Submit an Article
Become a reviewer
RU
Vol 275
Pages:
94-109
Download volume:
RUS ENG
Article
Geotechnical Engineering and Engineering Geology

Interpretable machine learning to detect well integrity issues

Authors:
Ildar M. Ishkulov1
Irik G. Fattakhov2
About authors
  • 1 — Engineer of the I Category Tatar Oil Research and Design Institute (TatNIPIneft) of PJSC TATNEFT ▪ Orcid ▪ Elibrary
  • 2 — Ph.D., Dr.Sci. Director for Enhanced Oil Recovery, Wave Technology and Biotechnology Tatar Oil Research and Design Institute (TatNIPIneft) of PJSC TATNEFT ▪ Orcid
Date submitted:
2025-04-08
Date accepted:
2025-09-18
Online publication date:
2025-10-17
Date published:
2025-10-31

Abstract

The problem of timely and accurate evaluation of well integrity is becoming increasingly relevant in the context of mature field development, high wellstream water cut, and a growing number of old wells. For production casing diagnostics, geophysical methods are typically used to identify damage and determine its interval. However, high workload of field personnel hinders prompt deployment of wireline crews to survey the integrity of wells. This results in lost oil production, increased water cut, environmental risks, increased non-productive injected volumes, and reduced key economic indices. To address these challenges, a novel approach to evaluation of casing string integrity based on machine learning models has been proposed. The paper presents a procedure for application of interpretable machine learning to detect production casing leakage and provides a comparison of this approach with the ROC-AUC statistical analysis method. The novel approach integrates the LightGBM machine learning algorithm and SHAP analysis to evaluate contribution of key features to well integrity prediction and determine their threshold values. The model training was based on data from 14,318 well surveys conducted between 2000 and 2022. The results indicate that the most important features are sulfate content, solution supersaturation ratio, and water cut. The study confirms the efficiency of interpretable machine learning methods for diagnosing complex technical systems. These results show the potential for application of such models in well integrity monitoring and well workover planning. This approach can also be used in other oil and gas applications, such as prediction of various problems and optimization of well operation conditions.

Область исследования:
Geotechnical Engineering and Engineering Geology
Keywords:
machine learning casing leakage data analysis interpretation surveys oil production oil field development
Go to volume 275

References

  1. Chernenko A.V., Lyshko G.N. Prevention of Formation Fluids Flows in Anullar Space Based on Mathematical Modeling of Processes in the Well. Neft. Gas. Novacii. 2018. N 3 (208), p. 30-33 (in Russian).
  2. Nabiullin A.Sh., Sinitsyna T.I., Vorontsov S.Yu. Studying the causes of casing leakages in production wells. Developing preventive methods for casing protection. Exposition Oil Gas. 2023. Iss. 8, p. 88-93 (in Russian). DOI: 10.24412/2076-6785-2023-8-88-93
  3. Anikeev D.P., Zakirov S.N., Anikeeva E.S., Lysenko A.D. Well leakage is a global problem, not a local one. Actual Problems of Oil and Gas. 2019. Iss. 4 (27), p. 14 (in Russian). DOI: 10.29222/ipng.2078-5712.2019-27.art15
  4. Trunov E.I., Ozdoeva A.Kh., Blotskaya A.I. et al. New approaches to the application of the acoustic method for continuous monitoring of well cementing integrity. Oil Industry Journal. 2024. N 2, p. 38-42 (in Russian). DOI: 10.24887/0028-2448-2024-2-38-42
  5. Sharipov A.F., Volkov A.N. System for control and appraisal of well gas-condensate tests quality. Vesti gazovoy nauki. 2016. N 4 (28), p. 173-180 (in Russian).
  6. Valiullin R.A., Sharafutdinov R.F., Fedotov V.Y. et al. The thermal convection study of behind-casing flow directed from up to down on a well model with induction heater. Bulletin of Bashkir University. 2017. Vol. 22. N 2, p. 325-329 (in Russian).
  7. Patidar A.K., Joshi D., Dristant U., Choudhury Y. et al. A review of tracer testing techniques in porous media specially attributed to the oil and gas industry. Journal of Petroleum Exploration and Production Technology. 2022. Vol. 12. Iss. 12, p. 3339-3356. DOI: 10.1007/s13202-022-01526-w
  8. Batista G. dos S., Takimi A.S., da Costa E.M. Chemical Changes in the Composition of Oil Well Cement with Core/Shell Nanoparticle Addition under CO2 Geological Storage Conditions. Energy & Fuels. 2024. Vol. 38. Iss. 23, p. 22947-22958. DOI: 10.1021/acs.energyfuels.4c03686
  9. Azamatov M.A., Shorokhov A.N. Production casing leakage determining method. Nedropolzovanie XXI vek. 2015. N 6 (56), p. 43-47 (in Russian).
  10. Shcherbakova K.O. The problem of high water cut in the products of horizontal wells. Proceedings of higher educational establishments. Geology and Exploration. 2022. Vol. 64. N 6, p. 29-38 (in Russian). DOI: 10.32454/0016-7762-2022-64-6-29-38
  11. Jabarov K.A. Mathematical modeling the processes of behind-casing fluid movement in the wells during waiting on cement. Oil Industry Journal. 2019. N 5, p. 67-71 (in Russian). DOI: 10.24887/0028-2448-2019-5-67-71
  12. Burkova A.A. Application of a new technology for repair and insulation works. Construction of oil and gas wells on land and sea. 2022. N 8 (356), p. 39-44 (in Russian). DOI: 10.33285/0130-3872-2022-8(356)-39-44
  13. Freiman O.A., Eremin N.A. Development of a methodology for predicting reservoir properties of oil using machine learning methods. Exposition Oil Gas. 2023. Iss. 7, p. 118-120 (in Russian). DOI: 10.24412/2076-6785-2023-7-118-120
  14. Tadjer A., Hong A., Bratvold R.B. Machine learning based decline curve analysis for short-term oil production forecast. Energy Exploration & Exploitation. 2021. Vol. 39. Iss. 5, p. 1747-1769. DOI: 10.1177/01445987211011784
  15. Pashali A.A., Azbukhanov A.F., Sukharev K.V., Topolnikov A.S. The pressure levels restoration at the pump suction on oil producing wells by the use of machine learning methods. Petroleum Engineering. 2022. Vol. 20. N 6, p. 165-172 (in Russian). DOI: 10.17122/ngdelo-2022-6-165-172
  16. Liang Xue, Yuetian Liu, Yifei Xiong et al. A data-driven shale gas production forecasting method based on the multi-objective random forest regression. Journal of Petroleum Science and Engineering. 2021. Vol. 196. N 107801. DOI: 10.1016/j.petrol.2020.107801
  17. Evseenkov A.S., Guz V.S., Shpetny D.N., Yudin E.V. Short-term forecasting of well flow rate based on probabilistic approach. Oil Industry Journal. 2023. N 2, p. 78-82 (in Russian). DOI: 10.24887/0028-2448-2023-2-78-82
  18. Arief I.H., Tao Yang. A Machine-Learning Approach to Predict Gas-Oil Ratio Based on Advanced Mud Gas Data. Petrophysics. 2024. Vol. 65. Iss. 4, p. 433-454.
  19. Negash B.M., Yaw A.D. Artificial neural network based production forecasting for a hydrocarbon reservoir under water injection. Petroleum Exploration and Development. 2020. Vol. 47. Iss. 2, p. 383-392. DOI: 10.1016/S1876-3804(20)60055-6
  20. Gabitova S.I., Davletbakova L.A., Klimov V.Yu. et al. A new method of decline curve forecasting for project wells on the base of machine learning algorithms. PROneft. Professionals about Oil. 2020. N 4 (18), p. 69-74 (in Russian). DOI: 10.7868/S2587739920040102
  21. Werneck R. de O., Prates R., Moura R. et al. Data-driven deep-learning forecasting for oil production and pressure. Journal of Petroleum Science and Engineering. 2022. Vol. 210. N 109937. DOI: 10.1016/j.petrol.2021.109937
  22. Xuanyi Song, Yuetian Liu, Liang Xue et al. Time-series well performance prediction based on Long Short-Term Memory (LSTM) neural network model. Journal of Petroleum Science and Engineering. 2020. Vol. 186. N 106682. DOI: 10.1016/j.petrol.2019.106682
  23. Ahmadi M.A., Soleimani R., Lee M. et al. Determination of oil well production performance using artificial neural network (ANN) linked to the particle swarm optimization (PSO) tool. Petroleum. 2015. Vol. 1. Iss. 2, p. 118-132. DOI: 10.1016/j.petlm.2015.06.004
  24. Pechko K.A., Senkin I.S., Belonogov E.V. Well modeling using machine learning methods for integrated modeling. PROneft. Professionals about Oil. 2022. Vol. 7. N 2 (23), p. 114-120 (in Russian). DOI: 10.51890/2587-7399-2022-7-2-114-120
  25. Vikara D., Khanna V. Application of a Deep Learning Network for Joint Prediction of Associated Fluid Production in Unconventional Hydrocarbon Development. Processes. 2022. Vol 10. Iss. 4. N 740. DOI: 10.3390/pr10040740
  26. Ng C.S.W., Ghahfarokhi A.J., Amar M.N. Application of nature-inspired algorithms and artificial neural network in waterflooding well control optimization. Journal of Petroleum Exploration and Production Technology. 2021. Vol. 11. Iss. 7, p. 3103-3127. DOI: 10.1007/s13202-021-01199-x
  27. 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 Аssets Engineering. 2021. Vol. 332. N 10, p. 140-149 (in Russian). DOI: 10.18799/24131830/2021/10/3401
  28. Ponomarev R.Yu., Migmanov R.R., Ziazev R.R. Assessment of the possibilities of using hybrid modeling to optimize the production potential of an oil and gas field. Exposition Oil Gas. 2023. Iss. 5, p. 64-68 (in Russian). DOI: 10.24412/2076-6785-2023-5-64-68
  29. Mekhonoshin R.O., Vildanov T.F., Kordik K.E. et al. Prediction of incidents occurrence at injection wells using machine learning algorithms. Oilfield engineering. 2023. N 9 (657), p. 16-21 (in Russian). DOI: 10.33285/0207-2351-2023-9(657)-16-21
  30. Chernikov A.D., Eremin N.A., Stolyarov V.E. et al. Application of artificial intelligence methods for identifying and predicting complications in the construction of oil and gas wells: problems and solutions. Georesources. 2020. Vol. 22. N 3, p. 87-96. DOI: 10.18599/grs.2020.3.87-96
  31. Shibaev A.A., Shrago I.L., Vasinkin I.A., Chernyshov A.S. Application of machine learning methods in the task of analysis of anomal behavior of technological features, in the classification of technological operations, of the well construction cycle. Burenie i neft. 2023. N 7-8, p. 28-31 (in Russian).
  32. Dexin Ma, Hongbo Yang, Zhi Yang et al. An Intelligent Method for Real-Time Surface Monitoring of Rock Drillability at the Well Bottom Based on Logging and Drilling Data Fusion. Processes. 2025. Vol. 13. Iss. 3. N 668. DOI: 10.3390/pr13030668
  33. Shalyapin D.V., Bakirov D.L., Fattakhov M.M. et al. The applying of machine learning methods to improve the quality of well casing. Oil and Gas Studies. 2020. N 5 (143), p. 81-93 (in Russian). DOI: 10.31660/0445-0108-2020-5-81-93
  34. Shlykov S.V. Application of machine learning methods to automate processes in the oil and gas industry. Transport and storage of Oil Products and Hydrocarbons. 2023. N 2, p. 46-53 (in Russian). DOI: 10.24412/0131-4270-2023-2-46-53
  35. Maiorov K.N. Application of machine learning algorithms for solving problems in the oil and gas sector. Intelligent Systems in Manufacturing. 2021. Vol. 19. N 3, p. 55-64 (in Russian). DOI: 10.22213/2410-9304-2021-3-55-64
  36. Sakhnyuk V.I., Novickov E.V., Sharifullin A.M. et al. Machine learning applications for well-logging interpretation of the Vikulov Formation. Georesources. 2022. Vol. 24. N 2, p. 230-238 (in Russian). DOI: 10.18599/grs.2022.2.21
  37. Rammay M.H., Abdulraheem A. PVT correlations for Pakistani crude oils using artificial neural network. Journal of Petroleum Exploration and Production Technology. 2017. Vol. 7. Iss. 1, p. 217-233. DOI: 10.1007/s13202-016-0232-z
  38. Salem A.М., Yakoot M.S., Mahmoud O. A novel machine learning model for autonomous analysis and diagnosis of well integrity failures in artificial-lift production systems. Advances in Geo-Energy Research. 2022. Vol. 6. N 2, p. 123-142. DOI: 10.46690/ager.2022.02.05
  39. Sadiki N., Jang D.-W. Estimation of Hydraulic and Water Quality Features Using Long Short-Term Memory in Water Distribution Systems. Water. 2024. Vol. 16. Iss. 21. N 3028. DOI: 10.3390/w16213028
  40. Xiaohui Yan, Tianqi Zhang, Wenying Du et al. A Comprehensive Review of Machine Learning for Water Quality Prediction over the Past Five Years. Journal of Marine Science and Engineering. 2024. Vol. 12. Iss. 1. N 159. DOI: 10.3390/jmse12010159
  41. Ishkulov I.M., Vafin R.R., Takhauov D.D. et al. Production casing leak detection methods revisited. Oil Industry Journal. 2024. N 7, p. 56-60 (in Russian). DOI: 10.24887/0028-2448-2024-7-56-60
  42. Ishkulov I.M., Tahauov D.D., Vafin R.R. et al. Well string leak detection using machine learning models. Petroleum Engineering. 2024. Vol. 22. N 4, p. 260-267 (in Russian). DOI: 10.17122/ngdelo-2024-4-260-267
  43. Xianlin Ma, Mengyao Hou, Jie Zhan, Zhenzhi Liu. Interpretable Predictive Modeling of Tight Gas Well Productivity with SHAP and LIME Techniques. Energies. 2023. Vol. 16. Iss. 9. N 3653. DOI: 10.3390/en16093653
  44. Smiti A. A critical overview of outlier detection methods. Computer Science Review. 2020. Vol. 38. N 100306. DOI: 10.1016/j.cosrev.2020.100306
  45. Kiani R., Wei Jin, Sheng V.S. Survey on extreme learning machines for outlier detection. Machine Learning. 2024. Vol. 113. Iss. 8, p. 5495-5531. DOI: 10.1007/s10994-023-06375-0
  46. Dash C.S.K., Behera A.K., Dehuri S., Ghosh A. An outliers detection and elimination framework in classification task of data mining. Decision Analytics Journal. 2023. Vol. 6. N 100164. DOI: 10.1016/j.dajour.2023.100164
  47. Morais É.T., Barberes G.A., Souza I.V.A.F. et al. Pearson Correlation Coefficient Applied to Petroleum System Characterization: The Case Study of Potiguar and Reconcavo Basins, Brazil. Geosciences. 2023. Vol. 13. Iss. 9. N 282. DOI: 10.3390/geosciences13090282
  48. Thippa Reddy G., Swarna Priya R.M., Parimala M. et al. A deep neural networks based model for uninterrupted marine environment monitoring. Computer Communications. 2020. Vol. 157, p. 64-75. DOI: 10.1016/j.comcom.2020.04.004
  49. Ishkulov I.M., Safarov А.Kh., Fattakhov I.G., Dyakonov А.А. Application of knowledge transfer method for predicting wells integrity failure. Oilfield engineering. 2025. № 5 (677), p. 24-28 (in Russian).
  50. Chicco D., Jurman G. The Matthews correlation coefficient (MCC) should replace the ROC AUC as the standard metric for assessing binary classification. BioData Mining. 2023. Vol. 16. N 4. DOI: 10.1186/s13040-023-00322-4
  51. Starovoitov V.V., Golub Y.I. Comparative study of quality estimation of binary classification. Informatics. 2020. Vol. 17. N 1, p. 87-101 (in Russian). DOI: 10.37661/1816-0301-2020-17-1-87-101
  52. Ishkulov I., Vafin R., Takhauov D. еt al. Innovative approach to diagnostics of well integrity using machine learning. Norwegian Journal of Development of the International Science. 2024. N 144, p. 29-34. DOI: 10.5281/zenodo.14169109
  53. Guolin Ke, Qi Meng, Finley T. et al. LightGBM: A Highly Efficient Gradient Boosting Decision Tree. Advances in Neural Information Processing Systems 30: 31st Annual Conference on Neural Information Processing Systems (NIPS 2017), 4-9 December 2017, Long Beach, CA, USA. Curran Associates Inc., 2018, p. 3147-3155. DOI: 10.5555/3294996.3295074
  54. Hosmer D.W., Lemeshow S. Applied Logistic Regression. Wiley, 2000, p. 392. DOI: 10.1002/0471722146
Access statistics
Abstract Views
388
Full-Text Views
60
Cited
Scopus:
0
Crossref:
0
Article Menu

Similar articles

Identification and classification of electrical loads in mining enterprises based on signal decomposition methods
2025 Yuriy L. Zhukovskiy, Pavel K. Suslikov
Editorial: Digital transformation in process and equipment management at Fuel and Energy Complex and Mineral Resources companies
2025 Yuriy L. Zhukovskiy, Ilya I. Beloglazov, Dmitrii A. Klebanov, Igor O. Temkin
Application of digital simulation methods for predicting parameters of blasted rock muckpile
2025 Sergei V. Khokhlov
Cluster approach for industrial CO2 capture and transport: savings via shared infrastructure
2025 Pavel S. Tsvetkov
Application of machine learning to modeling Herschel – Bulkley drilling fluid parameters for optimizing wellbore cleaning
2025 Vasiliy I. Nikitin, Mikhail V. Dvoynikov, Kirill S. Kupavykh, Tatiana A. Panteleeva
Alternative frameworks for equipment positioning in mining operations
2025 Mikhail S. Nikitenko, Danila Yu. Khudonogov, Sergei A. Kizilov