Supervised deep learning-based paradigm to screen the enhanced oil recovery scenarios.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
25 Mar 2023
25 Mar 2023
Historique:
received:
12
01
2023
accepted:
23
03
2023
entrez:
25
3
2023
pubmed:
26
3
2023
medline:
26
3
2023
Statut:
epublish
Résumé
High oil prices and concern about limited oil reserves lead to increase interest in enhanced oil recovery (EOR). Selecting the most efficient development plan is of high interest to optimize economic cost. Hence, the main objective of this study is to construct a novel deep-learning classifier to select the best EOR method based on the reservoir's rock and fluid properties (depth, porosity, permeability, gravity, viscosity), and temperature. Our deep learning-based classifier consists of a one-dimensional (1D) convolutional neural network, long short-term memory (LSTM), and densely connected neural network layers. The genetic algorithm has been applied to tune the hyperparameters of this hybrid classifier. The proposed classifier is developed and tested using 735 EOR projects on sandstone, unconsolidated sandstone, carbonate, and conglomerate reservoirs in more than 17 countries. Both the numerical and graphical investigations approve that the structure-tuned deep learning classifier is a reliable tool to screen the EOR scenarios and select the best one. The designed model correctly classifies training, validation, and testing examples with an accuracy of 96.82%, 84.31%, and 82.61%, respectively. It means that only 30 out of 735 available EOR projects are incorrectly identified by the proposed deep learning classifier. The model also demonstrates a small categorical cross-entropy of 0.1548 for the classification of the involved enhanced oil recovery techniques. Such a powerful classifier is required to select the most suitable EOR candidate for a given oil reservoir with limited field information.
Identifiants
pubmed: 36966250
doi: 10.1038/s41598-023-32187-2
pii: 10.1038/s41598-023-32187-2
pmc: PMC10039950
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
4892Informations de copyright
© 2023. The Author(s).
Références
Wang, X. et al. Mechanism of enhanced oil recovery by fuzzy-ball fluid as a novel oil-displacement agent. Energy Rep. 9, 1447–1463 (2023).
doi: 10.1016/j.egyr.2022.12.072
Vo Thanh, H., Sugai, Y. & Sasaki, K. Application of artificial neural network for predicting the performance of CO2 enhanced oil recovery and storage in residual oil zones. Sci. Rep. 10, 1–16 (2020).
doi: 10.1038/s41598-020-73931-2
Cui, K. et al. Stimulation of indigenous microbes by optimizing the water cut in low permeability reservoirs for green and enhanced oil recovery. Sci. Rep. 9, 1–12 (2019).
doi: 10.1038/s41598-019-52330-2
Sun, H., Wang, H. & Lun, Z. Effect of permeability and fractures on oil mobilization of unconventional resources during CO2 EOR using nuclear magnetic resonance. Sci. Rep. 11, 1–6 (2021).
Qu, M. et al. Laboratory study and field application of amphiphilic molybdenum disulfide nanosheets for enhanced oil recovery. J. Pet. Sci. Eng. 208, 109695 (2022).
doi: 10.1016/j.petrol.2021.109695
Mahdaviara, M., Sharifi, M. & Ahmadi, M. Toward evaluation and screening of the enhanced oil recovery scenarios for low permeability reservoirs using statistical and machine learning techniques. Fuel 325, 124795 (2022).
doi: 10.1016/j.fuel.2022.124795
Shen, B., Yang, S., Chen, H., Li, S. & Gao, X. A Novel Co2-Eor potential evaluation method based on Bo-lightgbm algorithms using hybrid feature mining. Geoenergy Sci. Eng. https://doi.org/10.2139/ssrn.4170657 (2023).
doi: 10.2139/ssrn.4170657
Syed, F. I., Muther, T., Dahaghi, A. K. & Neghabhan, S. CO2 EOR performance evaluation in an unconventional reservoir through mechanistic constrained proxy modeling. Fuel 310, 122390 (2022).
doi: 10.1016/j.fuel.2021.122390
Cho, J., Min, B., Jeong, M. S., Lee, Y. W. & Lee, K. S. Modeling of CO2-LPG WAG with asphaltene deposition to predict coupled enhanced oil recovery and storage performance. Sci. Rep. 11, 1–14 (2021).
Taber, J. J., Martin, F. D. & Seright, R. S. EOR screening criteria revisited—Part 1: Introduction to screening criteria and enhanced recovery field projects. SPE Reserv. Eng. 12, 189–198 (1997).
doi: 10.2118/35385-PA
Taber, J. J., Martin, F. D. & Seright, R. S. EOR screening criteria revisited—Part 2: Applications and impact of oil prices. SPE Reserv. Eng. 12, 199–206 (1997).
doi: 10.2118/39234-PA
Al Adasani, A. & Bai, B. Analysis of EOR projects and updated screening criteria. J. Pet. Sci. Eng. 79, 10–24 (2011).
doi: 10.1016/j.petrol.2011.07.005
Mashayekhizadeh, V., Kord, S. & Dejam, M. EOR potential within Iran. Spec. Top. Rev. Porous Media 5, 325–354 (2014).
doi: 10.1615/SpecialTopicsRevPorousMedia.v5.i4.50
Zhang, N. et al. Development of a hybrid scoring system for EOR screening by combining conventional screening guidelines and random forest algorithm. Fuel 256, 115915 (2019).
doi: 10.1016/j.fuel.2019.115915
Jensen, T. B., Harpole, K. J. & Østhus, A. EOR screening for Ekofisk. In SPE European Petroleum Conference (eds Jensen, T. B. et al.) (OnePetro, 2000).
Alvarado, V. & Manrique, E. Enhanced Oil Recovery: Field Planning and Development Strategies (Gulf Professional Publishing, 2010).
doi: 10.1016/B978-1-85617-855-6.00008-5
Amini, Y., Fattahi, M., Khorasheh, F. & Sahebdelfar, S. Neural network modeling the effect of oxygenate additives on the performance of Pt–Sn/γ-Al 2 O 3 catalyst in propane dehydrogenation. Appl. Petrochem. Res. 3, 47–54 (2013).
doi: 10.1007/s13203-013-0028-8
Surguchev, L. & Li, L. IOR evaluation and applicability screening using artificial neural networks. In SPE/DOE Improved Oil Recovery Symposium (eds Surguchev, L. & Li, L.) (OnePetro, 2000).
Kamari, A., Nikookar, M., Sahranavard, L. & Mohammadi, A. H. Efficient screening of enhanced oil recovery methods and predictive economic analysis. Neural Comput. Appl. 25, 815–824 (2014).
doi: 10.1007/s00521-014-1553-9
Gharbi, R. B. C. An expert system for selecting and designing EOR processes. J. Pet. Sci. Eng. 27, 33–47 (2000).
doi: 10.1016/S0920-4105(00)00049-8
Abass, E. & Song, C. L. Artificial intelligence selection with capability of editing a new parameter for EOR screening criteria. J. Eng. Sci. Technol. 6, 628–638 (2011).
Anikin, I. Knowledge representation model and decision support system for enhanced oil recovery methods. in Proceedings of the Intl’conference on Intelligent Systems, Data Mining and Information Technology (ICIDIT ‘2014) 101–105 (2014).
Moreno, J. E., Gurpinar, O. M., Liu, Y., Al-Kinani, A. & Cakir, N. EOR advisor system: A comprehensive approach to EOR selection. In International Petroleum Technology Conference (eds Moreno, J. E. et al.) (OnePetro, 2014).
Zerafat, M. M., Ayatollahi, S., Mehranbod, N. & Barzegari, D. Bayesian network analysis as a tool for efficient EOR screening. In SPE Enhanced Oil Recovery Conference (eds Zerafat, M. M. et al.) (OnePetro, 2011).
Alvarado, V. et al. Selection of EOR/IOR opportunities based on machine learning. In European Petroleum Conference (ed. Alvarado, V.) (OnePetro, 2002).
Lee, J.-Y., Shin, H.-J. & Lim, J.-S. Selection and evaluation of enhanced oil recovery method using artificial neural network. Geosyst. Eng. 14, 157–164 (2011).
doi: 10.1080/12269328.2011.10541345
Parada, C. H. & Ertekin, T. A new screening tool for improved oil recovery methods using artificial neural networks. In SPE Western Regional Meeting (eds Parada, C. H. & Ertekin, T.) (OnePetro, 2012).
Khazali, N., Sharifi, M. & Ahmadi, M. A. Application of fuzzy decision tree in EOR screening assessment. J. Pet. Sci. Eng. 177, 167–180 (2019).
doi: 10.1016/j.petrol.2019.02.001
Khrulenko, A. A. et al. Forecasting IOR/EOR potential based on reservoir parameters. In IOR 2013–17th European Symposium on Improved Oil Recovery (ed. Khrulenko, A. A.) cp-342 (European Association of Geoscientists & Engineers, 2013).
Trujillo, M. et al. Selection methodology for screening evaluation of enhanced-oil-recovery methods. In SPE Latin American and Caribbean Petroleum Engineering Conference (ed. Trujillo, M.) (OnePetro, 2010).
Zhan, C., Dai, Z., Soltanian, M. R. & de Barros, F. P. J. Data-worth analysis for heterogeneous subsurface structure identification with a stochastic deep learning framework. Water Resour. Res. 58, e2022WR033241 (2022).
doi: 10.1029/2022WR033241
Zhao, Y., Wang, H., Xu, N., Zong, G. & Zhao, X. Reinforcement learning-based decentralized fault tolerant control for constrained interconnected nonlinear systems. Chaos, Solitons Fractals 167, 113034 (2023).
doi: 10.1016/j.chaos.2022.113034
Zhang, K. et al. Training effective deep reinforcement learning agents for real-time life-cycle production optimization. J. Pet. Sci. Eng. 208, 109766 (2022).
doi: 10.1016/j.petrol.2021.109766
Li, R., Wu, X., Tian, H., Yu, N. & Wang, C. Hybrid memetic pretrained factor analysis-based deep belief networks for transient electromagnetic inversion. IEEE Trans. Geosci. Remote Sens. 60, 1–20 (2022).
Huang, C. Q. et al. Dual-graph attention convolution network for 3-D point cloud classification. IEEE Trans. Neural Netw. Learn. Syst. https://doi.org/10.1109/TNNLS.2022.3162301 (2022).
pubmed: 36459609
doi: 10.1109/TNNLS.2022.3162301
Amini, Y., Gerdroodbary, M. B., Pishvaie, M. R., Moradi, R. & Monfared, S. M. Optimal control of batch cooling crystallizers by using genetic algorithm. Case Stud. Therm. Eng. 8, 300–310 (2016).
doi: 10.1016/j.csite.2016.09.001
Jayalakshmi, T. & Santhakumaran, A. Statistical normalization and back propagation for classification. Int. J. Comput. Theory Eng. 3, 1793–8201 (2011).
Kiranyaz, S. et al. 1D convolutional neural networks and applications: A survey. Mech. Syst. Signal Process. 151, 107398 (2021).
doi: 10.1016/j.ymssp.2020.107398
Kumar Pandey, R., Aggarwal, S., Nath, G., Kumar, A. & Vaferi, B. Metaheuristic algorithm integrated neural networks for well-test analyses of petroleum reservoirs. Sci. Rep. 12, 1–16 (2022).
doi: 10.1038/s41598-022-21075-w
Heydari, A., Alborzi, Z. S., Amini, Y. & Hassanvand, A. Configuration optimization of a renewable hybrid system including biogas generator, photovoltaic panel and wind turbine: Particle swarm optimization and genetic algorithms. Int. J. Mod. Phys. C https://doi.org/10.1142/S0129183123500699 (2022).
doi: 10.1142/S0129183123500699
Pandey, R. K., Kumar, A. & Mandal, A. A robust deep structured prediction model for petroleum reservoir characterization using pressure transient test data. Petrol. Res. 7, 204–219 (2022).
doi: 10.1016/j.ptlrs.2021.09.003
Wu, M. T. Confusion matrix and minimum cross-entropy metrics based motion recognition system in the classroom. Sci. Rep. 12, 1–10 (2022).