Development of a Hybrid Scoring System for EOR Screening by Combining Conventional Screening Guidelines and Random Forest Algorithm

Abstract

Selecting a proper EOR method for a prospective reservoir is a key factor for successful application of EOR techniques. Reservoir engineers usually refer to screening guidelines to identify potential EOR processes for a given reservoir. However, these guidelines are characterized by poor discriminating powers. In this study, we develop a hybrid scoring system for EOR processes by combining conventional screening guidelines and the random forest algorithm. At first, the screening guidelines were established by compiling 977 EOR projects from various publications in different languages, including Oil and Gas Journal (OGJ) biannual EOR surveys, SPE publications, DOE reports, Chinese publications, etc. Boxplots were used to detect the special cases for each reservoir/fluid property and to present the graphical screening results. To avoid the experts' bias, the weighting factors for each EOR technique were determined through the application of the random forest algorithm, where the EOR types and the incremental oil recovery were utilized as objective functions. The scoring system was then established by the fuzzification of reservoir/fluid property scores and the computation of composite screening scores. A case study was used to demonstrate that with a simple input of reservoir/fluid information, the novel scoring system could effectively provide recommendations for EOR selection by ranking scores.

Department(s)

Geosciences and Geological and Petroleum Engineering

Research Center/Lab(s)

Center for Research in Energy and Environment (CREE)

Keywords and Phrases

Decision trees, EOR methods; Fuzzifications; Objective functions; Oil recoveries; Random forest algorithm; Reservoir engineers; Scoring systems; Weighting factors, Enhanced recovery

International Standard Serial Number (ISSN)

0016-2361

Document Type

Article - Journal

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2019 Elsevier Ltd, All rights reserved.

Publication Date

01 Nov 2019

Link to Full Text

Share

 
COinS