A A A Ц Ц Ц Ц

ШРИФТ:

Arial Times New Roman

ИНТЕРВАЛ:

х1 х1.5 х2

КЕРНИНГ:

Обычный Средний Большой

ИЗОБРАЖЕНИЯ:

Черно-белые Цветные
For the visually impaired Standard Version
Scientific, Technological and Production Journal
ISSN 2079–3332 (print)
ISSN 3034-6835 (online)
founded in 2001

Using AI to document geomechanical properties of exploration well core

Original articles: 2026 No 1

Using AI to document geomechanical properties of exploration well core

DOI: 10.56195/20793332-2026-26-1-4-12

Read in pdf D. V. Sidorova1, V. V. Khaustov2, V. A. Varnavsky3, S. V. Donetskiy1, A. I. Karnyushkin4
  1. Belgorod State National Research University, Belgorod, Russian Federation
  2. National Research Moscow State University of Civil Engineering, Moscow, Russian Federation
  3. Krasnoturinsk-Polimetall LLC, Krasnoturinsk, Russian Federation
  4. Moscow State Technical University named after. M. E. Bauman, Moscow, Russian Federation
p. 4-12, No.1/2026
Abstract:
This article examines the integration of artificial intelligence into documenting the geomechanical properties of exploration well core. Neural networks and the ChatGPT-4o language model were used to analyze core images. The study was conducted using over 100 core samples, with parallel comparison of artificial intelligence results and expert assessments. The artificial intelligence model demonstrates high accuracy in identifying intact core segments longer than 10 cm. Certain challenges in analyzing zones with metasomatites and intense fracturing are identified, due to the difficulty of recognizing subtle cracks and artificial damage, as well as errors in classifying rocks despite their visual similarity. The need for regular monitoring and updating of the model to prevent the degradation of its predictive capabilities is noted. The use of artificial intelligence technologies significantly reduces the labor costs and resources required to identify key geomechanical parameters of core, while emphasizing the importance of close collaboration between geomechanics and programming specialists to create standardized and relevant research methods. Integrating artificial intelligence into core analysis processes significantly improves the efficiency, accuracy, and reproducibility of geomechanical documentation.
Keywords:
artificial intelligence, geomechanical properties, core, neural networks, ChatGPT-4o, core image analysis, rock fracturing, multispectral data, image contrast enhancement
For citation:
Sidorova D.V., Khaustov V.V., Varnavsky V.A., Donetskiy S.V., Karnyushkin A.I. Using AI to document geomechan-ical properties of exploration well core. Mine Surveying and Subsurface Use. 2026;26(1):4-12. (In Russ.). https:// doi.org/10.56195/20793332-2026-26-1-4-12.
Information about the authors:
  1. Darya V. Sidorova – postgraduate student, Belgorod National Research University, Belgorod, Russian Federation; https:// orcid.org/0009-0002-7683-1508; e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
  2. Vladimir V. Khaustov – Dr. Sci. (Geol. & Mineral.), Associate Professor, National Research Moscow State University of Civil Engineering, Moscow, Russian Federation; https:// orcid.org/0000-0002-1895-7367; WoS Reseaarcher ID: C-3838-2016; Scopus Author ID: 7003912446; e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
  3. Vyacheslav V. Varnavskii – geomechanics, LLC “Krasnoturyinsk-Polymetal”, Sverdlovsk region, Krasnoturyinsk, Russian Federation; e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
  4. Sergey V. Donetskiy – Cand. Sci. (Eng.), Belgorod State National Research University, Belgorod, Russian Federation; WoS Researcher ID: PCS-4483-2025; e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
  5. Alexander I. Karnyushkin – Cand. Sci. (Eng.), Associate Professor, Moscow State Technical University named after N.E. Bauman, Moscow, Russian Federation; https:// orcid.org/0000-0001-5685-162Х; e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
References:
  1. 1. Абзалов М.З. Прикладная рудничная геология. Москва, 2016: 451. Abzalov M.Z. Applied mine geology. Moscow, 2016: 451. (In Russ.).
  2. 2. Киряева Т.А., Попов С.Е., Потапов В.П. Нейронные сети в задачах геомеханики, возможности применения, методы оценки. Вестник Научного центра ВостНИИ по промышленной и экологической безопасности. 2024; 4: 36-49. https://doi.org/10.25558/VOSTNII.2024.58.64.004. Kiryaeva T.A., Popov S.E., Potapov V.P. Neural networks in geomechanics problems, application possibilities, evaluation methods. Bulletin of the Scientific Center of the Eastern Research Institute for Industrial and Environmental Safety. 2024; 4: 36-49. (In Russ.). https://doi.org/10.25558/ VOSTNII.2024.58.64.004.
  3. 3. Хисамов Р.С., Бачков А.П., Войтович С.Е. и др. Искусственный интеллект – важный инструмент современного геолога. Геология нефтии газа. 2021; 2: 37-45. https://doi.org/10.31087/0016-7894-2021-2-37-45. Khisamov R.S., Bachkov A.P., Voitovich S.E. Artificial intelligence is an important tool of the modern geologist. Geology of oil and gas. 2021; 2:37-45. (In Russ.). https://doi.org/10.31087/0016-7894-2021-2-37-45.
  4. 4. Краснов Ф.В., Буторин А.В., Ситников А.Н. Автоматизированное обнаружение геологических объектов в изображениях сейсмического поля с применением нейронных сетей глубокого обучения. Бизнес-информатика. 2018; 2 (44): 7-15. Krasnov F.V., Butorin A.V., Sitnikov A.N. Automated detection of geological objects in seismic field images using deep learning neural networks. Business Informatics. 2018;2(44):7-15. (In Russ.).
  5. 5. Нагайцев М.В. Применение нейросетевых и прогностических моделей искусственного интеллекта при проведении геологоразведочных работ. Понизовье, 2024: 124. Nagaytsev M.V. Application of neural network and predictive artificial intelligence models in geological exploration. Ponizovye, 2024: 124. (In Russ.).
  6. 6. Патук М.И., Наумова В.В. Методы искусственного интеллекта для научных исследований в геологии. Электронные библиотеки. 2023; 26 (5): 673-696. https://doi.org/10.26907/1562-5419-2023-26-5-673-696. Patuk M.I., Naumova V.V. Artificial intelligence methods for scientific research in geology. Electronic libraries. 2023; 26 (5): 673-696. (InRuss.). https://doi.org/10.26907/1562-5419-2023-26-5-673-696.
  7. 7. Краснов Д.И. Модули внимания в сверточных нейронных сетях для распознавания малоразмерных объектов. Компьютерная оптика. 2024; 48 (6): 963-967. https://doi.org/10.18287/2412-6179-CO-1468. Krasnov D.I. Attention modules in convolutional neural networks for small-scale object recognition. Computer Optics. 2024; 48 (6): 963-967. (In Russ.). https://doi.org/10.18287/2412-6179-CO-1468.
  8. 8. Шагарова Л. В. Языковая модель ChatGPT и данные дистанционного зондирования Sentinel платформы Google Earth Engine на примере Омской области. Всероссийская конференция, посвященная Дню радио «Радиоэлектронные устройства и системы для инфокоммуникационных технологий» (РЭУС-ИТ – 2024): Доклады. Москва, 31 мая 2024 года. Москва, 2024: 83-87. Shagarova L.V. The ChatGPT language model and Sentinel remote sensing data from the Google Earth Engine platform: a case study of the Omsk region. All-Russian Conference dedicated to Radio Day «Radioelectronic Devices and Systems for In communication Technologies» (REUS-IT 2024): Reports, Moscow, May 31, 2024. Moscow: 2024; 83-87. (In Russ.).
  9. 9. Kim T., Yun T.S., Suh H.S. Can ChatGPT implement finite element models for geotechnical engineering applications? International Journal for Numerical and Analytical Methods in Geomechanics. 2025; 49 (6): 1747-1766. https://doi.org/10.48550/arXiv.2501.02199.
  10. 10. Saadati G., Javankhoshdel S., Mohebbi Najm Abad J, et al. AI-Powered Geotechnics: Enhancing Rock Mass Classification for Safer Engineering Practices. Rock Mechanics and Rock Engineering. 2024; 58 (10): 11319-11349. https://doi.org/10.1007/s00603-024-04189-7.
  11. 11. Bekele Y.W., GeoSim. AI: AI assistants for numerical simulations in geomechanics. АrXiv. 2025: 13. https://doi.org/10.48550/arXiv.2501.14186.
  12. 12. Bahrami Y., Hassani H. Optimization of machine learning algorithms for remote alteration mapping. Advancesin Space Research. 2024; 74 (4):1609-1632. https://doi.org/10.1016/j.asr.2024.05.045.
  13. 13. Гришков Г.А., Устинов С.А., Нафигин И.О. и др. Нейронные сети и возможности их применения для анализа пространственных геологических данных. XV Международная научно-практическая конференция «Развитие новых идей и тенденций в науках о Земле: инновационные технологии геологической разведки, горного и нефтегазового дела, бурение скважин, математическое моделирование и разведочная геофизика»: материалы. Москва, 2021. Москва: 2021; 33-36. Grishkov G.A., Ustinov S.A., Nafigin I.O., еt al. Neural networks and their application in spatial geological data analysis. XV International Scientific and Practical Conference “Development of New Ideas and Trends in Geosciences: Innovative Technologies in Geological Exploration, Mining, Oil and Gas, Well Drilling, Mathematical Modeling, and Exploration Geophysics”: proceedings. Moscow: S. Ordzhonikidze Russian State Geological Survey University, 2021. Moscow: 2021; 33-36. (In Russ.).
  14. 14. Caelen O., Blete M.-A. Developing Apps with GPT-4 and ChatGPT: Build Intelligent Chatbots, Content Generators, and More. O’Reilly, 2023:157.
  15. 15. Alto V. Modern Generative AI with ChatGPT and OpenAI Models: Leverage the capabilities of OpenAI’s LLM for productivity and innovation with GPT3 and GPT4. Packt Publishing. 2023: 285.

 

Управление топливными ресурсами

New materials