Localization and development of residual oil reserves using geochemical studies based on neural network algorithms

At the late stage of field development, residual oil reserves undergo a significant change from mobile to sedentary and stationary. These reserves are mainly located in technogenically and production altered, watered layers and areas of deposits.
Localization and development of such sources of hydrocarbons is an effective method of increasing the final oil recovery factor in mature fields, due to the presence of a readymade developed infrastructure for production, transportation and refining, as well as the availability of highly qualified personnel.
This article considers an approach that allows, based on neural network algorithms, the estimation the volumes and localization of residual oil reserves in multi-layer deposits in combination with the analysis of geochemical studies of reservoir fluids. The use of machine learning algorithms allows a targeted approach to the development of residual reserves by automated selection of wellwork. This approach significantly reduces the manual labor of specialists for data processing and decision-making time.

1. Aanonsen, Sigurd I., Geir Nævdal, Dean S. Oliver, Albert C. Reynolds, and Brice Vallès (2009). The ensemble Kalman filter in reservoir engineering – a review. SPE J, 14(3), pp. 393–412. https://doi.org/10.2118/117274-PA

2. Al-AbdulJabbar A. et al. (2018). Predicting formation tops while drilling using artificial intelligence. SPE Kingdom of Saudi Arabia Annual Technical Symposium and Exhibition. https://doi.org/10.2118/192345-MS

3. Bagmanova S.V. et al. (2019). Geology of the Volga-Ural oil and gas province. Orenburg: OGU, 127 p. (In Russ.)

4. Barber D. (2012). Bayesian reasoning and machine learning. Cambridge University Press, p. 610. https://doi.org/10.1017/CBO9780511804779

5. Bebis G., Georgiopoulos M. (1994). Feed-forward neural networks. IEEE Potentials, 13(4), pp. 27–31. https://doi.org/10.1109/45.329294

6. Charnyi I.A. (1963). Underground hydrodynamics. Moscow: Gostoptekhizdat, 397 p. (In Russ.)

7. Cybenko, G. (1989). Approximation by superpositions of a sigmoidal function. Mathematics of control, signals and systems, 2(4), pp. 303–314. https://doi.org/10.1007/BF02551274

8. Einicke G.A. (2012). Smoothing, Filtering and Prediction: Estimating the Past, Present and Future. Rijeka, Croatia: Intech, 286 p.

9. Ermolina A.V., Solovieva A.V. (2017). Characterization of the factors influencing the oil recovery of the formation. Geologiya, geografiya i global’naya energiya = Geology, geography and global energy, 4, pp. 43–48. (In Russ.)

10. Evensen G. (1994). Sequential data assimilation with a non-linear quasigeostrophic model using Monte Carlo methods to forecast error statistics. J Geophys Res, 99(C5), pp. 10143–10162. https://doi.org/10.1029/94JC00572

11. Gladkov E.A., Gladkova E.E. (2008). Ambiguity of geological and technological information in the process of adaptation of the hydrodynamic model. Burenie i neft, 10, pp. 40–41. (In Russ.)

12. Hamam H., Ertekin T.A. (2018). Generalized varying oil compositions and relative permeability screening tool for continuous carbon dioxide injection in naturally fractured reservoirs. SPE Kingdom of Saudi Arabia Annual Technical Symposium and Exhibition. https://doi.org/10.2118/192194-MS

13. Ignatenko A.M., Makarova I.L., Kopyrin A.S. (2019). Methods for preparing data for the analysis of semi-structured time series. Programmnye sistemy i vychislitel’nye metody, 4, pp. 87–94. (In Russ.) https://doi.org/10.7256/2454-0714.2019.4.31797

14. Kaigorodov S.V. (2022). Typical mistakes when creating hydrodynamic models. Part I. Geological model upscaling. Proneft, 2, pp. 52–58. (In Russ.)

15. Kidner D.B. (2003). Higher-order interpolation of regular grid digital elevation models. International Journal of Remote Sensing, 24(14), pp. 2981–2987. https://doi.org/10.1080/0143116031000086835

16. Kostikov D.V., Petrov A.N., Lyalin V.E. (2007). Preparation of initial data for the problem of interpreting geophysical well surveys using a multilayer neural network. Proc. Int. Symp. Reliability and Quality, v. 1, pp. 123–128. (In Russ.)

17. Li S., Chen J., Xiang J. (2020). Applications of deep convolutional neural networks in prospecting prediction based on two-dimensional geological big data. Neural computing and applications, 32(7), pp. 2037–2053.https://doi.org/10.1007/s00521-019-04341-3

18. Liu B., Li,Y., Li G., & Liu A. (2019). A spectral feature based convolutional neural network for classification of sea surface oil spill. ISPRS International Journal of Geo-Information, 8(4), p. 160. https://doi.org/10.3390/ijgi8040160

19. Lydia A., Francis S. (2019). Adagrad – an optimizer for stochastic gradient descent. Int. J. Inf. Comput. Sci., 6(5), pp. 566–568.

20. Minmin Cai, Núria Jiménez, Martin Krüger, Huan Guo, Yao Jun, Nontje Straaten, Hans H. Richnow (2015). Potential for aerobic and methanogenic oil biodegradation in a water flooded oil field (Dagang oil field), Fuel, 141, pp. 143–153. https://doi.org/10.1016/j.fuel.2014.10.035

21. Muslimov R.Kh. (2012). Oil recovery: past, present, future. Kazan: Fen, 663 p. (In Russ.)

22. Novikova S., Rizvanova Z., Ziniukov R., Usmanov S. (2020). Prospects of geochemical monitoring on the basis of borehole oil samples at bypassed oil reserves localization. Int. Multidis. Sci. GeoConf. SGEM, pp. 739–744. https://doi.org/10.5593/sgem2020/1.2/s06.094

23. Nurgaliev D., Ziniukov R., Sudakov V., Fakhriev, N., Averyanov A. (2021). Evaluation of the applicability of biodegradationMarkers for identification of the bypassed oil zones. 21st Int. Multidis. Sci. GeoConf. SGEM, pp. 935–941. https://doi.org/10.5593/sgem2021/1.1/s06.113

24. Nurgaliev et al. (2006). Variation of i-butane/n-butane ratio in oils of the Romashkino oil field for the period of 1982–2000: Probable influence of the global seismicity on the fluid migration. Journal of Geochemical Exploration, 89(1–3), pp. 293–296. https://doi.org/10.1016/j.gexplo.2005.12.022

25. O’Shea K., Nash R. (2015). An introduction to convolutional neural networks. arXiv preprint arXiv:1511.08458.

26. Ribeiro M.I. (2004). Kalman and extended kalman filters: Concept, derivation and properties. Institute for Systems and Robotics, 46 p.

27. Rifai A.P., Aoyama H., Tho N.H., Dawal S.Z.M., Masruroh N.A. (2020). Evaluation of turned and milled surfaces roughness using convolutional neural network. Measurement, 161, 107860. https://doi.org/10.1016/j.measurement.2020.107860

28. Rukundo O. (2021). Evaluation of Rounding Functions in Nearest Neighbor Interpolation. International Journal of Computational Methods, 18(08), 2150024. https://doi.org/10.1142/S0219876221500249

29. Ryzhov A.E. et al. (2013). Physical and mathematical modeling of multiphase filtration in the design of the development of the oil rim of the Yen-Yakhinskoye oil and gas condensate field. Vesti gazovoi nauki, 1(12), pp. 126–137. (In Russ.)

30. Semyachkov A.I. (2009). Filtration heterogeneity of fractured rocks. Moscow: Gornaya kniga, 151 p. (In Russ.)

31. Starovoitov V.V., Golub Yu.I. (2021). Data normalization in machine learning. Informatics, 18(3), pp. 83–96. (In Russ.) https://doi.org/10.37661/1816-0301-2021-18-3-83-96

32. Stepanov S.V., Sokolov S.V., Ruchkin A.A., Stepanov A.V., Knyazev A.V., Korytov A.V. (2018). The problems of assessing the mutual influence of production and injection wells based on mathematical modeling. Vestnik Tyumenskogo gosudarstvennogo universiteta. Fiziko-matematicheskoe modelirovanie. Neft, gaz, energetika, 4(3), pp. 146-164. (In Russ.) https://doi.org/10.21684/2411-7978-2018-4-3-146-164

33. Ta, J., Li S., Chen J., Liu C., Wang Y. (2021). Mineral prospectivity prediction via convolutional neural networks based on geological big data. Journal of Earth Science, 32(2), pp. 327–347. https://doi.org/10.1007/s12583-020-1365-z

34. Tan J., NourEldeen N., Mao K., Shi J., Li Z., Xu T., Yuan Z. (2019). Deep learning convolutional neural network for the retrieval of land surface temperature from AMSR2 data in China. Sensors, 19(13), 2987. https://doi.org/10.3390/s19132987

35. Toro-Vizcarrondo C., Wallace T.D. (1968). A test of the mean square error criterion for restrictions in linear regression. Journal of the American Statistical Association, 63(322), pp. 558–572. https://doi.org/10.1080/01621459.1968.11009275

36. Wen Xian-Huan, and Wen H. Chen (2006). Real-time reservoir model updating using ensemble Kalman filter with confirming option. SPE J., 11(04), pp. 431–442. https://doi.org/10.2118/92991-PA

37. Zaikin A., Salimov R. (2019). An application of Kalman filter model to reservoir pressure maintenance. Int. Multidis. Sci. GeoConf. SGEM, (1.2), pp. 627–634. https://doi.org/10.5593/sgem2019/1.2/S06.079

38. Zaitsev M.V., Mikhailov N.N., Tumanova E.S. (2021). Non-linear filtration models and the effect of nonlinearity parameters on flow rates in low-permeability reservoirs. Georesursy = Georesources, 23(4), pp. 44–50. https://doi.org/10.18599/grs.2021.4.5

39. Zakrevskii K.E. (2009). Geological 3D modeling. Moscow: Maska, 376 p. (In Russ.)

40. Zhou, Zhuang, Shengyang Li, and Yuyang Shao (2018). Crops classification from sentinel-2A multi-spectral remote sensing images based on convolutional neural networks. IGARSS 2018-2018 IEEE Int. Geoscience and Remote Sensing Symposium. https://doi.org/10.1109/IGARSS.2018.8518860

41. Zinoviev A.M. et al. (2013). Investigation of rheological properties and filtration features of high-viscosity oils from the fields of the Samara region. Vestnik Samarskogo gosudarstvennogo tekhnicheskogo universiteta. Seriya: Tekhnicheskie nauki, 2, pp. 197–205. (In Russ.)