Abstract
In recent years, the surrogate-assisted method, which is one of the most promising ways for reducing the computational burden of numerical simulation–based water-flooding reservoir production optimization, has been widely applied by researchers worldwide. Meanwhile, there are different fidelity models that can be applied to extract samples for establishing a surrogate model. However, most of the researches neglected the potential synergies between low-fidelity (LF) and high-fidelity (HF) samples. In this study, therefore, a rapid intelligent multi-fidelity support vector regression (SVR) model–assisted multi-objective production optimization method, namely, MFSVR-MOPO, is proposed to lessen the computational burden of the numerical simulation–based production optimization. The uniqueness of this proposed method is that the LF and HF samples are mapped to a high-dimension space by the kernel function of the SVR, and the relationships between variables and objectives are evaluated by a linear model. Moreover, the gray wolf algorithm was applied to search for the optimal hyperparameters of the SVR model so as to improve the evaluation accuracy. Two frequently used production optimization synthetic reservoirs with different scales were studied to illustrate the effectiveness and accuracy of the MFSVR-MOPO method. The results showed that the MFSVR-MOPO method performed comparably with the HF model–based method in terms of convergence and diversity, but reduced the number of simulation runs on the two reservoirs by approximately 108 times and 50 times, respectively.
Similar content being viewed by others
References
Bagherinezhad A, Boozarjomehry RB, Pishvaie MR (2017) Multi-criterion based well placement and control in the water-flooding of naturally fractured reservoir. Journal of Petroleum Science & Engineering 149:675–685
Chang C, Lin C (2011) LIBSVM: a library for support vector machines. ACM transactions on intelligent systems and technology (TIST) 2(3):1–27
Chen G, Zhang K, Zhang L et al (2020) Global and local surrogate-model-assisted differential evolution for waterflooding production optimization. SPE Journal 25(1):105–118
Deb K, Pratap A, Agarwal S, Meyarivan TAMT (2002) A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE transactions on evolutionary computation 6(2):182–197
Ding S, Lu R, Xi Y et al (2021) Optimizing vertical and deviated wells based on advanced initialization using new productivity potential map. Journal of Petroleum Science and Engineering 198:108263
Feng D, Bakhshian S, Wu K et al (2021) Wettability effects on phase behavior and interfacial tension in shale nanopores. Fuel 290:119983
Feng D, Wu K, Wang X et al (2019) Modeling the confined fluid flow in micro-nanoporous media under geological temperature and pressure. International Journal of Heat and Mass Transfer 145:118758
Feng D, Li X, Wang X et al (2018a) Capillary filling under nanoconfinement: the relationship between effective viscosity and water-wall interactions. International Journal of Heat and Mass Transfer 118:900–910
Feng D, Li X, Wang X et al (2018b) Water adsorption and its impact on the pore structure characteristics of shale clay. Applied Clay Science 155:126–138
Guo Z, Reynolds AC (2018) Robust life-cycle production optimization with a support-vector-regression proxy. Spe Journal 23(06):2409–2427
Guo Z, Reynolds AC, Zhao H (2018a) Waterflooding optimization with the INSIM-FT data-driven model. Computat. Geosci. 22(3):745–761
Guo Z, Chen C, Gao G et al (2018b) Enhancing the performance of the distributed Gauss-Newton optimization method by reducing the effect of numerical noise and truncation error with support-vector regression. SPE J. 23(6):2428–2443
Isebor OJ, Durlofsky LJ (2014). Biobjective optimization for general oil field development. J. Petrol. Sci. Eng.119,123-138
Israeli O (2007) A Shapley-based decomposition of the R-square of a linear regression. The Journal of Economic Inequality 5(2):199–212
Jansen JD, Fonseca RM, Kahrobaei S et al (2014) The egg model – a geological ensemble for reservoir simulation. Geosci Data. J1(2):192–195
Kang Q, Wu H, Zhang R et al (2021) Development of process simulation software for gathering and transportation pipeline network of intelligent oilfield. Oil & Gas Storage and Transportation 40(03):277–286
Li Z, Liang Y, Xu N et al (2021) Optimization of pipeline natural gas supply chain considering market competition. Oil & Gas Storage and Transportation 40(1):113–120
Lin R, Ren L, Zhao J et al (2017) Cluster spacing optimization of multi-stage fracturing in horizontal shale gas wells based on stimulated reservoir volume evaluation. Arabian Journal of Geosciences 10(2):38
Liu Z, Forouzanfar F, Zhao Y (2018) Comparison of SQP and AL algorithms for deterministic constrained production optimization of hydrocarbon reservoirs. J Pet Sci Eng 171:542–557
Liu F, Ma X, Chen J et al (2021) Injection production ratio optimization calculation model based on new water--drive type curve. Arabian Journal of Geosciences 14(18):1–7
Liu Y, Chen S, Guan B et al (2019a) Layout optimization of large-scale oil–gas gathering system based on combined optimization strategy. Neurocomputing 332:159–183
Liu Y, Sun W, Durlofsky LJ (2019b) A deep-learning-based geological parameterization for history matching complex models. Math. Geosci. 51:725–766
Liu Z, Reynolds A (2021) Robust multiobjective nonlinear constrained optimization with ensemble stochastic gradient sequential quadratic programming-filter algorithm. SPE Journal:1–16
Men S, Yan L, Liu J. et al. (2017) A classification method for seed viability assessment with infrared thermography. Sensors(Basel)17(4):845
Mirjalili S, Mirjalili SM, Lewis A (2014) Grey wolf optimizer. Advances in engineering software 69:46–61
Mohammadi B, Aghashariatmadari Z (2020) Estimation of solar radiation using neighboring stations through hybrid support vector regression boosted by Krill Herd algorithm. Arabian Journal of Geosciences 13:1–16
Nanda MA, Seminar KB, Nandika D et al (2018) A comparison study of kernel functions in the support vector machine and its application for termite detection. Information 9(1):5–14. https://doi.org/10.3390/info9010005
Nguyen H, Bui XN, Choi Y et al (2021) A novel combination of whale optimization algorithm and support vector machine with different kernel functions for prediction of blasting-induced fly-rock in quarry mines. Natural Resources Research:1–17
Peters L, Arts R., Brouwer G. et al.(2010) Results of the Brugge benchmark study for flooding optimisation and history matching. SPE Res Eval & Eng 13(3):391-405. SPE-119094-PA. doi: 10.2118/119094-PA.
Rajabi-Kochi M, Khamehchi E (2021) A modified optimization procedure for production and injection scheduling in an oil field using second derivative methods. Arabian Journal of Geosciences 14(16):1–10
Rao X, Zhao H, Deng Q (2020) Artificial-neural-network (ANN) based proxy model for performances forecast and inverse project design of water huff-n-puff technology. Journal of Petroleum Science and Engineering 195:107851
Rostamian A, Jamshidi S, Zirbes E (2019) The development of a novel multi-objective optimization framework for non-vertical well placement based on a modified non-dominated sorting genetic algorithm-II. Computational Geosciences 23(5):1065–1085. https://doi.org/10.1007/s10596-019-09863-2
Stein M (1987) Large sample properties of simulations using Latin hypercube sampling. Technometrics 29(2):143–151
Tolouei K, Moosavi E, Gholinejad M (2021) An effective MIP model based on grey wolf optimizer for lot-sizing LTPSOP in open-pit mines under uncertainty. Arabian Journal of Geosciences 14(17):1–17
Wang L, Yao Y, Zhang T et al (2022) A novel self-adaptive multi-fidelity surrogate-assisted multi-objective evolutionary algorithm for simulation-based production optimization. Journal of Petroleum Science and Engineering 110111
Wang L, Yao Y, Wang K, et al. 2021a. A novel surrogate-assisted multi-objective optimization method for well control parameters based on tri-training. Natural Resources Research, 2021.
Wang L, Li ZP, Adenutsi CD et al (2020) A novel multi-objective optimization method for well control parameters based on PSO-LSSVR proxy model and NSGA-II algorithm. Journal of Petroleum Science and Engineering 196:107694
Wang Y, Li X, Lu J (2021b) Experimental study and numerical modeling of boron transport in reservoir and its influence on seawater-breakthrough calculation. SPE Reservoir Evaluation & Engineering 24(02):292–309
Wu J, Azarm S (2001) Metrics for quality assessment of a multiobjective design optimization solution set. J. Mech. Des. 123(1):18–25
Yin F, Xue X, Zhang C, Zhang K, et al. 2021. Multifidelity genetic transfer: an efficient framework for production optimization. SPE J. (2021;): SPE-205013-PA. doi: 10.2118/205013-PA
Zhang L, Li ZP, Li H et al (2020) Application of polynomial chaos expansion to optimize injection-production parameters under uncertainty. Mathematical Problems in Engineering 2020
Zhang L, Li Z, Lai F et al (2019) Integrated optimization design for horizontal well placement and fracturing in tight oil reservoirs. J. Pet. Sci. Eng 178:82–96
Zhang T, Javadpour F, Yin Y, et al. 2020b Upscaling water flow in composite nanoporous shale matrix using lattice Boltzmann method. Water Resources Research, 2020, 56, e2019WR026007
Zhang T, Javadpour F, Li J et al (2021) Pore-scale perspective of gas/water two-phase flow in shale. SPE Journal 26(02):828–846
Zhao M, Zhang K, Chen G. et al. 2020a. A surrogate-assisted multi-objective evolutionary algorithm with dimension-reduction for production optimization. J Pet Sci Eng 192(September):107192. doi: 10.1016/i. petrol.2020.107192.
Zhao M, Zhang K, Chen G. et al.2020b. A classification-based surrogate-assisted multiobjective evolutionary algorithm for production optimization under geological uncertainty. SPE J.25(5):2450-2469. SPE-201229-PA. https:/doi. org/10.2118/201229-PA
Zhou YS, Ong MH, Nguyen D (2005) Lim, A study on polynomial regression and Gaussian process global surrogate model in hierarchical surrogate-assisted evolutionary algorithm, in:2005 IEEE Congress on Evolutionary Computation,3. IEEE:2832–2839
Zhu Y, Zabaras N (2018) Bayesian deep convolutional encoder-decoder networks for surrogate modeling and uncertainty quantification. J Comput Phys 366:415–447
Funding
This study was financially supported by the National Basic Research Program of China (2015CB250900).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no competing interests.
Additional information
Responsible Editor: Santanu Banerjee
Appendix. Procedure of training SVR models
Appendix. Procedure of training SVR models
The linear relationship between input (φ(x)) and output (y) in the SVR model is as follows:
where ω represents the coefficient vector and b is a constant scalar which could be easily obtained by solving the following cost function J optimization problem:
In Eq. 30 the training error is defined as the least-square error between predicted and real values. Thus, Eq. 30 is equivalent to:
Subject to
The Lagrangian function is described as follows:
By solving the solution ∇L = 0 of Eqs. 31 and 32, the following linear systems are obtained:
Simultaneously solving Eqs. 34 and 37 yields:
Combining Eqs. 36 and 38 yields:
We define \({1}_{N_S}={\left[1,1,\cdots , 1\right]}_{N_S}^T\), \(Y={\left[{y}_1,{y}_2,\cdots , {y}_{N_S}\right]}^T\), \(\alpha ={\left[{\alpha}_1,{\alpha}_2,\cdots , {\alpha}_{N_S}\right]}^T\), and ΩK, I = φ(xk)Tφ(xl).
Equation 39 thus becomes:
Combining Eqs. 35 and 40 yields:
where
Using the kernel function to replace the inner product of φ gives:
In this study, the RBF kernel was used. The following equation is thus obtained:
Multiplying Eq. 40 by \({1}_{N_S}^T{\left(\Omega +\frac{1}{\gamma }I\right)}^{-1}\) yields:
Replacing the relationship \({1}_N^T\alpha =0\), b is solved from Eq. 45 to obtain:
Considering Eq. 40, α is given as:
Combining Eqs. 29 and 34, and then applying Eq. 43, the function y(x) is obtained as:
Rights and permissions
About this article
Cite this article
Wang, L., Yao, Y., Zhang, T. et al. A rapid intelligent multi-fidelity surrogate-assisted multi-objective optimization method for water-flooding reservoir production optimization. Arab J Geosci 15, 262 (2022). https://doi.org/10.1007/s12517-022-09575-5
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12517-022-09575-5