Deep learning for diffusion in porous media
Abstract We adopt convolutional neural networks (CNN) to predict the basic properties of the porous media. Two different media types are considered: one mimics the sand packings, and the other mimics the systems derived from the extracellular space of biological tissues. The Lattice Boltzmann Method...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-06-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-36466-w |
| _version_ | 1797801419780128768 |
|---|---|
| author | Krzysztof M. Graczyk Dawid Strzelczyk Maciej Matyka |
| author_facet | Krzysztof M. Graczyk Dawid Strzelczyk Maciej Matyka |
| author_sort | Krzysztof M. Graczyk |
| collection | DOAJ |
| description | Abstract We adopt convolutional neural networks (CNN) to predict the basic properties of the porous media. Two different media types are considered: one mimics the sand packings, and the other mimics the systems derived from the extracellular space of biological tissues. The Lattice Boltzmann Method is used to obtain the labeled data necessary for performing supervised learning. We distinguish two tasks. In the first, networks based on the analysis of the system’s geometry predict porosity and effective diffusion coefficient. In the second, networks reconstruct the concentration map. In the first task, we propose two types of CNN models: the C-Net and the encoder part of the U-Net. Both networks are modified by adding a self-normalization module [Graczyk et al. in Sci Rep 12, 10583 (2022)]. The models predict with reasonable accuracy but only within the data type, they are trained on. For instance, the model trained on sand packings-like samples overshoots or undershoots for biological-like samples. In the second task, we propose the usage of the U-Net architecture. It accurately reconstructs the concentration fields. In contrast to the first task, the network trained on one data type works well for the other. For instance, the model trained on sand packings-like samples works perfectly on biological-like samples. Eventually, for both types of the data, we fit exponents in the Archie’s law to find tortuosity that is used to describe the dependence of the effective diffusion on porosity. |
| first_indexed | 2024-03-13T04:50:11Z |
| format | Article |
| id | doaj.art-1dfbd116dadd42f291ab9fa97b75ab37 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-13T04:50:11Z |
| publishDate | 2023-06-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-1dfbd116dadd42f291ab9fa97b75ab372023-06-18T11:13:55ZengNature PortfolioScientific Reports2045-23222023-06-0113111610.1038/s41598-023-36466-wDeep learning for diffusion in porous mediaKrzysztof M. Graczyk0Dawid Strzelczyk1Maciej Matyka2Faculty of Physics and Astronomy, Institute of Theoretical Physics, University of WrocławFaculty of Physics and Astronomy, Institute of Theoretical Physics, University of WrocławFaculty of Physics and Astronomy, Institute of Theoretical Physics, University of WrocławAbstract We adopt convolutional neural networks (CNN) to predict the basic properties of the porous media. Two different media types are considered: one mimics the sand packings, and the other mimics the systems derived from the extracellular space of biological tissues. The Lattice Boltzmann Method is used to obtain the labeled data necessary for performing supervised learning. We distinguish two tasks. In the first, networks based on the analysis of the system’s geometry predict porosity and effective diffusion coefficient. In the second, networks reconstruct the concentration map. In the first task, we propose two types of CNN models: the C-Net and the encoder part of the U-Net. Both networks are modified by adding a self-normalization module [Graczyk et al. in Sci Rep 12, 10583 (2022)]. The models predict with reasonable accuracy but only within the data type, they are trained on. For instance, the model trained on sand packings-like samples overshoots or undershoots for biological-like samples. In the second task, we propose the usage of the U-Net architecture. It accurately reconstructs the concentration fields. In contrast to the first task, the network trained on one data type works well for the other. For instance, the model trained on sand packings-like samples works perfectly on biological-like samples. Eventually, for both types of the data, we fit exponents in the Archie’s law to find tortuosity that is used to describe the dependence of the effective diffusion on porosity.https://doi.org/10.1038/s41598-023-36466-w |
| spellingShingle | Krzysztof M. Graczyk Dawid Strzelczyk Maciej Matyka Deep learning for diffusion in porous media Scientific Reports |
| title | Deep learning for diffusion in porous media |
| title_full | Deep learning for diffusion in porous media |
| title_fullStr | Deep learning for diffusion in porous media |
| title_full_unstemmed | Deep learning for diffusion in porous media |
| title_short | Deep learning for diffusion in porous media |
| title_sort | deep learning for diffusion in porous media |
| url | https://doi.org/10.1038/s41598-023-36466-w |
| work_keys_str_mv | AT krzysztofmgraczyk deeplearningfordiffusioninporousmedia AT dawidstrzelczyk deeplearningfordiffusioninporousmedia AT maciejmatyka deeplearningfordiffusioninporousmedia |