Hybrid Machine Learning for Modeling the Relative Permeability Changes in Carbonate Reservoirs under Engineered Water Injection

被引:0
作者
Reginato, Leonardo Fonseca [1 ]
Gioria, Rafael dos Santos [1 ]
Sampaio, Marcio Augusto [1 ]
机构
[1] Univ Sao Paulo, Dept Engn Minas & Petr, Escola Politecn, BR-05508010 Sao Paulo, Brazil
关键词
Hybrid Machine Learning; Engineered Water Injection; wettability alteration; LOW-SALINITY;
D O I
10.3390/en16134849
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
Advanced production methods utilize complex fluid iteration mechanisms to provide benefits in their implementation. However, modeling these effects with efficiency or accuracy is always a challenge. Machine Learning (ML) applications, which are fundamentally data-driven, can play a crucial role in this context. Therefore, in this study, we applied a Hybrid Machine Learning (HML) solution to predict petrophysical behaviors during Engineered Water Injection (EWI). This hybrid approach utilizes K-Means and Artificial Neural Network algorithms to predict petrophysical behaviors during EWI. In addition, we applied an optimization process to maximize the Net Present Value (NPV) of a case study, and the results demonstrate that the HML approach outperforms conventional methods by increasing oil production (7.3%) while decreasing the amount of water injected and produced (by 28% and 40%, respectively). Even when the injection price is higher, this method remains profitable. Therefore, our study highlights the potential benefits of utilizing HML solutions for predicting petrophysical behaviors during EWI. This approach can significantly improve the accuracy and efficiency of modeling advanced production methods, which may help the profitability of new and mature oil fields.
引用
收藏
页数:16
相关论文
共 18 条
[1]  
[Anonymous], BENCHMARK CASE PROPO
[2]  
[Anonymous], 2014, P SPE IMPR OIL REC S
[3]   Low Salinity EOR Effects in Limestone Reservoir Cores Containing Anhydrite: A Discussion of the Chemical Mechanism [J].
Austad, T. ;
Shariatpanahi, S. F. ;
Strand, S. ;
Aksulu, H. ;
Puntervold, T. .
ENERGY & FUELS, 2015, 29 (11) :6903-6911
[4]  
Bangert P, 2021, Machine Learning and Data Science in the Oil and Gas Industry: best practices, tools, and case studies, P69, DOI [10.1016/b978-0-12-820714-7.00004-2, DOI 10.1016/B978-0-12-820714-7.00004-2]
[5]  
Brooks R.H., 1964, Hydrology Paper No. 3, V7, P26
[6]  
Correia M., 2015, P SPE LAT AM CAR PET
[7]  
Craig F. F., 1971, MONOGRAPH SERIES SPE, V3, P38
[8]  
Evans S. J., 2019, P OFFSH TECHN C
[9]   Machine learning in oil and gas; a SWOT analysis approach [J].
Hajizadeh, Yasin .
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING, 2019, 176 :661-663
[10]   Application of neural networks in multiphase flow through porous media: Predicting capillary pressure and relative permeability curves [J].
Liu, Siyan ;
Zolfaghari, Arsalan ;
Sattarin, Shariar ;
Dahaghi, Amirmasoud Kalantari ;
Negahban, Shahin .
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING, 2019, 180 :445-455