RockFlow: Fast Generation of Synthetic Source Rock Images Using Generative Flow Models
Image-based evaluation methods are a valuable tool for source rock characterization. The time and resources needed to obtain images has spurred development of machine-learning generative models to create synthetic images of pore structure and rock fabric from limited image data. While generative mod...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-12-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/13/24/6571 |
| _version_ | 1797544811487559680 |
|---|---|
| author | Timothy I. Anderson Kelly M. Guan Bolivia Vega Saman A. Aryana Anthony R. Kovscek |
| author_facet | Timothy I. Anderson Kelly M. Guan Bolivia Vega Saman A. Aryana Anthony R. Kovscek |
| author_sort | Timothy I. Anderson |
| collection | DOAJ |
| description | Image-based evaluation methods are a valuable tool for source rock characterization. The time and resources needed to obtain images has spurred development of machine-learning generative models to create synthetic images of pore structure and rock fabric from limited image data. While generative models have shown success, existing methods for generating 3D volumes from 2D training images are restricted to binary images and grayscale volume generation requires 3D training data. Shale characterization relies on 2D imaging techniques such as scanning electron microscopy (SEM), and grayscale values carry important information about porosity, kerogen content, and mineral composition of the shale. Here, we introduce RockFlow, a method based on generative flow models that creates grayscale volumes from 2D training data. We apply RockFlow to baseline binary micro-CT image volumes and compare performance to a previously proposed model. We also show the extension of our model to 2D grayscale data by generating grayscale image volumes from 2D SEM and dual modality nanoscale shale images. The results show that our method underestimates the porosity and surface area on the binary baseline datasets but is able to generate realistic grayscale image volumes for shales. With improved binary data preprocessing, we believe that our model is capable of generating synthetic porous media volumes for a very broad class of rocks from shale to carbonates to sandstone. |
| first_indexed | 2024-03-10T14:05:50Z |
| format | Article |
| id | doaj.art-5c284f0b5d174ff2aa12fc87852eeeb2 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T14:05:50Z |
| publishDate | 2020-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-5c284f0b5d174ff2aa12fc87852eeeb22023-11-21T00:38:07ZengMDPI AGEnergies1996-10732020-12-011324657110.3390/en13246571RockFlow: Fast Generation of Synthetic Source Rock Images Using Generative Flow ModelsTimothy I. Anderson0Kelly M. Guan1Bolivia Vega2Saman A. Aryana3Anthony R. Kovscek4Department of Electrical Engineering, Stanford University, Stanford, CA 94305, USADepartment of Energy Resources Engineering, Stanford University, Stanford, CA 94305, USADepartment of Energy Resources Engineering, Stanford University, Stanford, CA 94305, USADepartment of Chemical Engineering, University of Wyoming, Laramie, WY 82071, USADepartment of Energy Resources Engineering, Stanford University, Stanford, CA 94305, USAImage-based evaluation methods are a valuable tool for source rock characterization. The time and resources needed to obtain images has spurred development of machine-learning generative models to create synthetic images of pore structure and rock fabric from limited image data. While generative models have shown success, existing methods for generating 3D volumes from 2D training images are restricted to binary images and grayscale volume generation requires 3D training data. Shale characterization relies on 2D imaging techniques such as scanning electron microscopy (SEM), and grayscale values carry important information about porosity, kerogen content, and mineral composition of the shale. Here, we introduce RockFlow, a method based on generative flow models that creates grayscale volumes from 2D training data. We apply RockFlow to baseline binary micro-CT image volumes and compare performance to a previously proposed model. We also show the extension of our model to 2D grayscale data by generating grayscale image volumes from 2D SEM and dual modality nanoscale shale images. The results show that our method underestimates the porosity and surface area on the binary baseline datasets but is able to generate realistic grayscale image volumes for shales. With improved binary data preprocessing, we believe that our model is capable of generating synthetic porous media volumes for a very broad class of rocks from shale to carbonates to sandstone.https://www.mdpi.com/1996-1073/13/24/6571porous mediaimage analysisshaledeep learninggenerative flow model |
| spellingShingle | Timothy I. Anderson Kelly M. Guan Bolivia Vega Saman A. Aryana Anthony R. Kovscek RockFlow: Fast Generation of Synthetic Source Rock Images Using Generative Flow Models Energies porous media image analysis shale deep learning generative flow model |
| title | RockFlow: Fast Generation of Synthetic Source Rock Images Using Generative Flow Models |
| title_full | RockFlow: Fast Generation of Synthetic Source Rock Images Using Generative Flow Models |
| title_fullStr | RockFlow: Fast Generation of Synthetic Source Rock Images Using Generative Flow Models |
| title_full_unstemmed | RockFlow: Fast Generation of Synthetic Source Rock Images Using Generative Flow Models |
| title_short | RockFlow: Fast Generation of Synthetic Source Rock Images Using Generative Flow Models |
| title_sort | rockflow fast generation of synthetic source rock images using generative flow models |
| topic | porous media image analysis shale deep learning generative flow model |
| url | https://www.mdpi.com/1996-1073/13/24/6571 |
| work_keys_str_mv | AT timothyianderson rockflowfastgenerationofsyntheticsourcerockimagesusinggenerativeflowmodels AT kellymguan rockflowfastgenerationofsyntheticsourcerockimagesusinggenerativeflowmodels AT boliviavega rockflowfastgenerationofsyntheticsourcerockimagesusinggenerativeflowmodels AT samanaaryana rockflowfastgenerationofsyntheticsourcerockimagesusinggenerativeflowmodels AT anthonyrkovscek rockflowfastgenerationofsyntheticsourcerockimagesusinggenerativeflowmodels |