Modeling Permeability Using Advanced White-Box Machine Learning Technique: Application to a Heterogeneous Carbonate Reservoir

被引:5
作者
Zhao, Lidong [1 ,2 ]
Guo, Yuanling [3 ]
Mohammadian, Erfan [2 ,7 ]
Hadavimoghaddam, Fahimeh [2 ]
Jafari, Mehdi [4 ]
Kheirollahi, Mahdi [5 ]
Rozhenko, Alexei [6 ]
Liu, Bo [2 ,7 ]
机构
[1] Northeast Petr Univ, Joint Int Res Lab Unconvent Energy Resources, Daqing 163318, Peoples R China
[2] Northeast Petr Univ, Key Lab Continental Shale Hydrocarbon Accumulat &, Minist Educ, Daqing 163318, Heilongjiang, Peoples R China
[3] SINOPEC Petr Explorat & Prod Res Inst, Beijing 102206, Peoples R China
[4] Shahid Beheshti Univ, Sch Earth Sci, Tehran 1983969411, Iran
[5] Univ Tehran, Coll Engn, Sch Min Engn, Tehran 145684, Iran
[6] Plekhanov Russian Univ Econ, Moscow 117997, Russia
[7] Northeast Petr Univ, Joint Int Res Lab Unconvent Energy Resources, Daqing 163318, Peoples R China
来源
ACS OMEGA | 2023年 / 8卷 / 25期
关键词
HYDRAULIC FLOW UNITS; PETROPHYSICAL PROPERTIES; ROCK; PREDICTION; CLASSIFICATION; METHODOLOGY; SOLUBILITY; PARAMETERS; INJECTION; ALGORITHM;
D O I
10.1021/acsomega.3c01927
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
From explorationto production, the permeability of reservoirrocksis essential for various stages of all types of hydrocarbon fielddevelopment. In the absence of costly reservoir rock samples, havinga reliable correlation to predict rock permeability in the zone(s)of interest is crucial. To predict permeability conventionally, petrophysicalrock typing is done. This method divides the reservoir into zonesof similar petrophysical properties, and the permeability correlationfor each zone is independently developed. The challenge of this approachis that the success depends upon the reservoir's complexityand heterogeneity and the methods and parameters used for rock typing.As a result, in the case of heterogeneous reservoirs, conventionalrock typing methods and indices fail to predict the permeability accurately.The target area is a heterogeneous carbonate reservoir in southwesternIran with a permeability range of 0.1-127.0 md. In this work,two approaches were used. First, based on permeability, porosity,the radius of pore throats at mercury saturation of 35% (r35), and connate water saturation (S (wc)) as inputs of K-nearest neighbors, the reservoir was classifiedinto two petrophysical zones, and then, permeability for each zonewas estimated. Due to the heterogeneous nature of the formation, thepredicted permeability results needed to be more accurate. In thesecond part, we applied novel machine learning algorithms, modifiedgroup modeling data handling (GMDH), and genetic programming (GP)to develop one universal permeability equation for the whole reservoirof interest as a function of porosity, the radius of pore throatsat mercury saturation of 35% (r35), and connate watersaturation (S (wc)). The novelty of the currentapproach is that despite being universal, the models developed usingGP and GMDH performed substantially better than zone-specific permeability,index-based empirical, or data-driven models used in the literature,such as FZI and Winland. The predicted permeability using GMDH andGP resulted in accurate prediction with R (2) of 0.99 and 0.95, respectively, in the heterogeneous reservoir ofinterest. Moreover, as this study aimed to develop an explainablemodel, different parameter importance analyses were also applied tothe developed permeability models, and r35 was foundto be the most impactful feature.
引用
收藏
页码:22922 / 22933
页数:12
相关论文
共 61 条
[41]   Competitive placement of oil perforation zones in hydraulic flow units from centrality measures [J].
Oliveira, G. P. ;
Roque, W. L. ;
Araujo, E. A. ;
Diniz, A. A. R. ;
Simoes, T. A. ;
Santos, M. D. .
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING, 2016, 147 :282-291
[42]   Machine learning strategies for classification and prediction of alteration facies: Examples from the Rosemont Cu-Mo-Ag skarn deposit, SE Tucson Arizona [J].
Ordonez-Calderon, Juan C. ;
Gelcich, Sergio .
JOURNAL OF GEOCHEMICAL EXPLORATION, 2018, 194 :167-188
[43]  
PITTMAN ED, 1992, AAPG BULL, V76, P191
[44]   A Structured Mobility-Based Methodology for Quantification of Net-Pay Cutoff in Petroleum Reservoirs [J].
Saboorian-Jooybari, Hadi .
SPE RESERVOIR EVALUATION & ENGINEERING, 2017, 20 (02) :317-333
[45]   Addressing Diverse Petroleum Industry Problems Using Machine Learning Techniques: Literary Methodology-Spotlight on Predicting Well Integrity Failures [J].
Salem, Adel M. ;
Yakoot, Mostafa S. ;
Mahmoud, Omar .
ACS OMEGA, 2022, 7 (03) :2504-2519
[46]   Computational intelligence intrusion detection techniques in mobile cloud computing environments: Review, taxonomy, and open research issues [J].
Shamshirband, Shahab ;
Fathi, Mahdis ;
Chronopoulos, Anthony T. ;
Montieri, Antonio ;
Palumbo, Fabio ;
Pescape, Antonio .
JOURNAL OF INFORMATION SECURITY AND APPLICATIONS, 2020, 55
[47]   A Survey of Deep Learning Techniques: Application in Wind and Solar Energy Resources [J].
Shamshirband, Shahab ;
Rabczuk, Timon ;
Chau, Kwok-Wing .
IEEE ACCESS, 2019, 7 :164650-164666
[48]   Group Method of Data Handling (GMDH) Lithology Identification Based on Wavelet Analysis and Dimensionality Reduction as Well Log Data Pre-Processing Techniques [J].
Shen, Chuanbo ;
Asante-Okyere, Solomon ;
Ziggah, Yao Yevenyo ;
Wang, Liang ;
Zhu, Xiangfeng .
ENERGIES, 2019, 12 (08)
[49]   Improvements in the selection criteria for representative special-core-analysis samples [J].
Siddiqui, S. ;
Okasha, T. M. ;
Funk, J. J. ;
Al-Harbi, A. M. .
SPE RESERVOIR EVALUATION & ENGINEERING, 2006, 9 (06) :647-653
[50]  
Sircar A., 2021, Petroleum Research, V6, P379, DOI [DOI 10.1016/J.PTLRS.2021.05.009, 10.1016/j.ptlrs.2021.05.009]