A hybrid particle swarm optimization and support vector regression model for modelling permeability prediction of hydrocarbon reservoir

被引:85
作者
Akande, Kabiru O. [1 ]
Owolabi, Taoreed O. [2 ,5 ]
Olatunji, Sunday O. [3 ]
AbdulRaheem, AbdulAzeez [4 ]
机构
[1] Univ Edinburgh, Sch Engn, Inst Digital Commun, Edinburgh EH8 9YL, Midlothian, Scotland
[2] King Fand Univ Petr & Minerals, Dept Phys, Dhahran, Saudi Arabia
[3] Univ Dammam, Dept Comp Sci, Dammam, Saudi Arabia
[4] King Fand Univ Petr & Minerals, Dept Petr Engn, Dhahran, Saudi Arabia
[5] Adekunle Ajasin Univ, Phys & Elect Dept, Akungba Akoko, Ondo State, Nigeria
关键词
Particle swarm optimization (PSO); Support vector regression (SVR); Hydrocarbon reservoir; Permeability prediction; Optimization techniques; SELECTION; MACHINES;
D O I
10.1016/j.petrol.2016.11.033
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
The significance of accurate permeability prediction cannot be over-emphasized in oil and gas reservoir characterization. Support vector machine regression (SVR), a computational intelligence technique, has been very successful in the estimation of permeability and has been widely deployed due to its unique features. However, careful selection of SVR hyper-parameters is highly essential to its optimum performance and this task is traditionally done using trial and error approach (TE-SVR) which takes a lot of time and do not guarantee optimal selection of the hyper-parameters. In this work, the performance of particle swarm optimization (PSO) technique, a heuristic optimization technique, is investigated for the optimal selection of SVR hyper-parameters for the first time in modelling and characterization of hydrocarbon reservoir. The technique is capable of automatic selection of the optimum combination of SVR hyper-parameters resulting in higher predictive accuracy and generalization ability of the developed model. The resulting PSO-SVR model is compared to SVR models whose parameters are obtained through random search (RAND-SVR) and trial and error approach (TE-SVR). The comparison is done using real-life industrial datasets obtained during petroleum exploration from four distinct oil wells located in a Middle Eastern oil and gas field. Simulation results indicate that the PSO-SVR model outperforms all the other models. Error reduction of 15.1%, 26.15%, 12.32% and 7.1% are recorded for PSO-SVR model compared to ordinary SVR (TE-SVR) in well-A, well-B, well-C and well-D, respectively. Also, reduction of 12.8%, 23.97%, 2.51% and 0.11 are recorded when PSO-SVR and RAND-SVR results are compared in the respective wells. Furthermore, the results show the potential of the application of heuristics algorithms, such as PSO, in the optimization of computational intelligence techniques employed in hydrocarbon reservoir characterizations. Therefore, PSO technique is proposed for the optimization of SVR hyper-parameters in permeability prediction and reservoir characterization based on its superior performance over the commonly employed optimization techniques.
引用
收藏
页码:43 / 53
页数:11
相关论文
共 34 条
[1]   Optimal power flow using particle swarm optimization [J].
Abido, MA .
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS, 2002, 24 (07) :563-571
[2]   Estimation of physical, mechanical and hydrological properties of permeable concrete using computational intelligence approach [J].
Adewumi, Adeshina A. ;
Owolabi, Taoreed O. ;
Alade, Ibrahim O. ;
Olatunji, Sunday O. .
APPLIED SOFT COMPUTING, 2016, 42 :342-350
[3]   A Novel Homogenous Hybridization Scheme for Performance Improvement of Support Vector Machines Regression in Reservoir Characterization [J].
Akande, Kabiru O. ;
Owolabi, Taoreed O. ;
Olatunji, Sunday O. ;
Abdulraheem, AbdulAzeez .
APPLIED COMPUTATIONAL INTELLIGENCE AND SOFT COMPUTING, 2016, 2016
[4]   Investigating the effect of correlation-based feature selection on the performance of support vector machines in reservoir characterization [J].
Akande, Kabiru O. ;
Owolabi, Taoreed O. ;
Olatunji, Sunday O. .
JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING, 2015, 22 :515-522
[5]  
[Anonymous], 2004, KERNEL METHODS PATTE
[6]  
[Anonymous], 2007, IEEE INT C ICML
[7]  
Bellman R.E, 1962, Adaptive Control Processes
[8]  
Bergstra J, 2012, J MACH LEARN RES, V13, P281
[9]  
Braet W., 2011, FMRI ACTIVATION RESP
[10]   Practical selection of SVM parameters and noise estimation for SVM regression [J].
Cherkassky, V ;
Ma, YQ .
NEURAL NETWORKS, 2004, 17 (01) :113-126