Title: Machine learning and data mining assisted petroleum reservoir engineering: a comprehensive review
Authors: Rupali Purbey; Harshwardhan Parijat; Divya Agarwal; Devarati Mitra; Rakhi Agarwal; Rakesh Kumar Pandey; Anil Kumar Dahiya
Addresses: School of Engineering and Technology, DIT University, Dehradun 248009, India ' School of Engineering and Technology, DIT University, Dehradun 248009, India ' School of Engineering and Technology, DIT University, Dehradun 248009, India ' School of Engineering and Technology, DIT University, Dehradun 248009, India ' School of Engineering and Technology, DIT University, Dehradun 248009, India ' School of Engineering and Technology, DIT University, Dehradun 248009, India ' Data Science Research Group, School of Computing, DIT University, Dehradun, 248009, India
Abstract: The oil and gas industry faces several challenges associated with managing massive datasets and extracting relevant information. The machine learning tools have proven to be significantly valuable for analysing complex, heterogeneous data and produce quicker and more reliable outcomes even on large-scales. Machine learning and data mining tools have been applied in several aspects of the upstream oil and gas industry, such as exploration, drilling, reservoir engineering, and production forecasting. This review has been explicitly focused on machine learning and data mining implementations in reservoir engineering, including reservoir characterisation and performance prediction, well test analysis, well logging and formation evaluation, and enhanced oil recovery operations. The commonly used statistical measures for classification and regression models have been discussed as well. The observations from the review have led to suitable suggestions that shall enrich the research in this area. [Received: July 29, 2021; Accepted: October 30, 2021]
Keywords: machine learning; data mining; prediction model; neural network; statistical measure; petroleum; reservoir engineering; performance prediction; well test; enhanced oil recovery.
DOI: 10.1504/IJOGCT.2022.124412
International Journal of Oil, Gas and Coal Technology, 2022 Vol.30 No.4, pp.359 - 387
Received: 29 Jul 2021
Accepted: 30 Oct 2021
Published online: 26 Jul 2022 *