The article provides a systematic review of artificial intelligence (AI) methods in geological and geophysical research. It covers fundamental AI concepts, classification by levels and domains, and core machine learning approaches: supervised, unsupervised, and reinforcement learning. Special emphasis is placed on geophysical data types (images, tabular data, time series, texts, graphs) and processing algorithms, including convolutional neural networks (CNN), LSTM, GNN, and hybrid architectures. Results from a comparative analysis of traditional rock physics methods (RPD) and AI technologies are presented: machine learning models improve prediction accuracy of rock elastic properties by 20–35 % (AAPE < 3–5 % vs. 10 % for RPD), successfully addressing lithology classification, shear wave velocity (Vs) prediction, and reservoir modeling. Software tools (TensorFlow, PyTorch, Scikit-learn) and practical use cases of AI integration in geosciences are discussed, highlighting synergy between data-driven and physics-based approaches. The material targets researchers and practitioners in geoinformatics, geology, and geophysics.

Vasiliy A. Petrushkin
Researcher
Geoinformatics Division
All-Russian Research Geological Oil Institutе
8, Varshavskoe shossee, Moscow, 117105, Russia
е-mail: pva@geosys.ru

1. Searle J.R. Minds, Brains, and Programs. Behavioral and Brain Sciences. 1980;3(3):417–457. DOI:10.1017/S0140525X00005756.
2. Mitchell T.M. Machine Learning. New York, McGraw-Hill; 1997. 432 p.
3. Samuel A.L. Some Studies in Machine Learning Using the Game of Checkers. IBM Journal of Research and Development. 1959;3(3): 210–229. DOI:10.1147/rd.33.0210.
4. Goodfellow I., Bengio Y., Courville A. Deep Learning. Cambridge, MIT Press, 2016. 800 p.
5. Hastie T., Tibshirani R., Friedman J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction (2nd ed). New York, Springer; 2009. 745p. DOI:10.1007/978-0-387-84858-7.
6. Bergen K.J., Johnson P.A., de Hoop M.V., Beroza G.C. Machine learning for data-driven discovery in solid Earth geoscience. Science. 2019; 363(6433):eaau0323. DOI:10.1126/science.aau0323.
7. Al-Anazi A., Gates I.D. Support vector regression for porosity prediction in a heterogeneous reservoir. Computers & Geosciences. 2012;(39): 222–229. DOI:10.1016/j.cageo.2011.06.011.
8. An Y., Sun D., Chen T., Wang Z., Li X., Li J., Li F., Li X. Current state and future directions for deep learning based automatic seismic fault interpretation: A systematic review. Earth-Science Reviews. 2023;(243):104509. DOI:10.1016/j.earscirev.2023.104509.
9. Dramsch J.S. 70 years of machine learning in geoscience in review. Advances in Geophysics. 2020;(61):1–55. DOI:10.1016/bs.agph.2020.08.002.
10. Suleymanov V., Bakulin A., Dmitriev M., Kazak E., Kazantsev A., Khromova I., Korolev M., Miklashevich D., Osypov K., Ovchinnikov K., Perepechkin D., Shulakova V., Tikhotskiy S., Tokarev M., Yaskevich S. Rock physics and ML comparison: elastic properties prediction and scale dependency.Frontiers in Earth Science. 2023;(11):1095252. DOI:10.3389/feart.2023.1095252.
11. Jiang L., Castagna J.P., Russell B., Guillen P. Rock physics modeling using machine learning. SEG Technical Program Expanded Abstracts 2020. 2020;2530–2534. DOI: 10.1190/segam2020-3427097.1.
12. Azadpour M., Saberi M.R., Jawherian A., Shabani M. Rock physics model-based prediction of shear wave velocity utilizing machine learning technique for a carbonate reservoir, southwest Iran. Journal of Petroleum Science and Engineering. 2020;(195):107864. DOI:10.1016/j.petrol.2020.107864.
13. Сheremisina E.N., Kirpicheva E.Y., Tokareva N.A., Milovidova A.A. Bazovy`e zadachi iskusstvennogo intellekta na primere geologorazvedki [Basic artificial Intelligence tasks in сontext of geological prospecting]. Geoinformatika. 2024;(4);83–92. DOI: 10.47148/1609-364X-2024-4-83-92. In Russ.
14. Trofimov Yu.V., Averkin A.N., Cheremisina E.N. Obzor i analiz metodov ob“yasnitel`nogo iskusstvennogo intellekta dlya resheniya zadach geoe`kologicheskogo rajonirovaniya i medicinskoj profilaktiki naseleniya [Review and Analysis of XAI Methods for Addressing Geoecological Zoning and Public Health Prevention Challenges]. Geoinformatika. 2024;(4);93–118. DOI: 10.47148/1609-364X-2024-4-93-118. In Russ.