Russian Federation
from 01.01.2015 to 01.01.2020
Rostov-na-Donu, Rostov-on-Don, Russian Federation
Modern approaches to predicting the properties of new materials rely on machine learning methods that process large volumes of data on the chemical composition, crystal structure, and electronic characteristics of substances. Within the consideration of this issue, the capabilities of neural networks, support vector methods, and ensemble algorithms are examined for solving problems of regression analysis and classification in order to determine mechanical, optical, and thermal parameters. The integration of experimental results with data from quantum-chemical simulations ensures improved accuracy of predictions and a reduction in the need for expensive laboratory tests. Issues of model robustness to overfitting are analyzed, as well as methods to improve their generalization ability through regularization techniques, data augmentation, and multi-level validation. Examples of practical implementation demonstrate the effectiveness of the proposed models in the design of materials for high-temperature superconductors, biocompatible polymers, and efficient catalysts used in green chemistry. Significant attention is paid to the development of interpretable models that allow the identification of causal relationships between atomic structure and macroscopic properties. Generative adversarial networks open up opportunities for the generation of new material structures with predetermined characteristics, which revolutionizes traditional methods of materials science. The obtained conclusions are of great importance for accelerating innovation processes in energy, the aerospace industry, and pharmaceuticals, contributing to the transition to data-driven approaches in scientific research. Prospects for further development are associated with the creation of multidisciplinary platforms that combine artificial intelligence, theoretical modeling, and experimental verification to solve complex problems of creating next-generation materials. The analysis covers the fundamental limitations of existing algorithms when working with heterogeneous datasets, including the influence of noise and incompleteness of initial data on the quality of predictions, as well as ways to overcome these limitations through hybrid models combining physico-chemical principles with empirical observations. Such a synthesis allows not only to predict known properties but also to identify previously unknown correlations, opening new horizons for the directed synthesis of substances with unique combinations of characteristics
economic efficiency of education, labor market, human capital, educational investments, structural transformation
1. Tyupaeva A. I., Azarova L. V. Ekonomicheskaya znachimost' i ekonomicheskaya effektivnost' obrazovaniya // Vestnik Tverskogo gosudarstvennogo tehnicheskogo universiteta. 2009. № 15. S. 211–215. EDN: https://elibrary.ru/RGVSIM
2. Cherednichenko L. G. Sovershenstvovanie sistemy obrazovaniya v kontekste razrabotki i realizacii nacional'noy ekonomicheskoy strategii // Nauchnye trudy Vol'nogo ekonomicheskogo obschestva Rossii. 2011. T. 154. S. 151–158. EDN: https://elibrary.ru/OIGWXB
3. Fenin K. V., Bulusheva A. A., Ryabova V. S., Schetinina A. R. Prichiny slozhnosti ocenki ekonomicheskoy effektivnosti obrazovaniya i diskriminacii v oplate truda ego rabotnikov v noveyshey istorii Rossii // Izvestiya vysshih uchebnyh zavedeniy. Povolzhskiy region. Ekonomicheskie nauki. 2019. № 2 (10). S. 50–62. DOI: https://doi.org/10.21685/2309-2874-2019-2-6; EDN: https://elibrary.ru/PXBYHZ
4. Shabatin I. I. Aktual'nye voprosy vzaimosvyazi razvitiya nacional'nogo obrazovaniya s formoy razvitiya ekonomiki // Ekonomika obrazovaniya. 2004. № 1 (20). S. 59–62.
5. Kulikova Yu. P. Innovacionnoe razvitie nacional'nogo obrazovaniya kak prioritetnoe napravlenie ekonomiki Rossii // Vestnik gumanitarnogo nauchnogo obrazovaniya. 2012. № 4–2 (18). S. 25–26. EDN: https://elibrary.ru/PMPVGF
6. Zabaykina I. V. Modeli okupaemosti investiciy v cifrovizaciyu i avtomatizaciyu proizvodstvennyh moschnostey pri neopredelennosti sprosa cen na resursy i logisticheskih riskov // Voprosy prirodopol'zovaniya. 2025. T. 4. № 8. S. 10–18. DOI: https://doi.org/10.25726/a2210-6904-1995-e; EDN: https://elibrary.ru/AOITWR
7. Il'yasova K. H., Hadzhimuradova B. H., Usmanova Z. S. Vliyanie obrazovaniya na ekonomiku Rossii // Tendencii razvitiya nauki i obrazovaniya. 2021. № 80–1. S. 87–89. DOI: https://doi.org/10.18411/trnio-12-2021-26; EDN: https://elibrary.ru/NXQFYF
8. Salamatov A. A., Amend A. F. Prioritety rossiyskogo obrazovaniya v usloviyah innovacionnogo razvitiya ekonomiki // Vestnik Instituta razvitiya obrazovaniya i povysheniya kvalifikacii pedagogicheskih kadrov pri ChGPU. Seriya 3. 2004. № 25. S. 9–14. EDN: https://elibrary.ru/VPLNTZ
9. Kim L. G. Sistema obrazovaniya na etape perehoda k innovacionnomu tipu ekonomiki // Nauka Udmurtii. 2011. № 3. S. 105–111. EDN: https://elibrary.ru/RBDMYR
10. Semeko G. V. Rol' obrazovaniya v ekonomike: evolyuciya teoreticheskih podhodov // Ekonomika obrazovaniya. 2011. № 1 (62). S. 32–44.
11. Problemy i perspektivy rossiyskogo obrazovaniya v oblasti ekonomicheskoy teorii // Voprosy politicheskoy ekonomii. 2023. № 2. S. 23–37.
12. Carenko I. V. Osobennosti funkcionirovaniya ekonomiki obrazovaniya kak otrasli narodnogo hozyaystva v sovremennyh usloviyah // Sovremennaya ekonomika: problemy i resheniya. 2025. № 7 (187). S. 151–164. DOI: https://doi.org/10.17308/meps/2078-9017/2025/7/151-164; EDN: https://elibrary.ru/EDOYIP
13. Kuznecov N. G., Shevchenko I. V., Cherkezova I. K. Sovremennaya sistema ekonomicheskogo obrazovaniya kak sintez rossiyskogo i mirovogo opyta // Vestnik Akademii / Rostovskiy gosudarstvennyy ekonomicheskiy universitet «RINH». 1998. № 1 (7). S. 59–63. EDN: https://elibrary.ru/WKSQWI
14. Kozlova T. V. Rol' ekonomicheskogo obrazovaniya v razvitii ekonomiki Rossii // Vestnik filiala Vserossiyskogo zaochnogo finansovo-ekonomicheskogo instituta v gorode Omske. 2008. № 9. S. 367–368. EDN: https://elibrary.ru/YLWGHR
15. Lu Ch. Obrazovatel'nye traektorii i akademicheskaya mobil'nost' v ramkah kitaysko-rossiyskogo partnerstva kak drayvery transfera znaniy i transformacii yazykovyh praktik v indoevropeyskih stranah // Voprosy prirodopol'zovaniya. 2025. T. 4. № 6. S. 99–107. DOI: https://doi.org/10.25726/y6389-1535-8195-f; EDN: https://elibrary.ru/VPBKFJ
