APPLICATION OF ARTIFICIAL INTELLIGENCE ALGORITHMS IN SOLVING PHYSICAL PROBLEMS OF MATERIALS SCIENCE
DOI:
https://doi.org/10.65164/hqjbv458Keywords:
Artificial intelligence, machine learning, materials informatics, density functional theory (dft), crystal graph convolutional neural networks (CGCNN), solid-state physics, computational material science, predictive modeling, energy materials, semiconductor physics.Abstract
The discovery of new materials with predefined properties is a cornerstone of modern technological progress. Traditional experimental and computational methods, such as Density Functional Theory (DFT), are often time-consuming and computationally expensive. This paper explores the integration of Artificial Intelligence (AI) and Machine Learning (ML) algorithms to accelerate the identification of novel materials. We demonstrate how neural networks and Gaussian process regression can predict thermodynamic stability and electronic properties of crystalline
structures. The results indicate that AI-driven models achieve high accuracy while reducing computational costs by several orders of magnitude.
References
[1]. A.V Umarov, B.A Mirsalixov, D.K Djumabayev, F.X Xusnuddinov Development and research of
layered composite materials based on Cu2ZnSnS (Se) 4 for solar cells. Volume 401, V International
Scientific Conference “Construction Mechanics, Hydraulics and Water Resources Engineering”
(CONMECHYDRO - 2023)
[2]. Zikrillaev, N. F., & Ayupov, K. S. (2022). Influence of Impurity Clusters on the Electronic Properties
of Silicon-based Materials. Technical Science and Innovation, 4(12)
[3]. Oganov, A. R., Lyakhov, A. O., & Valle, M. (2011). How Evolutionary Crystal Structure Prediction
Works—and Why. Accounts of Chemical Research.
[4]. S.V. Rogozhkin, A.A. Bogachev, A.A. Nikitin, A.L. Vasiliev, M.Yu. Presnyakov, M.Tomut,
Ch.Trautmann, TEM analysis of radiation effects in ODS steels induced by swift heavy ions. Nuclear
Instruments and Methods in Physics Research B 486 (2021)
[5]. Clifford E. Kintner, "Free-Space Measurements of Dielectrics and Three-Dimensional Periodic
Metamaterials" (2017). Theses and Dissertations. 2557.
[6]. P.K. Johnston, E. Doyle and R.A. Orzel, «Phenolics: A Literature Review of Thermal Decomposition
Products and Toxity», Journal of the American College of Toxicology Vol.7, №2.
[7]. Butler, K. T., Davies, D. W., Cartwright, H., & Walsh, A. (2018). Machine learning for molecular and
materials science. Nature, 559(7715).
[8]. Karniadakis, G. E., et al. (2021). Physics-informed machine learning. Nature Reviews Physics, 3(6),
422-440.
