Application of the combinatorial generalization ability estimates in planning tracer testing studies in oil and gas fields
- Authors: Ishkina S.K.1, Vorontsov K.V.2,3,4, Davletbaev A.Y.1, Miroshnichenko V.P.5
-
Affiliations:
- RN-BashNIPIneft, LLC
- M. V. Lomonosov Moscow State University
- Federal Research Center “Computer Science and Control”
- Moscow Institute of Physics and Technology (National Research University)
- RN-Yuganskneftegaz, LLC
- Issue: No 1 (2024)
- Pages: 68-78
- Section: Intelligent Planning and Control
- URL: https://journal-vniispk.ru/2071-8594/article/view/269784
- DOI: https://doi.org/10.14357/20718594240106
- EDN: https://elibrary.ru/VAUPCE
- ID: 269784
Cite item
Full Text
Abstract
The article discusses the limitations of using interference tests to construct a tracer testing program as a list of injection-production wells pairs. The decision tree classifier proposed in earlier works is considered as more preferred method for this task. The disadvantages of the existing tree learning algorithm is that it tends to overfit, especially in conditions of small data sets. In this work, we suggest to use techniques from combinatorial theory of overfitting, namely the complete cross-validation and the expected overfitting, as splitting criteria in decision tree nodes to enhance the algorithm's generalization ability. The approach is tested on two fields in Western Siberia, resulting in a statistically significant improvement in the quality of the decision tree and reduced overfitting, leading to more accurate constructing the plan of tracer testing for assessing the presence of hydraulic connectivity between injection and production wells. The application of combinatorial theory of overfitting to decision tree classifiers offers a promising avenue for enhancing the effectiveness of tracer testing in the oil and gas industry.
Full Text

About the authors
Shaura Kh. Ishkina
RN-BashNIPIneft, LLC
Author for correspondence.
Email: shaura-ishkina@yandex.ru
Chief Specialist of the Sector for Automation and Digitalization of Business Processes for Research and Development
Russian Federation, Ufa, Republic of BashkortostanKonstantin V. Vorontsov
M. V. Lomonosov Moscow State University; Federal Research Center “Computer Science and Control”; Moscow Institute of Physics and Technology (National Research University)
Email: voron@mlsa-iai.ru
Artificial Intelligence Institute, Doctor of Physical and Mathematical Sciences, Professor of the Russian Academy of Sciences, Professor, head of the Department of Mathematical Methods of Forecasting, Head of the Laboratory "Machine Learning and Semantic Analysis", Professor, head of the Department of Machine Learning and Digital Humanities, and head of Department of Intelligent Systems, Chief Researcher
Russian Federation, Moscow; Moscow; DolgoprudnyAlfred Ya. Davletbaev
RN-BashNIPIneft, LLC
Email: DavletbaevAY@bnipi.rosneft.ru
Candidate of Physical and Mathematical Sciences. Head of the Modeling and Analysis Welltests Directorate, Associate Professor of Applied Physics Department, Ufa University of Science and Technology
Russian Federation, Ufa, Republic of BashkortostanVadim P. Miroshnichenko
RN-Yuganskneftegaz, LLC
Email: VPMiroshnichenko@ung.rosneft.ru
Head of the Oil Fields Development Directorate
Russian Federation, Nefteyugansk, Khanty-Mansi Autonomous OkrugReferences
- Sokolovsky E.V., Chizhov S.I., Trenchikov Yu.I. et al. Metodicheskoe rukovodstvo po tehnologii provedenija indikatornyh issledovanij i interpretacii ih rezul'tatov dlja regulirovanija i kontrolja processa zavodnenija neftjanyh zalezhej. [Methodological guidance on the technology of carrying out indicator studies and interpreting their results for regulating and controlling the process of flooding oil deposits.] RD 39-014-7428-235-89. Grozny: SevKavNIPIneft, 1989. 79 p.
- Michael Shook G., Shannon L., Wylie A. Tracers and tracer testing: design, implementation, tracer selection, and interpretation methods. Idaho Falls, Idaho: INL, 2004. 36 p. doi: 10.2172/910642
- Patidar A.K., Joshi D., Dristant U. et al. A review of tracer testing techniques in porous media specially attributed to the oil and gas industry // J Petrol Explor Prod Technol. 2022. V. 12. P. 3339–3356. doi: 10.1007/s13202-022-01526-w
- Dugstad Ø., Viig S., Krognes B., Kleven R., Huseby O. Tracer monitoring of enhanced oil recovery projects // EPJ Web of Conferences. 2013. V. 50. No. 02002. doi: 10.1051/epjconf/20135002002
- åberg G. The use of natural strontium isotopes as tracers in environmental studies // Water Air Soil Pollut. 1995. V. 79. No. 1. P. 309–322. doi: 10.1007/BF01100444
- Joshi D., Patidar A.K., Mishra A., et al. Prediction of sonic log and correlation of lithology by comparing geophysical well log data using machine learning principles // GeoJournal. 2021. doi: 10.1007/S10708-021-10502-6
- Khilrani N., Prajapati P., Patidar A.K. Contrasting machine learning regression algorithms used for the estimation of permeability from well log data // Arab J Geosci. 2021. V. No. 20. P. 1–14. doi: 10.1007/S12517-021-08390-8
- Knackstedt M.A., Latham S., Madadi M., et al. Digital rock physics: 3D imaging of core material and correlations to acoustic and flow properties // The Lead Edge. 2009. V. 28. No. 1. P.28–33. doi: 10.1190/1.3064143
- Sprunger C., Muther T., Syed F.I., et al. State of the art progress in hydraulic fracture modeling using AI/ML techniques // Model Earth Syst Environ, 2022. V.8. P. 1–13. doi: 10.1007/S40808-021-01111-W
- Ishkina Sh. Kh. Kombinatornye ocenki pereobucheniya porogovyh reshayushchih pravil [Combinatorial bounds of overfitting for threshold classifiers] // Ufimskij matematicheskij zhurnal [Ufa Mathematical Journal]. 2018. V. 10. No. 1. P. 49–63. doi: 10.13108/2018-10-1-49
- Mirzayanov A.A., Asalkhuzina G.F., Pityuk Y.A., et al. Matricy primenimosti trassernyh issledovanij na primere elementa devyatitochechnoj sistemy razrabotki s treshchinami gidrorazryva [Matrixes of applicability of tracer research on the example of the element of nine-point development system with hydraulic fracturing] // Neftegazovoe delo [Petroleum engineering]. 2021. V. 19. No. 4. P. 41-49 doi: 10.17122/ngdelo-2021-4-41-49
- Trofimov A.S., Leonov V.A., Alpatov A.A. Sposob issledovanija i razrabotki mnogoplastovogo mestorozhdenija uglevodorodov [Method for research and development of a multilayer hydrocarbon field]. Patent No. 2315863 C2, Russian Federation. Published 01/27/2008.
- Ishkina Sh. Kh., Pityuk Y.A., Asalkhuzina G.F., et al. Sposob povyshenija informativnosti trassernyh issledovanij v neftegazovyh mestorozhdenijah [Method for increasing the informative value of tracer surveys in petroleum and gas deposits]. Patent No. 2776786 C1, Russian Federation. Published 07/26/2022
- Dorogush A. V., Ershov V., Gulin A. CatBoost: gradient boosting with categorical features support. Workshop on ML Systems at NIPS 2017.
- Sokolovsky E.V., Solovyyov G.B., Trenchikov Yu.I. Indicator methods of research of oil and gas layers. [Indikatornye metody izuchenija neftegazonosnyh plastov]. Moscow: Nedra, 1986. 157 p.
- Çetinkaya Z., Horasan F. Decision Trees in Large Data Sets // International Journal of Engineering Research and Development, 2021. V. 13. No. 1. P. 140-151. doi: 10.29137/umagd.763490
- Mitchell T. Machine Learning. McGraw Hill, 1997. 414 p.
- Breiman L., Friedman J.H., Olshen R.A., Stone C.J. Classification And Regression Trees (1st ed.). Routledge, 1984. doi: 10.1201/9781315139470
- Kuhn M., Johnson K. Classification Trees and Rule-Based Models. In: Applied Predictive Modeling. NY: Springer, 2013. doi: 10.1007/978-1-4614-6849-3_14
- Maimon O. and Rokach L. Data Mining and Knowledge Discovery Handbook, 2nd ed. Springer, 2010. 1285 p. doi: 10.1007/978-0-387-09823-4
- Ishkina Sh. Kh., Vorontsov K.V. Issledovanie zavyshennosti ocenok pereobucheniya porogovyh reshayushchih pravil [Sharpness estimation of combinatorial generalization ability bounds for threshold decision rules] // Avtomatika i telemekhanika [Automation and Remote Control]. 2021. V. 82. No. 5. P. 863-876. doi: 10.1134/S0005117921050106.
- Vorontsov K. V. Tochnye ocenki veroyatnosti pereobucheniya [Tight Bounds for the Probability of Overfitting] // Doklady RAN [Doklady Mathematics], 2009, Vol. 80, No. 3, pp. 793–796.
- Vorontsov K. V. Splitting and Similarity Phenomena in the Sets of Classifiers and Their Effect on the Probability of Overfitting // Pattern Recognition and Image Analysis, 2009, Vol. 19, No. 3, pp. 412–420.
- Vorontsov K. V. Exact Combinatorial Bounds on the Probability of Overfitting for Empirical Risk Minimization // Pattern Recognition and Image Analysis, 2010, Vol. 20, No. 3, pp. 269–285.
- Vorontsov K.V., Ivahnenko A.A. Tight combinatorial generalization bounds for threshold conjunction rules // 4th Int. Conf. on Pattern Recognition and Machine Intelligence, 2011. Lecture Notes in Computer Science. Springer–Verlag, 2011. P. 66–73
- GitHub Project https://github.com/shaurushka/thesholdclfs-gen-bound (accessed 01.06.2023)
- Github Project https://github.com/shaurushka/decisiontree-with-ccv-and-eof (accessed 01.06.2023)
- Bukhmastova S.V., Fakhreeva R.R., Pityuk Yu. A., et.al. Aprobaciya metodov MLR i CRMIP pri issledovanii vzaimovliyaniya skvazhin [Approbation of MLR and CRMIP methods in research of well interference] // Neftyanoe hozyajstvo [Oil industry]. 2020. No. 8. P. 58-62. doi: 10.24887/0028-2448-2020-8-58-62
- Rutherford A. Anova and ANCOVA: a GLM approach. John Wiley & Sons, 2011. 360 p.
- Lagutin M. B. Nagljadnaja matematicheskaja statistika [Visual mathematical statistics: textbook]. 2nd ed. Moscow: BINOM. Laboratoriya znanij, 2009. 472 p.
- Holm S. A simple sequentially rejective multiple test procedure // Scandinavian Journal of Statistics. 1979. V. 6. No. 2. P. 65–70.
- Fakhreeva R., Pityuk Yu., Asalkhuzina G., Davletbaev A., Miroshnichenko V., and Gusev G. Razvitie metoda mnogoparametricheskoj linejnoj regressii dlya analiza trassernyh issledovanij [Evolution of multivariate linear regression method for tracer studies analysis] // Vestnik Bashkirskogo universiteta [Bulletin of the Bashkir University]. 2021. P. 554-558. doi: 10.33184/bulletin-bsu-2021.3.2.
