A New Approach for Ranking Enhanced Oil Recovery Methods Based on Multi-Gene Genetic Programming

Seyede Alemohammad | Mohammad Manthouri | mohsen pirizadeh | meysam pirizadeh

---

URL :   http://research.shahed.ac.ir/WSR/WebPages/Report/PaperView.aspx?PaperID=159173
Date :  2022/01/16
Publish in :    Petroleum Science and Technology
DOI :  https://doi.org/10.1080/10916466.2022.2030752
Link :  https://cats.informa.com/PTS/submitChangePwd.do
Keywords :Enhanced Oil Recovery; Expert System; Machine Learning; Multi-Gene Genetic Programming; Artificial Neural Network.

Abstract :

---

Ranking the appropriate EOR methods for a specific oilfield characteristic is a difficult and challenging task due to a large number of related parameters and financial risks. However, an expert automatic ranking tool enables making important decisions about potential EOR strategies by using real data and experiences of previous reservoirs. In this research, first, a new production rate consisting of natural production and EOR production called EOR-PR is introduced, which resolves the shortcomings of the proposed rate of previous research. Then, a new machine learning approach for ranking EOR methods for specific conditions of a reservoir including rock and fluid features based on predicting the efficiency of each EOR method according to its EOR-PR value is proposed. In this regard, Multi-Gene Genetic Programming (MGGP), which is a powerful machine learning method for modeling engineering problems, has been used to develop the models and its performance has been compared with the artificial neural network method. The results show that MGGP with an average of 0.982 for R2 correlation has a significant performance in this issue, and on the other hand, this method, unlike conventional machine learning methods, provides a definite function as the output that allows further analysis for reservoir experts.