Prediction of Permeability Using Group Method of Data Handling (GMDH) Neural Network from Well Log Data

被引:28
作者
Mathew Nkurlu, Baraka [1 ,2 ]
Shen, Chuanbo [1 ,2 ]
Asante-Okyere, Solomon [1 ,2 ]
Mulashani, Alvin K. [2 ,3 ]
Chungu, Jacqueline [2 ]
Wang, Liang [1 ,2 ]
机构
[1] China Univ Geosci, Minist Educ, Key Lab Tecton & Petr Resources, Wuhan 430074, Peoples R China
[2] China Univ Geosci, Fac Earth Resources, Dept Petr Geol, Wuhan 430074, Peoples R China
[3] Mbeya Univ Sci & Technol, Coll Engn & Technol, Dept Geosci & Min Technol, Mbeya 00225, Tanzania
关键词
permeability; group method of data handling; artificial neural network; well logs; sensitivity analysis; GENETIC ALGORITHM; RESERVOIR; POROSITY; HYBRID;
D O I
10.3390/en13030551
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
Permeability is an important petrophysical parameter that controls the fluid flow within the reservoir. Estimating permeability presents several challenges due to the conventional approach of core analysis or well testing, which are expensive and time-consuming. On the contrary, artificial intelligence has been adopted in recent years in predicting reliable permeability data. Despite its shortcomings of overfitting and low convergence speed, artificial neural network (ANN) has been the widely used artificial intelligent method. Based on this, the present study conducted permeability prediction using the group method of data handling (GMDH) neural network from well log data of the West arm of the East African Rift Valley. Comparative analysis of GMDH permeability model and ANN methods of the back propagation neural network (BPNN) and radial basis function neural network (RBFNN) were further explored. The results of the study showed that the proposed GMDH model outperformed BPNN and RBFNN as it achieved R/root mean square error (RMSE) value of 0.989/0.0241 for training and 0.868/0.204 for predicting, respectively. Sensitivity analysis carried out revealed that shale volume, standard resolution formation density, and thermal neutron porosity were the most influential well log parameters when developing the GMDH permeability model.
引用
收藏
页数:18
相关论文
共 50 条
[1]  
Abdel-Aal R., 2002, P SPE AS PAC OIL GAS
[2]   Estimation of the reservoir permeability by petrophysical information using intelligent systems [J].
Ahmadi, M. ;
Saemi, M. ;
Asghari, K. .
PETROLEUM SCIENCE AND TECHNOLOGY, 2008, 26 (14) :1656-1667
[3]  
Ahmadi Mohammad Ali, 2016, Petroleum, V2, P67, DOI 10.1016/j.petlm.2015.07.008
[4]   Reservoir permeability prediction by neural networks combined with hybrid genetic algorithm and particle swarm optimization [J].
Ahmadi, Mohammad Ali ;
Zendehboudi, Sohrab ;
Lohi, Ali ;
Elkamel, Ali ;
Chatzis, Ioannis .
GEOPHYSICAL PROSPECTING, 2013, 61 (03) :582-598
[5]   Hybrid intelligent systems in petroleum reservoir characterization and modeling: the journey so far and the challenges ahead [J].
Anifowose F.A. ;
Labadin J. ;
Abdulraheem A. .
Journal of Petroleum Exploration and Production Technology, 2017, 7 (01) :251-263
[6]   Investigating the Predictive Performance of Gaussian Process Regression in Evaluating Reservoir Porosity and Permeability [J].
Asante-Okyere, Solomon ;
Shen, Chuanbo ;
Ziggah, Yao Yevenyo ;
Rulegeya, Mercy Moses ;
Zhu, Xiangfeng .
ENERGIES, 2018, 11 (12)
[7]  
Ayoub MA., 2019, PROC SPEIATMI ASIA P, DOI [10.2118/196446-ms, DOI 10.2118/196446-MS]
[8]  
Barberi F., 1978, PETROLOGY GEOCHEMIST, P55, DOI [10.1007/978-94-009-9803-2, DOI 10.1007/978-94-009-9803-2]
[9]   Prediction of permeability in a tight gas reservoir by using three soft computing approaches: A comparative study [J].
Baziar, Sadegh ;
Tadayoni, Mehdi ;
Nabi-Bidhendi, Majid ;
Khalili, Mohsen .
JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING, 2014, 21 :718-724
[10]   Committee neural networks for porosity and permeability prediction from well logs [J].
Bhatt, A ;
Helle, HB .
GEOPHYSICAL PROSPECTING, 2002, 50 (06) :645-660