Machine learning-based estimated ultimate recovery prediction and sweet spot evaluation of shale oil Online publication date: Fri, 08-Apr-2022
by Lufeng Zhan; Junwen Hu; Shaoyong Wang; Kun Wang; Bincheng Guo; Xuan Yang
International Journal of Oil, Gas and Coal Technology (IJOGCT), Vol. 30, No. 1, 2022
Abstract: In this paper, we propose a machine learning-based, multi-discipline integrated evaluation workflow to evaluate sweet spots. We predict the estimated ultimate recovery (EUR) map and evaluate sweet spots at different oil price scenarios in the study area. The results show that the correlation coefficient between well EUR and predicted EUR is 0.9247. At the oil price of $40, $50, and $60/bbl, the sweet spot areas are 3.31 km2, 27.75 km2, and 51.61 km2, and the total economically recoverable reserves are estimated to be 2.46 × 105 t, 14.02 × 105 t, 26.91 × 105 t respectively. It is concluded that machine learning model is an excellent way to auto learn the relationship between complex shale reservoir variables with EUR. It is innovative to show the distribution of sweet spots according to oil price. This workflow can be wildly used in the shale oil exploration and development to evaluate investments and optimise well placement. [Received: August 26, 2020; Accepted: April 19, 2021]
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Oil, Gas and Coal Technology (IJOGCT):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email subs@inderscience.com
Our Blog 
Follow us on Twitter 
Visit us on Facebook