One of the key tasks of oil field development monitoring is the evaluation of hydrodynamic interaction between production and injection wells. In practice, this task is usually solved by conducting expensive and time-consuming tracer (indicator) analysis. It is commonly important to develop an indirect methodology that allows solving this task promptly. This article considers an approach based on comparative analysis of monthly average values of reservoir pressure in the zones of oil recovery and injection volumes. A complex carbonate Tournaisian reservoir of the Opalikhinskoye field was chosen as the object of study. Large-scale tracer studies were carried out during the period of analysis, which is the justification of the object selection. The results of tracer studies are used as actual information on the hydrodynamic connection between the oil recovery and water injection zones. In practice, formation pressure values in the withdrawal zones are obtained during well tests, while the actual frequency and regularity of measurements do not allow the implementation of the proposed approach. In this regard, to assess the hydrodynamic relationship between the withdrawal and injection zones, it is proposed to use the formation pressure values performed with a one-month time step on a specially created model which was developed using the artificial intelligence methods. All digitized historical data on actual formation pressures during the oil production wells exploitation in Perm region were used in training the model. The minimum amount of geological and field information is used as input data for the calculation (average monthly values of oil and liquid flow rates, downtime coefficients and at least one actual formation pressure measurement for the entire history of well exploitation). The occurrence of reservoir pressure values in one-month increments gives an opportunity to compare it with the injection volumes of neighboring injection wells to assess the hydrodynamic interaction between production and injection wells. The results of the proposed approach are fully confirmed by the tracer studies, which are demonstrated in this article as the example of two pairs of wells.
References
1. Katanov Yu.E., Yagafarov A.K., Aristov A.I., Digital core: Approximation models of textural features of sandstone void space (In Russ.), Vestnik Akademii nauk Respubliki Bashkortostan, 2023, V. 47, no. 2(110), pp. 33–42, DOI: https://doi.org/10.24412/1728-5283-2023-2-33-42
2. Rongbo Shao, Hua Wang, Lizhi Xiao, Reservoir evaluation using petrophysics informed machine learning: A case study, Artificial Intelligence in Geosciences, 2024, DOI: https://doi.org/10.1016/j.aiig.2024.100070.
3. Joshi A., Raman B., Mohan C.K., Cenkeramaddi L.R., A new machine learning approach for estimating shear wave velocity profile using borelog data, Soil Dynamics and Earthquake Engineering, 2024, V. 177, DOI: https://doi.org/10.1016/j.soildyn.2023.108424.
4. Xianmu Hou, Peiqing Lian, Jiuyu Zhao et al., Identification of carbonate sedimentary facies from well logs with machine learning, Petroleum Research, 2024, DOI: https://doi.org/10.1016/j.ptlrs.2024.01.007.
5. Katanov Yu.E., Neyrosetevaya model’ prognozirovaniya skorosti i rezhimov bureniya skvazhin v slozhnopostroennykh kollektorakh (In Russ.), Izvestiya vuzov. Neft’ i gaz, 2021, no. 1(145), pp. 55–76, DOI: https://doi.org/10.31660/0445-0108-2021-1-55-76
6. Kai Xu, Zouwei Liu, Qi Chen et al., Application of machine learning in wellbore stability prediction: A review, Geoenergy Science and Engineering, 2024, V. 232, Part B, DOI: https://doi.org/10.1016/j.geoen.2023.212409.
7. Iming Liu, Xiao Tan, Yi Bao, Machine learning-assisted intelligent interpretation of distributed fiber optic sensor data for automated monitoring of pipeline corrosion, Measurement, 2024, V. 226, DOI: https://doi.org/10.1016/j.measurement.2024.114190.
8. Filippov E.V., Zakharov L.A., Martyushev D.A., Ponomareva I.N., Reproduction of reservoir pressure by machine learning methods and study of its influence on the cracks formation process in hydraulic fracturing (In Russ.), Zapiski Gornogo instituta = Journal of Mining Institute, 2022, V. 258, pp. 924–932, DOI: http:// doi.org/10.31897/PMI.2022.103
9. Martyushev D.A., Ponomareva I.N., Filippov E.V., Studying the direction of hydraulic fracture in carbonate reservoirs: using machine learning to determine reservoir pressure, Petroleum Research, 2022, DOI: http://doi.org/10.1016/j.ptlrs.2022.06.003
10. Zakharov L.A., Martyushev D.A., Ponomareva I.N., Predicting dynamic formation pressure using artificial intelligence methods (In Russ.), Zapiski Gornogo instituta = Journal of Mining Institute, 2022, V. 253, pp. 23–32, DOI: http://doi.org/10.31897/PMI.2022.11
