Application of machine learning technologies for the candidate-wells selection for hydraulic fracturing
https://doi.org/10.31660/04450108-2026-2-64-73
EDN: HFYDLJ
Abstract
In the face of dwindling easily hydrocarbon reserves in Russia, optimization methods of stimulation inflow, specifically hydraulic fracturing, has become critically important. Unfortunately, traditional approach of candidate-well selection features the high subjectivity of expert assessment and the inability of conventional tabular criteria to account for hidden non-linear relationships between geological and technical parameters. Therein lies the key problem with it. This article aims to develop and validate an intelligent system for predicting hydraulic fracturing efficiency based on Big Data. The study uses machine learning implemented through a hybrid neural network architecture as a leading method. The proposed model combines fully connected layers for processing static reservoir characteristics with Long Short-Term Memory (LSTM) recurrent blocks for analysis of dynamic production time series. The empirical database includes data from over 2,000 hydraulic fracturing operations. The results of this study demonstrate that proposed algorithm has an advantage over traditional methods: the accuracy of classifying successful operations increased from 56% to 70%. The model showed high robustness in ranking objects by productivity potential, even with minor discrepancies in quantitative flow rate forecasting. The practical significance of this work lies in providing an effective decision-support tool. This tool will minimize the risks of inefficient investments and automates the pre-selection process. The implementation of such systems facilitates the digital transformation of the oil and gas industry within the "Industry 4.0" framework.
About the Author
A. V. Malysheva
Almetyevsk State Technological University "Petroleum Higher School"
Russian Federation
Russian Federation
Anastasia V. Malysheva - Student, Member of the 3D Scanning Working Group of the Special Design and Technology Bureau.
Almetyevsk
References
1. Sadykov G. M., Gladkova P. O., Gaidamakin D. N. Application of hydraulic fracturing to enhance oil recovery. Innovative science. 2021;(12-2):34–36. (In Russ.).
2. Bissembayeva K. T., Dzhalalov G. I., Sabyrbayeva G. Efficiency estimation of hydraulic fracturing at oil deposit. Yessenov science journal. 2022. №2 (43). 2022;2(43):125–133. (In Russ.). https://doi.org/10.56525/CBZE7367
3. Bobkov D. O. Problems arising during hydraulic fracturing and the possibilities of their solution. Modern scientific research and innovation. 2017;(7): 41–46. (In Russ.).
4. Esipov D. V., Kuranakov D. S., Lapin V. N., Cherny S. G. Mathematical models of hydraulic fracturing. Computational technologies. 2014;19(2):33–61.
5. Ramazanov R. R., Kharlamov K. A., Letko I. I., Martsenyuk R. A. Effecienсy analysis of geological and technical measures. Oil industry. 2019;(6):62–65. (In Russ.). https://doi.org/10.24887/0028-2448-2019-6-62-65
6. Kiselev K. A. Criteria for selecting candidate wells for multistage hydraulic fracturing operations formation. Science Bulletin. 2020;2(1-22):203–206. (In Russ.).
7. Salimov O. V., Nasybullin A. V., Sakhabutdinov R. Z., Salimov V. G. The criteria for the selection of wells for hydraulic fracturing. Georesoursy. 2017;19(4):368–373. (In Russ.).
8. Farkhutdinova M. Analysis of the influence of well parameters and the hydraulic fracturing process on its efficiency. Moscow: LAP Lambert Academic Publishing; 2014. (In Russ.).
9. Stromilo D. V., Akhimbaeva B. S. Geological factors and modern approaches to hydraulic fracturing. Science Bulletin. 2024;5(12-2):418–425.
10. Popov E. A., Starikov M. A., Nevkin A. A. Implementation of machine learning algorithms in the production processes of companies in the oil and gas industry. Drilling and Oil. 2021;(4):36–40. (In Russ.).
11. Nadrshin I. R. The introduction of artificial intelligence in the process of preparation and conduct of hydraulic fracturing. Molodye neftyaniki. 2025;(IХ): 219–222. (In Russ.). https://doi.org/10.24412/cl-37425-2025-1-219-222
12. Martyushev D. A., Ponomareva I. N., Zakharov L. A., Shadrov T. A. Application of machine learning for forecasting formation pressure in oil field development. Bulletin of the Tomsk polytechnic university. Geo assets engineering. 2021;332(10):140–149. (In Russ.). https://doi.org/10.18799/24131830/2021/10/3401
13. Azbukhanov A. F., Kostrigin I. V., Bondarenko K. A., Semenova M. N., Sereda I. A., Yulmukhametov D. R. Selection of wells for hydraulic fracturing based on mathematical modeling using machine learning methods. Oil industry. 2019;(11):38–42. (In Russ.). https://doi.org/10.24887/0028-2448-2019-11-38-42
14. Kochnev A. A., Kozyrev N. D., Kochneva O. E., Galkin S. V. Development of a comprehensive methodology for the forecast of effectiveness of geological and technical measures based on machine learning algorithms. Georesursy. 2020;22(3):79–86. (In Russ.). https://doi.org/10.18599/grs.2020.3.79-86
15. Dutkin A. S., Alayeva N. N. Selection of parameters for predicting the effectiveness of hydraulic fracturing. Achievements, problems and prospects of the oil and gas industry development in 2024: proceedings of the IX International Scientific and Practical Conference. Almetyevsk: Almetyevsk State Technological University "Higher School of Petroleum"; 2024, pp. 685–689. (In Russ.).
16. Galkin V. I., Koltyrin A. N. Investigation of probabilistic models for forecasting the efficiency of proppant hydraulic fracturing technology. Journal of mining institute. 2020;(246):650–659. (In Russ.). https://doi.org/10.31897/PMI.2020.6.7
17. Mukhtarullin I. F., Yabirov R. Z., Vladimirov V. V. Prediction of oil production and workover effectiveness estimation on basis of analytical methods. Georesursy. 2010;1(33):42–43. (In Russ.).
18. Zagitova L. R., Dutkin A. S., Rasskazova A. A. Development of a method for predicting the performance of hydraulic fracturing using machine learning algorithms. Scientific and Technical Volga region Bulletin. 2024;(4):36–40. (In Russ.).
19. Kanevskaya R. D., Novikov A.V. Methods of modeling acid hydraulic fracturing. Automation, telemechanization and communication in oil industry. 2018;(3):28–34. (In Russ.). https://doi.org/10.30713/0132-2222-2018-3-28-34
20. Andronov Yu. V. Strekalov A. V. Choice of variables for neural network training for predicting the efficiency of formation hydraulic fracturing. Petroleum engineering. 2014;12(3):37–47. (In Russ.).
Review
For citations:
Malysheva A.V. Application of machine learning technologies for the candidate-wells selection for hydraulic fracturing. Oil and Gas Studies. 2026;(2):64-73. (In Russ.) https://doi.org/10.31660/04450108-2026-2-64-73. EDN: HFYDLJ
Views:
119
JATS XML
Email this article 
Post a Comment 