Application of machine learning techniques for identifying productive zones in unconventional reservoir

Amir Gharavi*, Mohamed Hassan, Jebraeel Gholinezhad, Hesam Ghoochaninejad, Hossein Barati, James Buick, Karrar A. Abbas

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

19 Downloads (Pure)

Abstract

Unconventional reservoirs are the productive zones in other words the rock quality and the mechanical properties of the rocks this process is devastating if humans or people try to search for the best reservoirs. So we can use machine learning (ML) algorithms to help us find and search easily and fast for the best reservoirs with less human interaction as possible. The objectives of this paper is to use machine learning (ML) techniques to predict and classify the reservoirs based on the properties of each reservoirs and choose the best reservoir. In this paper we have made a comparison between the different types of machine learning algorithm and described how we get the best and worst result for each one, the comparison we made gave us that the AdaBoost algorithm gave the worst performance measured in the accuracy while the random forest (RF) algorithm gave the best performance, this paper aim to make improvement of the process of searching for productive zones using ML algorithms.

Original languageEnglish
Pages (from-to)87-101
Number of pages15
JournalInternational Journal of Intelligent Networks
Volume3
DOIs
Publication statusPublished - 19 Aug 2022

Keywords

  • Exploratory data analysis
  • Feature engineering
  • Feature importance
  • Hyperparameter tuning
  • Machine learning
  • Quick analyser
  • Unconventional resources

Cite this