Viscoelastic numerical modeling and deep learning for seismic reservoir characterization
Abstract/Contents
- Abstract
- In this thesis, numerical modeling and deep-learning techniques are used to tackle the complex problem of subsurface reservoir characterization using geophysical measurements. The first part of the dissertation is focused on understanding and numerically modeling rocks as viscoelastic materials. Rocks modeled using viscoelastic theory helped in understanding coupled fluid-solid interaction effects at the pore scale that cannot be modeled using elasticity theory. Modeling scale effects of heterogeneities in layered viscoelastic media confirmed the dependence of seismic velocities and intrinsic attenuation on the ratio of dominant wavelength to length spacing. A viscoelastic upscaling method was developed that helped in integration of seismic data considering viscoelastic information measured at different frequencies. The second part of the dissertation is focused on using deep learning for quantitative seismic interpretation. In this part, solutions to quantitative seismic interpretation problems were learned by a deep network directly from the data. Convolutional neural networks (CNNs) used in this work were found to capture spatial patterns and were relatively easier to design and train as compared to other deep learning architectures. The success of CNN based network architectures in solving geophysical problems were demonstrated using four different seismic reservoir characterization problems -- 1. Acoustic impedance inversion from post-stack seismic data, 2. P-wave velocity, S-wave velocity and density inversion from pre-stack seismic data, 3. Petrophysical properties (porosity and volume of clay) predictions from pre-stack seismic data, and 4. Amplitude variation with offset (AVO) classification from pre-stack seismic data. The network architectures developed in this dissertation serve as a benchmark for future deep network architectures (more sophisticated ones) that are foreseen to be developed to solve similar problems with greater accuracy.
Description
| Type of resource | text |
|---|---|
| Form | electronic resource; remote; computer; online resource |
| Extent | 1 online resource. |
| Place | California |
| Place | [Stanford, California] |
| Publisher | [Stanford University] |
| Copyright date | 2019; ©2019 |
| Publication date | 2019; 2019 |
| Issuance | monographic |
| Language | English |
Creators/Contributors
| Author | Das, Vishal |
|---|---|
| Degree supervisor | Mukerji, Tapan, 1965- |
| Thesis advisor | Mukerji, Tapan, 1965- |
| Thesis advisor | Biondi, Biondo, 1959- |
| Thesis advisor | Mavko, Gary, 1949- |
| Degree committee member | Biondi, Biondo, 1959- |
| Degree committee member | Mavko, Gary, 1949- |
| Associated with | Stanford University, Department of Geophysics. |
Subjects
| Genre | Theses |
|---|---|
| Genre | Text |
Bibliographic information
| Statement of responsibility | Vishal Das. |
|---|---|
| Note | Submitted to the Department of Geophysics. |
| Thesis | Thesis Ph.D. Stanford University 2019. |
| Location | electronic resource |
Access conditions
- Copyright
- © 2019 by Vishal Das
- License
- This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).
Also listed in
Loading usage metrics...