The article focuses on the fundamental challenges of artificial intelligence (AI) encountered in multidisciplinary research and methods for addressing them using machine learning and neural networks. The authors emphasize the importance of a systematic approach, which enables accurate problem formulation, especially in poorly formalized domains such as geology and ecology. The study examines key AI tasks, including retrodiction, prediction, search, and design, while proposing solutions such as clustering and regression analysis. Special attention is given to the application of explainable artificial intelligence (XAI) methods, which enhance model interpretability and foster a deeper understanding of complex processes in interdisciplinary studies. The use of holotypic algorithms, which effectively address classification and object recognition tasks based on multidimensional data analysis, is highlighted. The paper underscores the significance of AI in automating and improving the efficiency of scientific research in interdisciplinary fields.

Eugenia N. Cheremisina
Doctor of Technical Sciences, Professor
Head of the Geoinformatics Department
All-Russian Research Geological Petroleum Institute (VNIGNI)
8, Varshavskoe shosse, 117105, Moscow, Russia
Head of the Department of Systems Analysis and Management
Dubna State University
19, Universitetskaya str., Dubna, Moscow region, 141980, Russia
e-mail: e.cheremisina@geosys.ru
ORCID: 0000-0002-6041-8359
SPIN-код: 1472-2283
AuthorID: 119359

Elena Yu. Kirpicheva
Candidate of Technical Sciences
Director of the Institute of Systems Analysis and Management
Dubna State University
19, Universitetskaya str., Dubna, Moscow region, 141980, Russia
e-mail: kirphel@mail.ru

Nadezhda A. Tokareva
PhDin Physical and Mathematical Sciences, associate professor
Head of the Department of Information Technologies
Dubna State University
19, Universitetskaya str., Dubna, Moscow region, 141980, Russia
e-mail: tokareva@uni-dubna.ru

Anna A. Milovidova
Candidate of Technical Sciences
Associate Professor of the Department of Systems Analysis and Management
Dubna State University
19, Universitetskaya str., Dubna, Moscow region, 141980, Russia
e-mail: milanna@uni-dubna.ru

1. Voronin A.Yu., Voronin Yu.A. Zadachi iskusstvennogo intellekta i upravlenie personalom geologorazvedochnykh organizatsii [Tasks of artificial intelligence and personnel management of geological exploration organizations]. Novosibirsk: IVMIMG; 2005. 259 p.
2. Poleshchuk I.A. Sistemnyi podkhod i ponyatie sistemy [Systems approach and the concept of a system]. Science, Technology and Education. 2015;(10):165–168.
3. Spivak V.A. Sistemnyi podkhod i sistemnoe myshlenie kak universal’naya kompetentsiya spetsialista i rukovoditelya [System approach and system thinking as a universal competence of a specialist and manager]. Cheboksary: Sreda; 2022. 136 p. DOI 10.31483/a-10424.
4. Dalbaeva V.Yu., Nyurenberg M.N. On interpreting the “system approach” concept. Baikal Research Journal. 2013;(5):14.
5. Yadav N. Ethics of artificial intelligence and robotics: key issues and modern ways to solve them. Journal of Digital Technologies and Law. 2023;1(4):955–972. DOI: 10.21202/jdtl.2023.41.
6. Matveev A.N., Semenov A.N. Ispol’zovanie data science i mashinnogo obucheniya v intellektual’nykh sistemakh [Using data science and machine learning in intelligent systems]. E-Scio. 2023;(6):64–70.
7. Veshneva I.V. Artificial intelligence technologies: classification, limitations, prospects and threats. Izvestiya of Saratov University. Economics. Management. Law. 2023;23(4):428–438. DOI: 10.18500/1994-2540-2023-23-4-428-438.
8. Voronin A.Yu. Raionirovanie territorii na osnove iskusstvennogo intellekta i raspoznavaniya obrazov v zadachakh prirodopol’zovaniya [Zoning of territories based on artificial intelligence and pattern recognition in environmental management tasks]: dissertation of Doctor of Technical Sciences  : 25.00.35. Moscow, 2007. 213 p.
9. Chugunov V.S. Stupeni kontrollinga i strukturnaya ustoichivost’ sistem upravleniya organizatsiei [Stages of controlling and structural stability of organization management systems]. Controlling. 2011;(39):18–22.
10. Narayanan A., Bergen K.J. Prototype-Based Methods in Explainable AI and Emerging Opportunities in the Geosciences. 2024. arXiv:2410.19856. DOI: 10.48550/arXiv.2410.19856.
11. Krell E., Kamangir H., Collins W., King S.A., Tissot P. Aggregation strategies to improve XAI for geoscience models that use correlated, high-dimensional rasters Environmental Data Science. 2023;2:e45. DOI: 10.1017/eds.2023.39.
12. Chen W., Ma X., Wang Z., Li W., Fan C., Zhang J., Que X., Li C. Exploring neuro-symbolic AI applications in geoscience: implications and future directions for mineral prediction. Earth Science Informatics. 2024;17:1819–1835. DOI: 10.1007/s12145-024-01278-7.
13. Jiang S., Sweet L.-B., Blougouras G., Brenning A., Li W., Reichstein M., Denzler J., Shangguan W., Yu G., Huang F., Zscheischler J. How interpretable machine learning can benefit process understanding in the geosciences. Earth’s Future. 2024;12(7):e2024EF004540. DOI: 10.1029/2024EF004540.
14. Cheremisina E.N., Kostyleva T.V., Kirpicheva E.Yu. Methodology for setting and solving underformalized geological problems. System analysis in science and education. 2024;(1):1–13.