Interpretable machine learning optimization (InterOpt) for operational parameters: A case study of highly-efficient shale gas development

Chen，Yun Tian1; Zhang，Dong Xiao1,2,3; Zhao，Qun4; Liu，De Xun4

2023

10.1016/j.petsci.2022.12.017

Petroleum Science   影响因子和分区

1672-5107

1995-8226

An algorithm named InterOpt for optimizing operational parameters is proposed based on interpretable machine learning, and is demonstrated via optimization of shale gas development. InterOpt consists of three parts: a neural network is used to construct an emulator of the actual drilling and hydraulic fracturing process in the vector space (i.e., virtual environment); the Sharpley value method in interpretable machine learning is applied to analyzing the impact of geological and operational parameters in each well (i.e., single well feature impact analysis); and ensemble randomized maximum likelihood (EnRML) is conducted to optimize the operational parameters to comprehensively improve the efficiency of shale gas development and reduce the average cost. In the experiment, InterOpt provides different drilling and fracturing plans for each well according to its specific geological conditions, and finally achieves an average cost reduction of 9.7% for a case study with 104 wells.

Interpretable machine learning Neural network Operational parameters optimization Shale gas development Shapley value

SCI ; EI

英语

其他

National Natural Science Foundation of China[62106116];

Energy & Fuels ; Engineering

Energy & Fuels ; Engineering, Petroleum

WOS:001034569600001

KEAI PUBLISHING LTD

20232014099948

Cost benefit analysis ; Cost reduction ; Gases ; Geology ; Hydraulic fracturing ; Infill drilling ; Maximum likelihood estimation ; Monte Carlo methods ; Parameter estimation ; Shale gas ; Vector spaces

Geology:481.1 ; Oil Field Production Operations:511.1 ; Petroleum Deposits : Development Operations:512.1.2 ; Natural Gas Deposits:512.2 ; Gas Fuels:522 ; Artificial Intelligence:723.4 ; Cost and Value Engineering; Industrial Economics:911 ; Management:912.2 ; Mathematics:921 ; Statistical Methods:922 ; Mathematical Statistics:922.2

2-s2.0-85159149932

Scopus

1.Eastern Institute for Advanced Study,Zhejiang,315200,China
2.Department of Mathematics and Theories,Peng Cheng Laboratory,Guangdong,518055,China
3.National Center for Applied Mathematics Shenzhen (NCAMS),Southern University of Science and Technology,Guangdong,518055,China
4.Research Institute of Petroleum Exploration and Development,CNPC,Beijing,100083,China

Chen，Yun Tian,Zhang，Dong Xiao,Zhao，Qun,et al. Interpretable machine learning optimization (InterOpt) for operational parameters: A case study of highly-efficient shale gas development[J]. Petroleum Science,2023,20(3):1788-1805.

Chen，Yun Tian,Zhang，Dong Xiao,Zhao，Qun,&Liu，De Xun.(2023).Interpretable machine learning optimization (InterOpt) for operational parameters: A case study of highly-efficient shale gas development.Petroleum Science,20(3),1788-1805.

Chen，Yun Tian,et al."Interpretable machine learning optimization (InterOpt) for operational parameters: A case study of highly-efficient shale gas development".Petroleum Science 20.3(2023):1788-1805.