Development of applied solutions based on large language models (LLM) is in demand in the oil and gas industry, which utilizes significant volumes of heterogeneous unstructured data. However, in practice, the implementation of such models faces a number of organizational and technical constraints that can halt project execution. Information about successful developments in this field is fragmented and unsystematic. Therefore, there is a need to collect and analyze such data to improve the awareness of researchers and practitioners about projects implemented in Russia and abroad, their topics, as well as the methodological and technical solutions applied. This article presents an analytical review of publications dedicated to the use of large language models in the earth sciences and the oil and gas industry, published in 2023–2025 in both domestic and international journals. Promising directions for applied developments are highlighted, approaches to model specialization for geosciences and oil and gas production are considered, and implemented projects are analyzed.

Galina V. Prozorova
Candidate of Pedagogical Sciences, Associate Professor,
Associate Professor of the Department of Intelligent Systems and Technologies
Federal State Budget Educational Institution of Higher Education «Industrial University of Tyumen»
38, Volodarsky Str., Tyumen, 625003, Russia
e-mail: prozorovagv@tyuiu.ru
ORCID ID: 0000-0002-1080-8826
Scopus Author ID: 57192106444
SPIN-code: 4633-5046
AuthorID: 720104

Lyudmila B. Senkevich
Candidate of Pedagogical Sciences, Associate Professor,
Associate Professor of the Department of Cybernetic Systems
Federal State Budget Educational Institution of Higher Education «Industrial University of Tyumen»
38, Volodarsky Str., Tyumen, 625003, Russia
e-mail: senkevichlb@tyuiu.ru
SPIN-code: 9174-0318
AuthorID: 433252

1. Khandabattu H. The 2025 Hype Cycle for Artificial Intelligence Goes Beyond GenAI. 08.07.2025. Available at: https://www.gartner.com/en/articles/hype-cycle-for-artificial-intelligence (accessed 13.11.2025).
2. Arifullin A., Markin V. Prospects for the application of generative artificial intelligence in the petroleum industry. Energy Policy. 2024;(5):50–59. DOI: 10.46920/2409‑5516_2024_5196_50.
3. Vygon G. Otsutstvie universal’nykh LLM-reshenii v neftegaze vedet k dublirovaniyu usilii i lishnim raskhodam [The lack of universal LLM solutions in the oil and gas industry leads to duplication of efforts and unnecessary costs]. CNews. 14.10.2024. Available at: https://gov.cnews.ru/projects/2024/Grigorij_Vygon_VygonConsulting?erid=LjN8K1LcK (accessed 13.11.2025).
4. Iskusstvennyi intellekt v neftegazovoi otrasli: praktiki vnedreniya, vyzovy i potentsial razvitiya: doklad po itogam sessii ehkspertnogo kluba Evraziiskogo soyuza ehkspertov po nedropol’zovaniyu [Artificial intelligence in the oil and gas industry: implementation practices, challenges, and development potential. Report from the Eurasian Union of Subsoil Use experts’ club session]. July 2025. 9 p. Available at: http://eues.ru/news/iskusstvennyi-intellekt-v-neftegazovoi-otrasli-praktika-vnedrenia-vyzovy-i-potencial-razvitia (accessed 13.11.2025).
5. Dobrynin V.N., Cheremisina E.N., Kirpircheva E.Yu., Lyubimova A.V. Semantic task engineering in geosciences: towards a new paradigm of multidisciplinary research. Geoinformatika. 2025;(3):84–95. DOI: 10.47148/1609-364X-2025-3-84-95.
6. Kaluhin D.N. Automatic georeferencing of topographic maps using Python programming language. Izvestia Vuzov. Geodesy and Aerophotosurveying. 2023;67(1):57–65. DOI:10.30533/GiA-2023-004.
7. Ling C., Zhao X., Lu J., Deng C., Zheng C., Wang J., … & Zhao, L. Beyond One-Model-Fits-All: A Survey of Domain Specialization for Large Language Models. arXiv. 2023;arXiv:2305.18703v2. 42 p. Available at: https://arxiv.org/pdf/2305.18703v2 (accessed 18.11.2025).
8. Ling C., Zhao X., Lu J. et al. Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey. arXiv. 2024;arXiv:2305.18703v7. 35 p. Available at: https://arxiv.org/pdf/2305.18703 (accessed 13.11.2025). DOI: 10.48550/arXiv.2305.18703.
9. Malin C. World’s largest industrial LLM revealed! Middle East AI News. 04.03.2024. Available at: https://www.middleeastainews.com/p/aramco-launches-largest-industrial-llm (accessed 13.11.2025).
10. Lin Zh., Deng Ch., Zhou L. et al. GeoGalactica: A Scientific Large Language Model in Geoscience. arXiv. 2024;arXiv:2401.00434v2. Available at: https://arxiv.org/html/2401.00434v2 (accessed 13.11.2025).
11. Mao Y., Dong X., Xu W., Gao Y., Wei B. FIT-RAG: Black-Box RAG with Factual Information and Token Reduction. ACM Transactions on Information Systems. 2025;43(2):40. DOI: 10.1145/3676957.
12. Kolbasenkova A.E. Strukturno-semanticheskie osobennosti neftegazovykh terminov v sovremennom russkom yazyke : avtoreferat diss. kand. filol. nauk [Structural and semantic features of oil and gas terms in modern Russian: abstract of dissertation of candidate of philological sciences]. St. Petersburg, 2020. 25 p.
13. Rodrigues R.B.M., Privatto P.I.M., de Sousa G.J., Murari R.P., Afonso L.C.S., Papa J.P., Pedronette D.С.G., Guilherme I.R., Perrout S.R., Riente A.F. PetroBERT: A Domain Adaptation Language Model for Oil and Gas Applications in Portuguese. In: Computational Processing of the Portuguese Language: Proceedings of 15th International Conference PROPOR 2022 (Fortaleza, 21–23 March 2022). Pinheiro V. et al., eds. Cham: Springer; 2022P. 101–109. DOI: 10.1007/978-3-030-98305-5_10.
14. Gharieb A., Gabry M.A., Soliman M.Y. The Role of Personalized Generative AI in Advancing Petroleum Engineering and Energy Industry:
A Roadmap to Secure and Cost-Efficient Knowledge Integration: A Case Study. Paper presented at the SPE Annual Technical Conference and Exhibi-tion, New Orleans, Louisiana, USA, September 2024. 2024. Available at: https://onepetro.org/SPEATCE/proceedings-abstract/24ATCE/24ATCE/
563531 (accessed 13.11.2025). DOI: 10.2118/220716-MS.
15. Rabata R. From Reactive to Proactive: LLMs in Oil and Gas Incident Prevention. 12.06.2024. Available at: https://www.capellasolutions.com/blog/from-reactive-to-proactive-llms-in-oil-and-gas-incident-prevention (accessed 13.11.2025).
16. Rabata R. Optimizing Drilling Operations with LLM-Powered Predictive Maintenance. 18.07.2024. Available at: https://www.capellasolutions.com/blog/optimizing-drilling-operations-with-llm-powered-predictive-maintenance (accessed 13.11.2025).
17. Enterprise AI for the Oil & Gas Industry. C3 AI. Available at: https://c3.ai/industries/enterprise-ai-for-oil-and-gas/ (accessed 13.11.2025).
18. Matheus J., Tiwari S., Szemat W., Amaya D. Revolutionizing Real-Time Drilling: Leveraging Large Language Models and Retrieval-Augmented Generation for Enhanced Operational Efficiency. Paper presented at the Offshore Technology Conference, Houston, Texas, USA, May 2025. 2025. Available at: https://onepetro.org/OTCONF/proceedings-abstract/25OTC/25OTC/662535 (accessed 13.11.2025). DOI: 10.4043/35742-MS.
19. Ferrigno E., Rodriguez M., Davidsson E. Revolutionizing Drilling Operations: Next-gen Llm-AI for Real-time Support in Well Construction Control Rooms. Paper presented at the SPE Annual Technical Conference and Exhibition, New Orleans, Louisiana, USA, September 2024. 2024. Available at: https://onepetro.org/SPEATCE/proceedings-abstract/24ATCE/24ATCE/563550 (accessed 13.11.2025). DOI: 10.2118/220798-MS.
20. SIBUR vnedryaet v svoi protsessy neirosetevuyu model’ GigaChat [SIBUR is implementing the GigaChat neural network model into its processes]. 22.05.2024. Available at: https://www.sibur.ru/ru/press-center/news-and-press/cibur-vnedryaet-v-svoi-protsessy-neyrosetevuyu-model-gigachat (accessed 13.11.2025).
21. Shahini M., Wang C.Y., Roeder M.A., Pethe S., Coffman S.W., Howard P., Hu B., Wasserman H., Arnwine J. Leveraging Large Language Models for Cost Management and Supply Chain Optimization. Paper presented at the SPE Annual Technical Conference and Exhibition, New Orleans, Louisiana, USA, September 2024. 2024. Available at: https://onepetro.org/SPEATCE/proceedings-abstract/24ATCE/24ATCE/D021S012R004/563785 (accessed 13.11.2025). DOI: 10.2118/221022-MS.
22. Vetkina A.V., Piskunov S.A., Shishaev G.Yu., Rukavishnikov V.S. Avtomatizirovannyi poisk geologicheskikh analogov mestorozhdenii na osnove bol’shikh yazykovykh modelei [Automated search for geological analogues of deposits based on large language models]. In: Intellektual’nyi analiz dannykh v neftegazovoi otrasli 2025: sbornik materialov konferentsii. Moscow : Geomodel’ Razvitie; 2025. pp. 146–149.
23. “Rosneft’” vnedryaet novye tekhnologii s ispol’zovaniem iskusstvennogo intellekta [Rosneft is introducing new technologies using artificial intelligence]. 28.07.2025. Available at: https://www.rosneft.ru/press/news/item/222604 (accessed 13.11.2025).
24. Pang Z., Liu S., Lin Y., Fang X., Liu H., Peng C., Lian C. Large language model-based multi-objective modeling framework for vacuum gas oil hydrotreating. Chinese Journal of Chemical Engineering. 2025;84:133–145. DOI: 10.1016/j.cjche.2025.05.012.
25. Yarikov S.A., Kravchenko E.S. RAG-sistema v korporativnoi srede: osobennosti, vnedrenie i metriki ehffektivnosti [RAG System in a Corporate Environment: Features, Implementation, and Performance Metrics]. In: Intellektual’nyi analiz dannykh v neftegazovoi otrasli 2025: sbornik materialov konferentsii. Moscow : Geomodel’ Razvitie; 2025. pp. 150–153.
26. Leonov Ya.A. Umnye dokumenty: kak LLM transformiruet upravlenie otchetami i dokumentaciej [Smart documents: How LLM is transforming report and documentation management] In: Intellektual’nyi analiz dannykh v neftegazovoi otrasli 2025: sbornik materialov konferentsii. Moscow : Geomodel’ Razvitie; 2025. pp. 142–145.
27. Pacis F.J., Alyaev S., Pelfrene G., Wiktorski T. Enhancing Information Retrieval in the Drilling Domain: Zero-Shot Learning with Large Language Models for Question-Answering. Paper presented at the IADC/SPE International Drilling Conference and Exhibition, Galveston, Texas, USA, March 2024. 2024. Available at: https://onepetro.org/SPEDC/proceedings-abstract/24DC/1-24DC/542912 (accessed 13.11.2025). DOI: 10.2118/217671-MS.
28. “Tatneft’” i Universitet ITMO predstavili tsifrovogo ehksperta na osnove generativnogo II [Tatneft and ITMO University presented a digital expert based on generative AI]. 26.09.2023. Available at: https://www.tatneft.ru/news/5135 (accessed 13.11.2025).
29. Zhou X.G., Jing X.W., Wu W.K., Gao G.Z. Preliminary Research on Applications of Large Language Models in E&P Industry. Paper presented at the SPE Annual Technical Conference and Exhibition, New Orleans, Louisiana, USA, September 2024. 2024. Available at: https://onepetro.org/SPEATCE/proceedings/24ATCE/24ATCE/D021S012R007/563645 (accessed 13.11.2025). DOI: 10.2118/220833-MS.
30. Silva R., Lopes R., Santos P., Couto P., Silva H., Conceição T. Wiisu: an LLM Based Assistant for Structured Data Retrieval in Oil and Gas Exploration. Fifth EAGE Digitalization Conference & Exhibition. 2025;(1):1–5. DOI: 10.3997/2214-4609.202539076.
31. Shayahmetov R.A., Trofimov V.E., Kozlov A.V., Basyrov M.A., Kuleshkov I.V. Digitalization and automation of field development design processes. Petroleum Engineering. 2024;22(6)185–193. DOI: 10.17122/ ngdelo-2024-6-185-193.
32. Chen Z., Zhong R., Long W., Tang H., Wang A., Liu Z., Yang X., Ren B., Littlefield J., Koyejo S., Masnadi M.S., Brandt A.R. Advancing oil and gas emissions assessment through large language model data extraction. Energy and AI. 2025;20:100481. DOI: 10.1016/j.egyai.2025.100481.