ARTIFICIAL INTELLIGENCE IN MATERIALS SCIENCE: CHANGES IN MATERIALS DISCOVERY AND DEVELOPMENT
DOI:
https://doi.org/10.32782/3041-2080/2025-5-17Keywords:
artificial intelligence (AI), materials science, new concept of materials design, image processing, composition, structure, computer vision algorithmsAbstract
This review highlighted the transformative impact of artificial intelligence in various fields of materials science. It is shown that modern materials science is undergoing intense integration with artificial intelligence (AI), which fundamentally changes the paradigms of scientific research and technological development. This synergy opens up new horizons for predicting material properties, and optimizing their composition and structure. The use of machine learning (ML) methods, particularly deep learning (DL), accelerates the processes of discovering new functional materials by allowing the analysis of vast arrays of experimental data and computational modeling results, identifying hidden patterns, and establishing correlations between composition, structure, and macroscopic properties. The application of AI in materials science includes several key areas. ML algorithms are successfully used for predicting the thermodynamic stability and mechanical properties of alloys, as well as for modeling material synthesis and processing. DL models show high efficiency in recognizing microstructures from images obtained with electron microscopy, which contributes to the automation of analysis and quality control. Furthermore, AI methods are indispensable for identifying optimal crystallization conditions, ensuring the directed design of materials with desired properties. Thus, AI acts not just as a tool, but as a catalyst for progress, allowing a transition from empirical «trial and error» methods to rational, goal-oriented material design. This trend is crucial for the future development of materials science, as it significantly reduces the time and resources required for the commercialization of innovative technologies.
References
Samarasinghe S. Neural Networks for Applied Sciences and Engineering. Auerbach Publications, Taylor and Francis group, New York, 2006. P. 570. https://doi.org/10.1201/9780849333750.
Alzubaidi L., Zhang J., Humaidi A. et al. Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions, J. Big Data. 2021. 8, 53. https://doi.org/10.1186/s40537-021-00444-8
Raccuglia P., Elbert K., Adler Ph. et al. Machine-learning-assisted materials discovery using failed experiments, Nature. 2016. 533, P. 73–76. https://doi.org/10.1038/nature17439
Peivaste I., Belouettar S., Mercur Fr. et al. Artificial intelligence in materials science and engineering: Current landscape, key challenges, and future trajectories. Composite Structures. 2025. V. 372. P. 119419 https://doi.org/10.1016/j.compstruct.2025.119419
Mueller T., Gilad Kusne A., Ramprasad R. Machine learning in materials – recent progress and emerging applications. Reviews in Computational Chemistery (John Wiley & Sons, Inc, Baltimore MD. 2016. P. 291. https://doi.org/10.1002/9781119148739.ch4
Mobarak M. H., Mimona M. A., Islam M. A. et al. Scope of machine learning in materials research. A Review. Appl. Surf. Sci. Adv. 2023. 18, 100523. https://doi.org/10.1016/j.apsadv.2023.100523
LeSar R. Materials informatics: An emerging technology for materials development. Stat. Anal. Data Min.: ASA Data Sci. J. 2009. 1, 372. https://doi.org/10.1002/sam.10034
Ford E., Maneparambil K., Rajan S. et al. Machine learning-based accelerated property prediction of two- phase materials using microstructural descriptors and finite element analysis. Comput. Mater. Sci. 2021. 191, 110328 https://doi.org/10.1016/j.commatsci.2021.110328
Choudhary K., DeCost Br., Chen C. et al. Recent advances and applications of deep learning methods in materials science, Nature. 2022. 59. 8. https://doi.org/10.1038/s41524-022-00734-6
Zuccarini C., Ramachandran K., Jayaseelan D. et al. Stress distribution analysis in zirconium diboride and silica carbide (ZrB2-SiC) based TPS under hypersonic flight conditions using machine learning driven approach. Ultra-High Temperature Ceramics: Materials for Extreme Environment Applications. 2021. URL: https://crimsonpublishers.com/rdms/pdf/RDMS.000999.pdf
Tran V.Q. Using artificial intelligence approach for investigating and predicting yield stress of cemented paste backfill. Sustainability 15, 2023. 2892. https://doi.org/10.3390/su15042892
Granzner M., Strauss A., Reitererat M. et al. Data-driven condition assessment and life cycle analysis methods for dynamically and fatigue-loaded railway infrastructure components. Infrastructures. 2023. 8 (11), 162. https://doi.org/10.3390/infrastructures8110162
Toshiba розробляє перший у світі штучний інтелект, здатний виконувати 3D-вимірювання, використовуючи лише фотографії з монокулярної камери з об’єктивом-змітом. URL: https://www.global.toshiba/ww/technology/corporate/rdc/rd/topics/21/2111-02.html
Балашова Л. Метінвест запровадив ШІ для контролю якості продукції на «Запоріжсталі». Forbes Ukraine. 2024. URL: https://metinvestholding.com/ua/media/news/metnvest-zaprovadiv-sh-dlya-kontrolyu-yakost-produkc-na-zaporzhstal-forbes-ukraine
Zhao F., Zhang Z., Ye Y. et al. Machine learning guided prediction of dynamic energy release in high- entropy alloys. Mater. Des. 2024. 246. http://dx.doi.org/10.1016/j.matdes.2024.113339
Jordan M. I., Mitchell T. M. (2015). Machine learning: Trends, perspectives, and prospects. Science V. 349, Is. 6245. P. 255–260. URL: https://www.cs.cmu.edu/~tom/pubs/Science-ML-2015.pdf
Cantor B., Chang I., Knight P. et al. Microstructural Development in Equiatomic Multicomponent Alloys. Materials Science and Engineering: A, 2004. 375. P. 213–218. https://doi.org/10.1016/j.msea.2003.10.257
Yeh J.-W., Chen S.-K., Line S.-J. et al. Nanostructured high-entropy alloys with multiple principal elements: Novel alloy design concepts and outcomes. Advanced Engineering Materials. 2004. V. 6, Is. 5. P. 299–303. https://doi.org/10.1002/adem.200300567
Miracle A., Brenner D., Detor D. et al. Defining pathways for realizing the revolutionary potential of high entropy alloys. 2021. URL: https://www.tms.org/portal/portal/Publications/Studies/heaPathways/heaPathways.aspx.
Kattner U. The calphad method and its role in material and process development. Tecnol. Em Metal. Mater. E Min., 2016. V.13. N. 1. P. 3–15. http://dx.doi.org/10.4322/2176-1523.1059
Raabe D., Tasan C., Springer H. et al. From high-entropy alloys to high-entropy steels. Steel research international. 2015. V. 86, Is. 10. P. 1127–1138. https://doi.org/10.1002/srin.201500133
Wang Y., Li D., Parent L. et al. Improving the wear resistance of white cast iron using a new concept. High-entropy microstructure Wear. 2011. V. 271. Is. 9–10. P. 1623–1628. https://doi.org/10.1016/j.wear.2010.12.029
Wang Y. P., Li D. Y., Parent L., Tian H. Performances of hybrid high-entropy high-Cr cast irons during sliding wear and air-jet solid-particle erosion. Wear, 2013. V. 301. Is. 1–2. P. 390–397. https://doi.org/10.1016/j.wear.2012.12.045
Pasini W., Bellе M., Pereira L., F. R. et al. Analysis of carbides in multi-component cast iron design based on high entropy alloys concepts. Materials Research. 2021.V. 24. N. 2. http://dx.doi.org/10.1590/1980-5373-mr-2020-0398
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
