Artificial Intelligence for Subsurface Characterization and Monitoring
- 1st Edition - January 20, 2025
- Editor: Aria Abubakar
- Language: English
- Paperback ISBN:9 7 8 - 0 - 4 4 3 - 2 3 5 1 7 - 7
- eBook ISBN:9 7 8 - 0 - 4 4 3 - 2 2 4 2 2 - 5
Artificial Intelligence for Subsurface Characterization and Monitoring provides an in-depth examination of how deep learning accelerates the process of subsurface character… Read more
Purchase options
Institutional subscription on ScienceDirect
Request a sales quoteArtificial Intelligence for Subsurface Characterization and Monitoring provides an in-depth examination of how deep learning accelerates the process of subsurface characterization and monitoring and provides an end-to-end solution. In recent years, deep learning has been introduced to the geoscience community to overcome some longstanding technical challenges. This book explores some of the most important topics in this discipline to explain the unique capability of deep learning in subsurface characterization for hydrocarbon exploration and production and for energy transition. Readers will discover deep learning methods that can improve the quality and efficiency of many of the key steps in subsurface characterization and monitoring.
The text is organized into five parts. The first two parts explore deep learning for data enrichment and well log data, including information extraction from unstructured well reports as well as log data QC and processing. Next is a review of deep learning applied to seismic data and data integration, which also covers intelligent processing for clearer seismic images and rock property inversion and validation. The closing section looks at deep learning in time lapse scenarios, including sparse data reconstruction for reducing the cost of 4D seismic data, time-lapse seismic data repeatability enforcement, and direct property prediction from pre-migration seismic data.
- Focus on deep learning applications for geoscience provides a one-stop reference for deep learning applications for geoscience.
- Comprehensive examples of the state-of-art techniques throughout the subsurface characterization workflow provide readers with a chance to familiarize themselves with deep learning applications not only in their own field of expertise but also in other relevant fields.
- All applications come with realistic field dataset examples so that readers can learn what to expect in real life.
Geophysics; petrophysics; geology; petroleum engineering. Geophysicists: process seismic data to provide seismic images used for energy resource exploration. Petrophysicists: process and interpret wellbore data used for energy resource exploration. Geoscientists: integrate and analyze geoscience data of different measurements. Reservoir engineers: analyze data for recovering hydrocarbon from subsurface reservoirs
- Title of Book
- Cover image
- Title page
- Table of Contents
- Copyright
- Dedication
- List of contributors
- Preface
- Introduction
- Part I: Deep learning for data enrichment
- Chapter one. Rejuvenating legacy data by digitizing raster logs
- Abstract
- Introduction
- Raster images and challenges with information extraction
- Raster digitization workflow
- Image translation using conditional generative adversarial networks
- Deep learning–based methods
- Conclusions and discussions
- Acknowledgments
- References
- Chapter two. Information extraction from unstructured well reports
- Abstract
- Introduction
- Applications in the oil and gas industry
- Document intelligence—methods and applications
- Document layout analysis
- Visual information extraction
- Field examples
- Conclusions
- References
- Part II: Deep learning applied to well log data
- Chapter three. Well log data quality control and processing
- Abstract
- Introduction
- Overview of example datasets
- Data harmonization
- Primary filters for outlier detection
- Analysis of wellbore logs and robust anomaly identification
- Missing log prediction
- Conclusions
- Acknowledgments
- AI disclosure
- References
- Chapter four. Automatic well marker picking
- Abstract
- Introduction
- Marker separation
- Marker picking
- Marker QC
- Conclusions
- References
- Chapter five. Automatic log interpretation
- Abstract
- Introduction
- Machine learning methods and application
- Field examples
- Conclusions
- References
- Part III: Deep learning applied to seismic data
- Chapter six. Intelligent processing for clearer seismic images
- Abstract
- Introduction
- Application examples
- Conclusions
- References
- Chapter seven. Seismic interpretation with improved quality and efficiency
- Abstract
- Introduction
- Solutions
- Conclusions and discussions
- Acknowledgments
- References
- Part IV: Deep learning for data integration
- Chapter eight. Automatic seismic-well tie
- Abstract
- Introduction
- A review of existing solutions
- Self-supervised learning workflow
- Examples
- Conclusions and discussions
- Acknowledgments
- References
- Chapter nine. Rock property inversion and validation
- Abstract
- Introduction
- Example dataset
- Solutions
- Extended application for windfarm site characterization
- Conclusions and discussions
- Acknowledgments
- References
- Part V: Deep learning in time lapse scenarios
- Chapter ten. Time-lapse seismic data repeatability enforcement
- Abstract
- Introduction
- Machine learning case studies
- Discussions
- References
- Chapter eleven. Direct property prediction from premigration seismic data
- Abstract
- Introduction
- Methodology
- Results
- Observation and conclusion
- Acknowledgments
- References
- Index
- No. of pages: 300
- Language: English
- Edition: 1
- Published: January 20, 2025
- Imprint: Elsevier
- Paperback ISBN: 9780443235177
- eBook ISBN: 9780443224225
AA
Aria Abubakar
Aria Abubakar is a senior R&D manager and scientist/engineer with more than 20 years of academic and industry experience. Aria has a variety of assignments in research, engineering (hardware), and software organization. He is currently the Head of Data Science & Scientific Advisor for Digital Subsurface Solutions at SLB based in the United States. He received his MSc degree in electrical engineering and PhD degree in computational sciences from Delft University of Technology in Delft, the Netherlands. He was the 2020 SEG-AAPG Distinguish Lecturer and the 2014 SEG North America Honorary Lecturer. Aria is the recipient of 2022 Conrad Schlumberger Award of EAGE and 2022 Honorary Membership Award of SEG. He holds over 50 patents/patent applications and has published 5 books and book chapters, over 120 peer-reviewed scientific articles, over 250 peer-reviewed conference papers, and over 50 conference abstracts.