Hybrid application of unsupervised and supervised learning in forecasting absolute open flow potential for shale gas reservoirs

Lian Wang, Yuedong Yao, Kongjie Wang, Caspar Daniel Adenutsi, Guoxiang Zhao and Fengpeng Lai

Energy, 2022, vol. 243, issue C

Abstract: Forecasting productivity of shale gas has gained much attention in recent years. However, few researchers considered forecasting absolute open flow potential (AOFP). The conventional method of determining the AOFP of gas wells is through a systematic well testing which is time consuming and has adverse economic effects. Therefore, the objective of this research is to establish an efficient and applicable method for forecasting shale gas well AOFP. In this study, we combined one of the most classic unsupervised machine learning methods namely, principal component analysis (PCA) with least squares support vector regression (LSSVR) which is an efficient supervised machine learning method in forecasting the AOFP for shale gas wells. This method was named hybrid machine learning method based on PCA and LSSVR model (LSSVR-PCA). The proposed method was applied to the Weiyuan, Changning as well as Zhaotong shale gas reservoirs in the Sichuan basin, southwest China. Results showed that the proposed method could forecast AOFP with high accuracy and efficiency if adequate well data are accessible. This hybrid machine learning method also provides an intelligent approach for field engineers to forecast the AOFP and appropriately allocate production of gas wells.

Keywords: Principal component analysis; Support vector regression; Absolute open flow potential; Shale gas (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (3)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544221029960
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:243:y:2022:i:c:s0360544221029960

DOI: 10.1016/j.energy.2021.122747

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().