.1021/acscentsci.0c00426

C. Chen, Y. Zuo, W. Ye, X. Li, Z. Deng, and S. P. Ong, “A Critical Review of Machine Learning of Energy Materials,” Adv. Energy Mater., vol. 10, no. 8, p. 1903242, Feb. 2020, doi: 10.1002/aenm.201903242.

Seyed Mohamad Moosavi, Kevin Maik Jablonka, “The Role of Machine Learning in the Understanding and Design of Materials,” J. Am. Chem. Soc., vol. 142, no. 48, 2020, [Online]. Available: https://pubs.acs.org/doi/10.1021/jacs.0c09105

Mariangeles Salas, Anand Singh, Carlos Pignataro, “AI-powered open-source infrastructure for accelerating materials discovery and advanced manufacturing,” Commun. Matrials, 2026, [Online]. Available: https://www.nature.com/articles/s43246-026-01105-0

Harshit Sharma, Gaurav Arora, Manoj Kumar Singh, Vinod Ayyappan, Papiya Bhowmik, Sanjay Mavinkere Rangappa, “Review of machine learning approaches for predicting mechanical behavior of composite materials,” Discov. Appl. Sci., vol. 7, no. 1238, 2025, [Online]. Available: https://link.springer.com/article/10.1007/s42452-025-07616-8