Dynamic interwell connectivity analysis of multi-layer waterflooding reservoirs based on an improved graph neural network
), Abstract
The analysis of interwell connectivity plays an important role in the formulation of oilfield development plans and the description of residual oil distribution. In fact, sandstone reservoirs in China's onshore oilfields generally have the characteristics of thin and many layers, so multi-layer joint production is usually adopted. It remains a challenge to ensure the accuracy of splitting and dynamic connectivity in each layer of the injection-production wells with limited field data. The three-dimensional well pattern of multi-layer reservoir and the relationship between injection-production wells can be equivalent to a directional heterogeneous graph. In this paper, an improved graph neural network is proposed to construct an interacting process mimics the real interwell flow regularity. In detail, this method is used to split injection and production rates by combining permeability, porosity and effective thickness, and to invert the dynamic connectivity in each layer of the injection-production wells by attention mechanism. Based on the material balance and physical information, the overall connectivity from the injection wells, through the water injection layers to the production layers and the output of final production wells is established. Meanwhile, the change of well pattern caused by perforation, plugging and switching of wells at different times is achieved by updated graph structure in spatial and temporal ways. The effectiveness of the method is verified by a combination of reservoir numerical simulation examples and field example. The method corresponds to the actual situation of the reservoir, has wide adaptability and low cost, has good practical value, and provides a reference for adjusting the injection-production relationship of the reservoir and the development of the remaining oil.
Keywords
References
Albertoni, A., Lake, L.W., 2003. Inferring interwell connectivity only from well-rate fluctuations in waterfloods. SPE Reservoir Eval. Eng. 6 (1), 6–16. https://doi.org/10.2118/83381-PA.
Chen, C., Zhang, W., Yue, B., et al., 2022. A new method for quantitative description of dominant channels in high water-cut stage. Improved Oil and Gas Recovery 6. https://doi.org/10.14800/IOGR.1212.
Chen, J.H., Yan, Q.H., Luo, Y.T., et al., 2022. A historical production data based method for production splitting of multi-layer commingled gas wells. China Offshore Oil Gas 4 (1), 110–116 (in Chinese).
Deng, B.R., Zhang, J.Q., Chang, J.H., et al., 2019. A new production splitting method based on discrimination of injection-production relation. Proceedings of The International Field Exploration and Development Conference 2017, 303–315. https://doi.org/10.1007/978-981-10-7560-5_27.
Du, L.D., Liu, Y.T., Xue, L., et al., 2022. A deep learning framework using graph convolutional networks for adaptive correction of interwell connectivity and gated recurrent unit for performance Prediction. SPE Reservoir Eval. Eng. 25 (4), 815–831. https://doi.org/10.2118/210575-PA.
Du, Q.J., Pan, G.M., Hou, J., et al., 2019. Study of the mechanisms of streamline-adjustment-assisted heterogeneous combination flooding for enhanced oil recovery for post-polymer-flooded reservoirs. Petrol. Sci. 16 (3), 606–618. https://doi.org/10.1007/s12182-019-0311-0.
Du, S.Y., Wang, R.F., Wei, C.J., et al., 2020. The connectivity evaluation among wells in reservoir utilizing machine learning methods. IEEE Access 8, 47209–47219. https://doi.org/10.1109/ACCESS.2020.2976910.
Feng, J.W., Shang, L., Li, X.Z., et al., 2019. 3D numerical simulation of heterogeneous in situ stress field in low-permeability reservoirs. Petrol. Sci. 16, 939–955. https://doi.org/10.1007/s12182-019-00360-w.
Guo, Q., Meng, L.X., 2019. Study on evaluation and reconstruction of reservoir seepage field in high water cut stage based on analysis of seepage characteristics. J. Pet. Explor. Prod. Technol. 9 (1), 417–426. https://doi.org/10.1007/s13202-018-0476-x.
He, Z.L., Sun, J.F., Guo, P.H., et al., 2021. Construction of carbonate reservoir knowledge base and its application in fracture-cavity reservoir geological modeling. Petrol. Explor. Dev. 48 (4), 824–834. https://doi.org/10.1016/S1876-3804(21)60069-1.
Huang, H., Gong, B., Sun, W.Y., 2023. A deep-learning-based graph neural network-long-short-term memory model for reservoir simulation and optimization with varying well controls. SPE J. 1–19. https://doi.org/10.2118/215842-PA.
Kumar, A., Sharma, M.M., 2020. Diagnosing hydraulic fracture geometry, complexity, and fracture wellbore connectivity using chemical tracer flowback. Energies 13 (21). https://doi.org/10.3390/en13215644.
Liang, J.S., Zheng, W., Yuan, Z.B., 2014. Well group connectivity relations discriminate based on cart algorithm.. Applied Sciences, Materials Science and Information Technologies in Industry 513–517, 1252-1255 https://doi.org/10.4028/www.scientific.net/AMM.513-517.1252.
Liao, H.W., Wang, C., Zuo, D.R., 2002. Applying transient testing to the judgement of inter-well connectivity. Petrol. Explor. Dev. 29 (4), 87–89 (in Chinese).
Liu, C., 2022. Numerical simulation of ultra-low permeability reservoirs: progress and challenges. Front. Energy Res. 10. https://doi.org/10.https://doi.org/10.3389/fenrg.2022.895135.
Liu, H., Pei, X.H., Luo, K., et al., 2013. Current status and trend of separated layer water flooding in China. Petrol. Explor. Dev. 40 (6), 785–790. https://doi.org/10.1016/S1876-3804(13)60105-6.
Liu, W., Liu, W., Gu, J.W., et al., 2020. Research on interwell connectivity of oil reservoirs based on Kalman filter and artificial neural network. Petroleum Geology and Recovery Efficiency 27 (2), 118–124. https://doi.org/10.13673/j.cnki.cn37-1359/te.2020.02.015. (in Chinese).
Long, M., Xu, H.M., Chen, Y.K., et al., 2012. KHK production splitting method combined with relative permeability curve. J. Oil Gas Technol. (J. Jianghan Petroleum Inst.) 34 (4), 114–118 (in Chinese).
Lu, G.Q., Zeng, B.L., Dong, S.Q., et al., 2023. Lithology identification using graph neural network in continental shale oil reservoirs: a case study in Mahu Sag, Junggar Basin, Western China. Mar. Petrol. Geol. 150. https://doi.org/10.1016/j.marpetgeo.2023.106168.
Lu, X.G., Li, W., 2022. Feasibility and technologies for improving recovery at extra-high water cut development stage in waterflooding reservoirs. Petroleum Geology and Recovery Efficiency 29 (6), 130–137. https://doi.org/10.13673/j.cnki.cn37-1359/te.202201009. (in Chinese).
Ma, L.M., Yu, Z.L., Yu, C.L., et al., 2022. Analysis of dynamic inter-well connectivity in multilayer reservoirs based on node analysis splitting. Sci. Technol. Eng. 22 (11), 4335–4343 (in Chinese).
Ma, X.P., Zhang, K., Yao, C.J., et al., 2020. Multiscale-network structure inversion of fractured media based on a hierarchical-parameterization and data-driven evolutionary-optimization method. SPE J. 25 (5), 2729–2748. https://doi.org/10.2118/201237-PA.
Masihi, M., King, P.R., Nurafza, P., 2007. Fast estimation of connectivity in fractured reservoirs using percolation theory. SPE J. 12 (2), 167–178. https://doi.org/10.2118/94186-PA.
Moreno, G.A., Lake, L.W., 2014. Input signal design to estimate interwell connectivities in mature fields from the capacitance-resistance model. Petrol. Sci. 11 (4), 563–568. https://doi.org/10.1007/s12182-014-0372-z.
Moreno, G.A., Lake, L.W., 2014. On the uncertainty of interwell connectivity estimations from the capacitance-resistance model. Petrol. Sci. 11, 265–271. https://doi.org/10.1007/s12182-014-0339-0.
Naudomsup, N., Lake, L.W., 2019. Extension of capacitance/resistance model to tracer flow for determining reservoir properties. SPE Reservoir Eval. Eng. 22 (1), 266–281. https://doi.org/10.2118/187410-PA.
Pu, C.S., Jing, C., He, Y.L., et al., 2016. Multistage interwell chemical tracing for step-by-step profile control of water channeling and flooding of fractured ultra-low permeability reservoirs. Petrol. Explor. Dev. 43 (4), 679–688. https://doi.org/10.1016/S1876-3804(16)30079-9.
Sayarpour, M., Zuluaga, E., Kabir, C.S., et al., 2009. The use of capacitance-resistance models for rapid estimation of waterflood performance and optimization. J. Petrol. Sci. Eng. 69 (3–4), 227–238. https://doi.org/10.1016/j.petrol.2009.09.006.
Scarselli, F., Gori, M., Tsoi, A.C., et al., 2009. The graph neural network model. IEEE Trans. Neural Network. 20 (1), 61–80. https://doi.org/10.1109/TNN.2008.2005605.
Serres-Piole, C., Preud’homme, H., Moradi-tehrani, N., et al., 2012. Water tracers in oilfield applications: guidelines. J. Petrol. Sci. Eng. 98–99, 22–39. https://doi.org/10.1016/j.petrol.2012.08.009.
Tan, X.Q., Liu, Y.Y., Zhou, X.Z., et al., 2019. Multi-parameter quantitative assessment of 3D geological models for complex fault-block oil reservoirs. Petrol. Explor. Dev. 46 (1), 194–204. https://doi.org/10.1016/S1876-3804(19)30019-9.
Wang, H.C., Han, J.F., Zhang, K., et al., 2021. An interpretable interflow simulated graph neural network for reservoir connectivity analysis. SPE J. 26 (4), 1636–1651. https://doi.org/10.2118/205024-PA.
Yousef, A.A., Gentil, P., Jensen, J.L., et al., 2006. A capacitance model to infer interwell connectivity from production-and injection-rate fluctuations. SPE Reservoir Eval. Eng. 9 (6), 630–646. https://doi.org/10.2118/95322-PA.
Zeng, X.J., Zhang, W.S., Chen, T., et al., 2022. Evaluating interwell connectivity in waterflooding reservoirs with graph-based cooperation-mission neural networks. SPE J. 27 (4), 2443–2452. https://doi.org/10.2118/209607-PA.
Zhang, S.C., Lei, X., Zhou, Y.S., et al., 2015. Numerical simulation of hydraulic fracture propagation in tight oil reservoirs by volumetric fracturing. Petrol. Sci. 12, 674–682. https://doi.org/10.1007/s12182-015-0055-4.
Zhao, H., Xu, L.F., Guo, Z.Y., et al., 2020. Flow-path tracking strategy in a data-driven interwell numerical simulation model for waterflooding history matching and performance prediction with infill wells. SPE J. 25 (2), 1007–1025. https://doi.org/10.2118/199361-PA.
京公网安备11010802044758号