Predicting porosity, permeability, and tortuosity of porous media from images by deep learning
Abstract Convolutional neural networks (CNN) are utilized to encode the relation between initial configurations of obstacles and three fundamental quantities in porous media: porosity ( $$\varphi$$ φ ), permeability (k), and tortuosity (T). The two-dimensional systems with obstacles are considered....
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2020-12-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-020-78415-x |
| _version_ | 1818749309414277120 |
|---|---|
| author | Krzysztof M. Graczyk Maciej Matyka |
| author_facet | Krzysztof M. Graczyk Maciej Matyka |
| author_sort | Krzysztof M. Graczyk |
| collection | DOAJ |
| description | Abstract Convolutional neural networks (CNN) are utilized to encode the relation between initial configurations of obstacles and three fundamental quantities in porous media: porosity ( $$\varphi$$ φ ), permeability (k), and tortuosity (T). The two-dimensional systems with obstacles are considered. The fluid flow through a porous medium is simulated with the lattice Boltzmann method. The analysis has been performed for the systems with $$\varphi \in (0.37,0.99)$$ φ ∈ ( 0.37 , 0.99 ) which covers five orders of magnitude a span for permeability $$k \in (0.78, 2.1\times 10^5)$$ k ∈ ( 0.78 , 2.1 × 10 5 ) and tortuosity $$T \in (1.03,2.74)$$ T ∈ ( 1.03 , 2.74 ) . It is shown that the CNNs can be used to predict the porosity, permeability, and tortuosity with good accuracy. With the usage of the CNN models, the relation between T and $$\varphi$$ φ has been obtained and compared with the empirical estimate. |
| first_indexed | 2024-12-18T04:01:44Z |
| format | Article |
| id | doaj.art-44c73faaec22405489053f3f380e5ee8 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-12-18T04:01:44Z |
| publishDate | 2020-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-44c73faaec22405489053f3f380e5ee82022-12-21T21:21:41ZengNature PortfolioScientific Reports2045-23222020-12-0110111110.1038/s41598-020-78415-xPredicting porosity, permeability, and tortuosity of porous media from images by deep learningKrzysztof M. Graczyk0Maciej Matyka1Institute of Theoretical Physics, Faculty of Physics and Astronomy, University of WrocławInstitute of Theoretical Physics, Faculty of Physics and Astronomy, University of WrocławAbstract Convolutional neural networks (CNN) are utilized to encode the relation between initial configurations of obstacles and three fundamental quantities in porous media: porosity ( $$\varphi$$ φ ), permeability (k), and tortuosity (T). The two-dimensional systems with obstacles are considered. The fluid flow through a porous medium is simulated with the lattice Boltzmann method. The analysis has been performed for the systems with $$\varphi \in (0.37,0.99)$$ φ ∈ ( 0.37 , 0.99 ) which covers five orders of magnitude a span for permeability $$k \in (0.78, 2.1\times 10^5)$$ k ∈ ( 0.78 , 2.1 × 10 5 ) and tortuosity $$T \in (1.03,2.74)$$ T ∈ ( 1.03 , 2.74 ) . It is shown that the CNNs can be used to predict the porosity, permeability, and tortuosity with good accuracy. With the usage of the CNN models, the relation between T and $$\varphi$$ φ has been obtained and compared with the empirical estimate.https://doi.org/10.1038/s41598-020-78415-x |
| spellingShingle | Krzysztof M. Graczyk Maciej Matyka Predicting porosity, permeability, and tortuosity of porous media from images by deep learning Scientific Reports |
| title | Predicting porosity, permeability, and tortuosity of porous media from images by deep learning |
| title_full | Predicting porosity, permeability, and tortuosity of porous media from images by deep learning |
| title_fullStr | Predicting porosity, permeability, and tortuosity of porous media from images by deep learning |
| title_full_unstemmed | Predicting porosity, permeability, and tortuosity of porous media from images by deep learning |
| title_short | Predicting porosity, permeability, and tortuosity of porous media from images by deep learning |
| title_sort | predicting porosity permeability and tortuosity of porous media from images by deep learning |
| url | https://doi.org/10.1038/s41598-020-78415-x |
| work_keys_str_mv | AT krzysztofmgraczyk predictingporositypermeabilityandtortuosityofporousmediafromimagesbydeeplearning AT maciejmatyka predictingporositypermeabilityandtortuosityofporousmediafromimagesbydeeplearning |