Machine learning to predict effective reaction rates in 3D porous media from pore structural features
- PMID: 35361834
- PMCID: PMC8971379
- DOI: 10.1038/s41598-022-09495-0
Machine learning to predict effective reaction rates in 3D porous media from pore structural features
Abstract
Large discrepancies between well-mixed reaction rates and effective reactions rates estimated under fluid flow conditions have been a major issue for predicting reactive transport in porous media systems. In this study, we introduce a framework that accurately predicts effective reaction rates directly from pore structural features by combining 3D pore-scale numerical simulations with machine learning (ML). We first perform pore-scale reactive transport simulations with fluid-solid reactions in hundreds of porous media and calculate effective reaction rates from pore-scale concentration fields. We then train a Random Forests model with 11 pore structural features and effective reaction rates to quantify the importance of structural features in determining effective reaction rates. Based on the importance information, we train artificial neural networks with varying number of features and demonstrate that effective reaction rates can be accurately predicted with only three pore structural features, which are specific surface, pore sphericity, and coordination number. Finally, global sensitivity analyses using the ML model elucidates how the three structural features affect effective reaction rates. The proposed framework enables accurate predictions of effective reaction rates directly from a few measurable pore structural features, and the framework is readily applicable to a wide range of applications involving porous media flows.
© 2022. The Author(s).
Conflict of interest statement
The authors declare no competing interests.
Figures
![Figure 1](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/8971379/bin/41598_2022_9495_Fig1_HTML.gif)
![Figure 2](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/8971379/bin/41598_2022_9495_Fig2_HTML.gif)
![Figure 3](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/8971379/bin/41598_2022_9495_Fig3_HTML.gif)
![Figure 4](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/8971379/bin/41598_2022_9495_Fig4_HTML.gif)
![Figure 5](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/8971379/bin/41598_2022_9495_Fig5_HTML.gif)
![Figure 6](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/8971379/bin/41598_2022_9495_Fig6_HTML.gif)
Similar articles
-
Predictions of dynamic changes in reaction rates as a consequence of incomplete mixing using pore scale reactive transport modeling on images of porous media.J Contam Hydrol. 2015 Aug;179:171-81. doi: 10.1016/j.jconhyd.2015.06.004. Epub 2015 Jun 11. J Contam Hydrol. 2015. PMID: 26142546
-
Evaluation of the effects of porous media structure on mixing-controlled reactions using pore-scale modeling and micromodel experiments.Environ Sci Technol. 2008 May 1;42(9):3185-93. doi: 10.1021/es7022835. Environ Sci Technol. 2008. PMID: 18522092
-
Fluid-Solid Reaction in Porous Media as a Chaotic Restart Process.Phys Rev Lett. 2023 Jun 30;130(26):264001. doi: 10.1103/PhysRevLett.130.264001. Phys Rev Lett. 2023. PMID: 37450789
-
Reactive Flows in Porous Media: Challenges in Theoretical and Numerical Methods.Annu Rev Chem Biomol Eng. 2021 Jun 7;12:543-571. doi: 10.1146/annurev-chembioeng-092920-102703. Epub 2021 Mar 30. Annu Rev Chem Biomol Eng. 2021. PMID: 33784175 Review.
-
A review on reactive transport model and porosity evolution in the porous media.Environ Sci Pollut Res Int. 2022 Jul;29(32):47873-47901. doi: 10.1007/s11356-022-20466-w. Epub 2022 May 6. Environ Sci Pollut Res Int. 2022. PMID: 35522402 Free PMC article. Review.
Cited by
-
Leave No Photon Behind: Artificial Intelligence in Multiscale Physics of Photocatalyst and Photoreactor Design.Adv Sci (Weinh). 2024 May;11(18):e2306604. doi: 10.1002/advs.202306604. Epub 2024 Mar 13. Adv Sci (Weinh). 2024. PMID: 38477404 Free PMC article. Review.
-
Reinforcement Learning for Traversing Chemical Structure Space: Optimizing Transition States and Minimum Energy Paths of Molecules.J Phys Chem Lett. 2024 Jan 11;15(1):349-356. doi: 10.1021/acs.jpclett.3c02771. Epub 2024 Jan 3. J Phys Chem Lett. 2024. PMID: 38170921 Free PMC article.
-
An interpretable deep learning approach for designing nanoporous silicon nitride membranes with tunable mechanical properties.NPJ Comput Mater. 2023;9(1):82. doi: 10.1038/s41524-023-01037-0. Epub 2023 May 27. NPJ Comput Mater. 2023. PMID: 37273663 Free PMC article.
-
Coupled Lattice Boltzmann Modeling Framework for Pore-Scale Fluid Flow and Reactive Transport.ACS Omega. 2023 Apr 3;8(15):13649-13669. doi: 10.1021/acsomega.2c07643. eCollection 2023 Apr 18. ACS Omega. 2023. PMID: 37091418 Free PMC article.
References
-
- Norouzi AM, Babaei M, Han WS, Kim K-Y, Niasar V. CO2-plume geothermal processes: A parametric study of salt precipitation influenced by capillary-driven back flow. Chem. Eng. J. 2021;425:130031.
-
- Erfani H, Joekar-Niasar V, Farajzadeh R. Impact of microheterogeneity on upscaling reactive transport in geothermal energy. ACS Earth Space Chem. 2019;3:2045.
-
- Maher K, Steefel CI, DePaolo DJ, Viani BE. The mineral dissolution rate conundrum: Insights from reactive transport modeling of U isotopes and pore fluid chemistry in marine sediments. Geochim. et Cosmochim. Acta. 2006;70:337.
-
- Lee W, et al. Spatiotemporal evolution of iron and sulfate concentrations during riverbank filtration: Field observations and reactive transport modeling. J. Contam. Hydrol. 2020;234:103697. - PubMed
-
- Zhi W, et al. From hydrometeorology to river water quality: Can a deep learning model predict dissolved oxygen at the continental scale? Environ. Sci. Technol. 2021;55:2357. - PubMed
Publication types
MeSH terms
Substances
LinkOut - more resources
Full Text Sources