Page 281 - Machine Learning for Subsurface Characterization

Chapter 9

Noninvasive fracture

characterization based on
the classification of sonic wave

travel times

Siddharth Misra* and Hao Li †
*
Harold Vance Department of Petroleum Engineering, Texas A&M University, College Station,
†
TX, United States, The University of Oklahoma, Norman, OK, United States
Chapter outline
1 Introduction 244 4 Methodology for developing data-
1.1 Mechanical driven model for the noninvasive
discontinuities 244 characterization of static
1.2 Characterization of mechanical discontinuities in
discontinuities 244 material 259
1.3 Machine learning 4.1 Classification methods
for characterization implemented for the
of discontinuities 245 proposed fracture
2 Objective 246 characterization workflow 262
2.1 Assumptions and limitations 5 Results for the classification-
of the proposed data-driven based noninvasive characterization
fracture characterization of static mechanical
method 247 discontinuities in materials 271
2.2 Significance and 5.1 Characterization of material
relevance of the proposed containing static discontinuities
data-driven fracture of various dispersions around
characterization the primary orientation 271
method 247 5.2 Characterization of material
3 Fast-marching method (FMM) 248 containing static discontinuities of
3.1 Introduction 248 various primary orientations 275
3.2 Validation 248 5.3 Characterization of material
3.3 Fast-marching simulation containing static discontinuities
of compressional wavefront of various spatial distributions 281
travel time for materials Acknowledgments 285
containing discontinuities 256 References 285
Further reading 287

Machine Learning for Subsurface Characterization. https://doi.org/10.1016/B978-0-12-817736-5.00009-0
© 2020 Elsevier Inc. All rights reserved. 243