Hybrid approach for permeability prediction in porous media: combining FFT simulations with machine learning

Bang Ly Hai-; -Long Nguyen Hoang; -Hung Phan Viet; Vincent Monchiet

doi:10.15625/2615-9783/21133

Author affiliations

Authors

Hai-Bang Ly University of Transport Technology, Hanoi 100000, Vietnam
Hoang-Long Nguyen University of Transport Technology, Hanoi 100000, Vietnam
Viet-Hung Phan 1-University of Transport and Communications, Hanoi 100000, Vietnam; 2-Univ Gustave Eiffel, Univ Paris Est Creteil, CNRS, MSME UMR 8208, 77454, Marne-la-Vallée, France
Vincent Monchiet Univ Gustave Eiffel, Univ Paris Est Creteil, CNRS, MSME UMR 8208, 77454, Marne-la-Vallée, France

DOI:

https://doi.org/10.15625/2615-9783/21133

Keywords:

Permeability, machine learning, porous media, FFT, optimization

Abstract

The prediction of permeability in porous media is a critical aspect in various scientific and engineering applications. This paper presents a machine learning (ML) model based on the XGBoost algorithm for predicting the permeability of porous media using microstructure characteristics. The seahorse optimization algorithm was employed to fine-tune the hyperparameters of the XGBoost algorithm, resulting in a model with predictive solid capabilities. Regression analysis and residual errors indicated that the model achieved good prediction results on the training and testing datasets, with RMSE values of 0.0494 and 0.0826, respectively. A SHAP value sensitivity analysis revealed that the essential inputs were the size of the inclusions, with the quantiles representing the maximum size of the inclusions being the most significant variables affecting permeability. The findings of this study have important implications for the design and optimization of porous media, and the XGBoost algorithm-based ML model provides a fast and accurate tool for predicting the permeability of porous media based on microstructure characteristics.

Downloads

Download data is not yet available.

References

Al‐Omari A., Masad E., 2004. Three dimensional simulation of fluid flow in X‐ray CT images of porous media. Num Anal Meth Geomechanics, 28, 1327–1360. https://doi.org/10.1002/nag.389.

Auriault J.L., Boutin C., 1992. Deformable porous media with double porosity. Quasi-statics. I: Coupling effects. Transport in Porous Media, 7, 63–82.

Auriault J.L., Boutin C., 1993. Deformable porous media with double porosity. Quasi-statics. II: Memory effects. Transport in Porous Media, 10, 153–169.

Auriault J.L., Boutin C., 1994. Deformable porous media with double porosity III: Acoustics. Transport in Porous Media, 14, 143–162.

Bachu S., 2008. CO2 storage in geological media: Role, means, status and barriers to deployment. Progress in Energy and Combustion Science, 34, 254–273. https://doi.org/10.1016/j.pecs.2007.10.001.

Blum, A.L., Langley, P., 1997. Selection of relevant features and examples in machine learning. Artificial intelligence 97, 245–271.

Borujeni A.T., Lane N.M., Thompson K., Tyagi M., 2013. Effects of image resolution and numerical resolution on computed permeability of consolidated packing using LB and FEM pore-scale simulations. Computers & Fluids, 88, 753–763.

Brunton S.L., Noack B.R., Koumoutsakos P., 2020. Machine Learning for Fluid Mechanics. Annu. Rev. Fluid Mech, 52, 477–508. https://doi.org/10.1146/annurev-fluid-010719-060214.

Burman E., Hansbo P., 2007. A unified stabilized method for Stokes' and Darcy's equations. Journal of Computational and Applied Mathematics, 198, 35–51.

Chen T., Guestrin C., 2016. Xgboost: A scalable tree boosting system, in: Proceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining, 785–794.

Correa M.R., Loula A.F.D., 2009. A unified mixed formulation naturally coupling Stokes and Darcy flows. Computer Methods in Applied Mechanics and Engineering, 198, 2710–2722.

de Borst R., 2017. Fluid flow in fractured and fracturing porous media: A unified view. Mechanics Research Communications, Multi-Physics of Solids at Fracture, 80, 47–57. https://doi.org/10.1016/j.mechrescom.2016.05.004.

Dietrich P., Helmig R., Sauter M., Hötzl H., Köngeter J., Teutsch G., 2005. Flow and transport in fractured porous media. Springer Berlin, Heidelberg. http://doi.org/10.1007/b138453.

Erofeev A., Orlov D., Ryzhov A., Koroteev D., 2019. Prediction of Porosity and Permeability Alteration Based on Machine Learning Algorithms. Transp Porous Med, 128, 677–700. https://doi.org/10.1007/s11242-019-01265-3.

Ewing R.E., 1983. 1. Problems Arising in the Modeling of Processes for Hydrocarbon Recovery, in: Ewing, R.E. (Ed.), The Mathematics of Reservoir Simulation. Society for Industrial and Applied Mathematics, 3–34. https://doi.org/10.1137/1.9781611971071.ch1.

Flah M., Nunez I., Ben Chaabene W., Nehdi M.L., 2021. Machine learning algorithms in civil structural health monitoring: a systematic review. Archives of Computational Methods in Engineering, 28, 2621–2643.

Grassl P., 2009. A lattice approach to model flow in cracked concrete. Cement and Concrete Composites, 31, 454–460.

Hasanipanah M., Abdullah R.A., Iqbal M., Ly H.-B., 2023. Predicting Rubberized Concrete Compressive Strength Using Machine Learning: A Feature Importance and Partial Dependence Analysis. Journal of Science and Transport Technology, 3, 27–44.

Herzig J.P., Leclerc D.M., Goff P.Le., 1970. Flow of Suspensions through Porous Media Application to Deep Filtration. Industrial & Engineering Chemistry, 62, 8–35. https://doi.org/10.1021/ie50725a003.

Huppert H.E., Neufeld J.A., 2014. The Fluid Mechanics of Carbon Dioxide Sequestration. Annu. Rev. Fluid Mech, 46, 255–272. https://doi.org/10.1146/annurev-fluid-011212-140627.

Khalid Awan U., Tischbein B., Martius C., 2015. Simulating Groundwater Dynamics Using Feflow‐3D Groundwater Model Under Complex Irrigation and Drainage Network of Dryland Ecosystems of Central Asia. Irrigation and Drainage, 64, 283–296. https://doi.org/10.1002/ird.1897.

Li X., Li D., Xu Y., 2019. Modeling the effects of microcracks on water permeability of concrete using 3D discrete crack network. Composite Structures, 210, 262–273.

Ly H.-B., Asteris P.G., Pham T.B., 2020. Accuracy assessment of extreme learning machine in predicting soil compression coefficient. Vietnam Journal of Earth Sciences, 42(3), 228–336. https://doi.org/10.15625/0866-7187/42/3/14999.

Ly H.-B., Le Droumaguet B., Monchiet V., Grande D., 2015. Designing and modeling doubly porous polymeric materials. The European Physical Journal Special Topics, 224, 1689–1706.

Ly H.B., Monchiet V., Grande D., 2016. Computation of permeability with Fast Fourier Transform from 3-D digital images of porous microstructures. International Journal of Numerical Methods for Heat & Fluid Flow 26(5), 1328–1345.

Ly H.-B., Nguyen T.-A., 2024. Machine learning-driven innovations in green eco-environmental rubberized concrete design towards sustainability. Materials Today Communications, 39, 108551.

Ly H.-B., Nguyen T.-A., Tran V.Q., 2021. Development of deep neural network model to predict the compressive strength of rubber concrete. Construction and Building Materials 301, 124081.

Ly H.-B., Phan V.-H., Monchiet V., Nguyen H.-L., Nguyen-Ngoc L., 2022. Numerical investigation of macroscopic permeability of biporous solids with elliptic vugs. Theoretical and Computational Fluid Dynamics, 36, 689–704.

Mezhoud S., Monchiet V., Bornert M., Grande D., 2020. Computation of macroscopic permeability of doubly porous media with FFT based numerical homogenization method. European Journal of Mechanics-B/Fluids, 83, 141–155.

Michel J.-C., Moulinec H., Suquet P., 1999. Effective properties of composite materials with periodic microstructure: a computational approach. Computer Methods in Applied Mechanics and Engineering, 172, 109–143.

Monchiet V., Bonnet G., Lauriat G., 2009. A FFT-based method to compute the permeability induced by a Stokes slip flow through a porous medium. Comptes Rendus Mécanique, 337, 192–197.

Monchiet V., Ly H.-B., Grande D., 2019. Macroscopic permeability of doubly porous materials with cylindrical and spherical macropores. Meccanica, 54, 1583–1596.

Morgan D., Jacobs R., 2020. Opportunities and Challenges for Machine Learning in Materials Science. Annu. Rev. Mater. Res., 50, 71–103. https://doi.org/10.1146/annurev-matsci-070218-010015.

Moulinec H., Suquet P., 1998. A numerical method for computing the overall response of nonlinear composites with complex microstructure. Computer Methods in Applied Echanics and Engineering, 157, 69–94.

Nguyen T.-A., Ly H.-B., Jaafario A., Pham B.T., 2020. Estimation offriction capacity of driven piles in clay using. Vietnam Journal of Earth Sciences, 42(3), 265–275. https://doi.org/10.15625/0866-7187/42/3/15182.

Nguyen T.-K., Monchiet V., Bonnet G., 2013. A Fourier based numerical method for computing the dynamic permeability of periodic porous media. European Journal of Mechanics-B/Fluids, 37, 90–98.

Nhu V.-H., Thai B.P., Tien D.B., 2023. A novel swarm intelligence optimized extreme learning machine for predicting soil shear strength: A case study at Hoa Vuong new urban project (Vietnam). Vietnam Journal of Earth Sciences, 45(2), 219–237. https://doi.org/10.15625/2615-9783/18338.

Pan C., Hilpert M., Miller C.T., 2004. Lattice-Boltzmann simulation of two-phase flow in porous media. Water Resources Research, 40, W01501. Doi: 10.1029/2003WR002120.

Phan V.-H., Ly H.-B., 2024. RIME-RF-RIME: A novel machine learning approach with SHAP analysis for predicting macroscopic permeability of porous media. Journal of Science and Transport Technology, 58–71.

Phoon K.-K., Zhang W., 2023. Future of machine learning in geotechnics. Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards, 17, 7–22. https://doi.org/10.1080/17499518.2022.2087884.

Phung B.-N., Le T.-H., Nguyen M.-K., Nguyen T.-A., Ly H.-B., 2023. Practical Numerical Tool for Marshall Stability Prediction Based On Machine Learning: An Application for Asphalt Concrete Containing Basalt Fiber. Journal of Science and Transport Technology, 27–45.

Ren F., Hu H., Tang H., 2020. Active flow control using machine learning: A brief review. J Hydrodyn, 32, 247–253. https://doi.org/10.1007/s42241-020-0026-0.

Renard P., De Marsily G., 1997. Calculating equivalent permeability: a review. Advances in Water Resources, 20, 253–278.

Sander R., Pan Z., Connell L.D., 2017. Laboratory measurement of low permeability unconventional gas reservoir rocks: A review of experimental methods. Journal of Natural Gas Science and Engineering, 37, 248–279.

Srinivasan G., Hyman J.D., Osthus D.A., Moore B.A., O’Malley D., Karra S., Rougier E., Hagberg A.A., Hunter A., Viswanathan H.S., 2018. Quantifying topological uncertainty in fractured systems using graph theory and machine learning. Scientific Reports, 8, 11665.

Thai H.-T., 2022. Machine learning for structural engineering: A state-of-the-art review, in: Structures. Elsevier, 448–491.

Tian J., Qi C., Sun Y., Yaseen Z.M., Pham B.T., 2021. Permeability prediction of porous media using a combination of computational fluid dynamics and hybrid machine learning methods. Engineering with Computers, 37, 3455–3471. https://doi.org/10.1007/s00366-020-01012-z.

Vadyala S.R., Betgeri S.N., Matthews J.C., Matthews E., 2022. A review of physics-based machine learning in civil engineering. Results in Engineering, 13, 100316.

Van Phong T., Ly H.-B., Trinh P.T., Prakash I., BTJVJOES P., 2020. Landslide susceptibility mapping using Forest by Penalizing Attributes (FPA) algorithm based machine learning approach. Vietnam J. Earth Sci., 42(3), 237–246. https://doi.org/10.15625/0866-7187/42/3/15047.

Wang C.Y., 2001. Stokes flow through a rectangular array of circular cylinders. Fluid Dynamics Research, 29, 65–80. https://doi.org/10.1016/S0169-5983(01)00013-2.

Wang C.Y., 2003. Stokes slip flow through square and triangular arrays of circular cylinders. Fluid Dynamics Research, 32, 233–246. https://doi.org/10.1016/S0169-5983(03)00049-2.

Wei J., Chu X., Sun X., Xu K., Deng H., Chen J., Wei Z., Lei M., 2019. Machine learning in materials science. InfoMat, 1, 338–358. https://doi.org/10.1002/inf2.12028.

Xuan B.T., Thuy D.L., Van P.T., Hong N.V., Van Le H., Nguyen D.D., Prakash I., Thanh T.P., Thai B.B., 2024. Groundwater potential zoning using Logistics Model Trees based novel ensemble machine learning model. Vietnam Journal of Earth Sciences, 46(2), 272–281. https://doi.org/10.15625/2615-9783/20316.

Yasuhara H., Elsworth D., 2006. A numerical model simulating reactive transport and evolution of fracture permeability. Int. J. Numer. Anal.

Meth. Geomech, 30, 1039–1062. https://doi.org/10.1002/nag.513.

Zhao S., Zhang T., Ma S., Wang M., 2023. Seahorse optimizer: a novel nature-inspired meta-heuristic for global optimization problems. Appl Intell, 53, 11833–11860. https://doi.org/10.1007/s10489-022-03994-3.

Zhou H., Liang X., Wang Z., Zhang X., Xing F., 2017. Bond deterioration of corroded steel in two different concrete mixes. Struct. Eng. Mech, 63, 725–734.