Page 182 - Machine Learning for Subsurface Characterization

Chapter 6

Index construction,

dimensionality reduction, and
clustering techniques for the

identification of flow units in
shale formations suitable for

enhanced oil recovery using
light-hydrocarbon injection

Hao Li* and Siddharth Misra †
* †
The University of Oklahoma, Norman, OK, United States, Harold Vance Department of Petroleum
Engineering, Texas A&M University, College Station, TX, United States

Chapter outline
1 Introduction 158 4 Methodology to generate the
1.1 Geology of the shale microscopic displacement (MD)
formation 158 index 164
1.2 Literature survey 158 4.1 Description of the MD-index 164
1.3 Objectives 159 4.2 Calculation of the MD-index 166
2 Properties influencing EOR 5 Methodology to generate the
efficiency of light-hydrocarbon K-means clustering (KC) index 175
injection 160 5.1 Description of the KC-index 175
3 Methodology to generate the 5.2 Calculation of the KC-index 176
ranking (R) index 162 6 Limitations 178
3.1 Description of the R-index 162 7 Conclusions 178
3.2 Calculation of the R-index 162 References 179

Nomenclature

MMP Minimum miscibility pressure
Magnitude of formation parameter (j) in formation (i)
P i, j
Ranking characteristic parameter for formation (i)
R i

Machine Learning for Subsurface Characterization. https://doi.org/10.1016/B978-0-12-817736-5.00002-8
© 2020 Elsevier Inc. All rights reserved. 157