Page 154 - Machine Learning for Subsurface Characterization

Chapter 5

Robust geomechanical

characterization by analyzing
the performance of

shallow-learning regression
methods using unsupervised

clustering methods

†
Siddharth Misra*, Hao Li and Jiabo He ‡,a
*
Harold Vance Department of Petroleum Engineering, Texas A&M University, College Station,
‡
†
TX, United States, The University of Oklahoma, Norman, OK, United States, School of Computing
and Information Systems, University of Melbourne, Parkville, VIC, Australia
Chapter outline
1 Introduction 130 3.1 Prediction performances of
2 Methodology 132 shallow-learning regression
2.1 Data preparation 132 models 147
2.2 Data preprocessing 133 3.2 Comparison of prediction
2.3 Metric to evaluate the log- performances of shallow-learning
synthesis performance of the regression models in Well 1 148
shallow-learning regression 3.3 Performance of clustering-
models 133 based reliability of sonic-log
2.4 Shallow-learning regression synthesis 151
models 134 4 Conclusions 154
2.5 Clustering techniques 141 References 155
3 Results 147

Nomenclature

RSS Residual sum of squares
TSS Total sum of squares
SSE Sum of squared errors
OLS Ordinary least squares

a
Formerly at the University of Oklahoma, Norman, OK, United States
Machine Learning for Subsurface Characterization. https://doi.org/10.1016/B978-0-12-817736-5.00005-3
© 2020 Elsevier Inc. All rights reserved. 129