Express Analysis of the Structural and Electronic Properties of Nanomaterials Using Big Data, Large Language Models and Generative Artificial Intelligence
https://doi.org/10.35596/1729-7648-2025-23-3-46-53
Abstract
The possibility of using large language models, generative machine learning and big data methods for predictive analysis of the electronic properties of nanostructures based on semiconductor materials is considered, without limiting the generality of this approach for other crystalline materials. The conceptual solution in the form of a cross-platform software application with an advanced search generation capability for applying this approach to working with scientific data arrays is described. Preliminary test results showed a positive result of using the developed solution to predict semiconductor properties (bandgap width, Fermi energy) of a reference material. Prospects for the development and implementation of big data methods, large language models, and generative artificial intelligence in the context of modern trends in materials science are discussed.
About the Authors
N. A. Shymanski
AndersenBel Ltd; Belarusian State University
Belarus
Solutions Architect
Belarus
Solutions Architect
A. V. Baglov
Belarusian State University; Belarusian State University of Informatics and Radioelectronics
Belarus
M. Sci (Eng.), Senior Researcher at the R&D Laboratory of Energy Efficient Materials and Technologies; Researcher at the Center of Nanoelectronics and Advanced Materials
Belarus
M. Sci (Eng.), Senior Researcher at the R&D Laboratory of Energy Efficient Materials and Technologies; Researcher at the Center of Nanoelectronics and Advanced Materials
Kh. B. Musaev
Institute of Basic and Applied Research at the National Research University Tashkent Institute of Engineers of Irrigation and Agricultural Mechanization
Uzbekistan
Ph. D. (Chem.), Doctoral Student, Institute of Basic and Applied Research
Uzbekistan
Ph. D. (Chem.), Doctoral Student, Institute of Basic and Applied Research
O. N. Ruzimuradov
Turin Polytechnic University in Tashkent
Uzbekistan
Dr. Sci. (Chem.), Professor at the Department of Natural-Mathematical Science
Uzbekistan
Dr. Sci. (Chem.), Professor at the Department of Natural-Mathematical Science
L. S. Khoroshko
Belarusian State University; Belarusian State University of Informatics and Radioelectronics
Belarus
Cand. Sci. (Phys. and Math.), Associate Professor, Leading Researcher at the Laboratory of Energy Efficient Materials and Technologies; Leading Researcher at the Center of Nanoelectronics and Advanced Materials
Belarus
Cand. Sci. (Phys. and Math.), Associate Professor, Leading Researcher at the Laboratory of Energy Efficient Materials and Technologies; Leading Researcher at the Center of Nanoelectronics and Advanced Materials
References
1. Niu H. N., Niu S., Oganov A. R. (2019) Simple and Accurate Model of Fracture Toughness of Solids. J. Appl. Phys. 125. https://doi.org/10.1063/1.5066311.
2. Zhu Y., Qu Z., Zhang J., Wang X., Jiang S., Xu Z., et al. (2024) Dai First-Principles Prediction of Ferroelectric Janus Si2XY (X/Y = S/Se/Te, X ≠ Y) Monolayers with Negative Poisson’s Ratios. Phys. Chem. Chem. Phys. 26, 4555–4563. https://doi.org/10.1039/D3CP05107B.
3. Ojih J., Al-Fahdi M., Yao Y., Hu J., Ming Hu (2024) Graph Theory and Graph Neural Network Assisted High-Throughput Crystal Structure Prediction and Screening for Energy Conversion and Storage. J. Mater. Chem. A. 12, 8502–8515. https://doi.org/10.1039/D3TA06190F.
4. Price S. L. (2009) Computed Crystal Energy Landscapes for Understanding and Predicting Organic Crystal Structures and Polymorphism. Acc. Chem. Res. 42 (1), 117–126. https://doi.org/10.1021/ar800147t.
5. Ozaki T. (2003) Variationally Optimized Atomic Orbitals for Large-Scale Electronic Structures. Phys. Rev. B. 67. https://doi.org/10.1103/physrevb.67.155108.
6. Ozaki T., Kino H. (2004) Numerical Atomic Basis Orbitals from H to Kr. Phys. Rev. B: Condens. Matter Mater. Phys. 69. https://doi.org/10.1103/PhysRevB.69.195113.
7. Ozaki T., Kino H. (2005) Efficient Projector Expansion for the Ab Initio LCAO Method. Phys. Rev. B. 72. https://doi.org/10.1103/PhysRevB.72.045121.
8. Shymanski N. A., Baglov A. V., Khoroshko L. S. (2023) Automation of Processing the Results of Nanomaterials Structure and Properties Studying. BIG DATA and Advanced Analytics: Proceed. of IX Int. Sci. & Pract. Conf., Minsk, May 17–18, in 2 p. P. 1. Minsk, Belarusian State University of Informatics and Radioelectronics. 296–300 (in Russian).
9. Shymanski N. A., Baglov A. V., Khoroshko L. S. (2023) Automate the Processing of the Results of Studying the Material Structure. Information Tehnologies and Systems 2023 (ITS 2023): Proceed. of Int. Sci. Conf., Minsk, Nov. 22. Minsk, Belarusian State University of Informatics and Radioelectronics. 207–208 (in Russian).
10. Shymanski N. A., Baglov A. V., Khoroshko L. S. (2024) Express Analysis of the Structural and Electronic Properties of Nanomaterials Using Big Data, Large Language Models & Generative AI. Electronic Design Automation: Proceed. of Int. Sci.&Pract. Conf., Minsk, Nov. 28. Minsk, Belarusian State University of Informatics and Radioelectronics. 100–103 (in Russian).
Review
For citations:
Shymanski N.A., Baglov A.V., Musaev Kh.B., Ruzimuradov O.N., Khoroshko L.S. Express Analysis of the Structural and Electronic Properties of Nanomaterials Using Big Data, Large Language Models and Generative Artificial Intelligence. Doklady BGUIR. 2025;23(3):46-53. (In Russ.) https://doi.org/10.35596/1729-7648-2025-23-3-46-53
Views:
24
Email this article 