Abstract
Flow, transport, mechanical, and fracture properties of porous media depend on their morphology and are usually estimated by experimental and/or computational methods. The precision of the computational approaches depends on the accuracy of the model that represents the morphology. If high accuracy is required, the computations and even experiments can be quite time-consuming. At the same time, linking the morphology directly to the permeability, as well as other important flow and transport properties, has been a long-standing problem. In this paper, we develop a new network that utilizes a deep learning (DL) algorithm to link the morphology of porous media to their permeability. The network is neither a purely traditional artificial neural network (ANN), nor is it a purely DL algorithm, but, rather, it is a hybrid of both. The input data include three-dimensional images of sandstones, hundreds of their stochastic realizations generated by a reconstruction method, and synthetic unconsolidated porous media produced by a Boolean method. To develop the network, we first extract important features of the images using a DL algorithm and then feed them to an ANN to estimate the permeabilities. We demonstrate that the network is successfully trained, such that it can develop accurate correlations between the morphology of porous media and their effective permeability. The high accuracy of the network is demonstrated by its predictions for the permeability of a variety of porous media.
Similar content being viewed by others
References
Adler, P.M., Jacquin, C.G., Quiblier, J.A.: Flow in simulated porous media. Int. J. Multiph. Flow. 16, 691 (1990)
Alpaydin, E.: Introduction to Machine Learning, 3rd edn. MIT Press, Cambridge (2016)
Andreä, H., Combaret, N., Dvorkin, J., Glatt, E., Han, J., Kabel, M., Keehm, Y., Krzikalla, F., Lee, M., Madonna, C., Marsh, M., Mukerji, T., Saenger, E.H., Sain, R., Saxena, N., Ricker, S., Wiegmann, A., Zhan, X.: Digital rock physics benchmarks—Part I: imaging and segmentation. Comput. Geosci. 50, 25 (2013)
Aramideh, S., Vlachos, P.P., Ardekani, A.M.: Pore-scale statistics of flow and transport through porous media. Phys. Rev. E 98, 013104 (2018)
Arns, C.H., Knackstedt, M.A., Pinczewski, W.M., Lindquist, W.B.: Accurate estimation of transport properties from microtomographic images. Geophys. Res. Lett. 28, 3361 (2001)
Arns, C.H., Knackstedt, M.A., Martys, N.S.: Cross-property correlations and permeability estimation in sandstone. Phys. Rev. E. 72, 046304 (2005)
Banavar, J.R., Johnson, D.L.: Characteristic pore sizes and transport in porous media. Phys. Rev. B 35, 7283 (1987)
Baruchel, J., Bleuet, P., Bravin, A., Coan, P., Lima, E., Madsen, A., Ludwig, W., Pernot, P., Susini, J.: Advances in synchrotron hard X-ray based imaging. Comptes Rendus Physique 9, 624 (2008)
Bengio, Y.: Learning Deep Architectures for AI. Now Publishers, Hanover (2009)
Blunt, M.J.: Multiphase Flow in Permeable Media. Cambridge University Press, Cambridge (2017)
Brandon, D., Kaplan, W.D.: Microstructural Characterization of Materials. Wiley, New York (2013)
Caruana, R., Lawrence, S.: Overfitting in neural nets: backpropagation, conjugate gradient, and early stopping. Adv. Neural Inf. Process. Syst. 402(408), 13 (2001)
Chapelle, O., Scholkopf, B., Zien, A. (eds.): Semi-supervised Learning. In: IEEE Transactions on Neural Networks, vol. 20, p. 542. IEEE (2009)
Chen, X.W., Xiaotong, L.: Big data deep learning: challenges and perspectives. IEEE Access 2, 514 (2014)
Chen, S., Kirubanandham, A., Chawla, N., Jiao, Y.: Stochastic multi-scale reconstruction of 3D microstructure consisting of polycrystalline grains and second-phase particles from 2D micrographs. Metall. Mater. Trans. A 47, 1440 (2016)
Daigle, H.: Application of critical path analysis for permeability prediction in natural porous media. Adv. Water Resour. 96, 43 (2016)
David, C., Gueguen, Y., Pampoukis, G.: Effective medium theory and network theory applied to the transport properties of rock. J. Geophys. Res. 95(B5), 6993 (1990)
Deng, L., Dong, Y.: Deep learning: methods and applications. Found. Trends Signal Process. 7, 197 (2014)
Devroye, L.: Non-uniform Random Variate Generation. Springer, Berlin (2006)
Doyen, P.M.: Permeability, conductivity, and pore geometry of sandstone. J. Geophys. Res. 93(B7), 7729 (1988)
Ghanbarian, B., Javadpour, F.: Upscaling pore pressure-dependent gas permeability in shales. J. Geophys. Res. Solid Earth 122, 2541 (2017)
Ghanbarian, B., Torres-Verdín, C., Skaggs, T.H.: Quantifying tight-gas sandstone permeability via critical path analysis. Adv. Water Resour. 92, 316 (2016)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)
Hamzehpour, H., Rasaei, M.R., Sahimi, M.: Development of optimal models of porous media by combining static and dynamic data: the permeability and porosity distributions. Phys. Rev. E 75, 056311 (2007)
Jiang, Z., van Dijke, M.I.J., Sorbie, K.S., Couples, G.D.: Representation of multiscale heterogeneity via multiscale pore networks. Water Resour. Res. 49, 5437 (2013)
Jiao, Y., Stillinger, F.H., Torquato, S.: A superior descriptor of random textures and its predictive capacity. Proc. Natl. Acad. Sci. USA 106, 17634 (2009)
Jiao, Y., Padilla, E., Chawla, N.: Modeling and predicting microstructure evolution in lead/tin alloy via correlation functions and stochastic material reconstruction. Acta Mater. 61, 3370 (2013)
Johnson, M.E.: Multivariate Statistical Simulation: A Guide to Selecting and Generating Continuous Multivariate Distributions. Wiley, New York (2013)
Johnson, D.L., Koplik, J., Schwartz, L.M.: New pore-size parameter characterizing transport in porous media. Phys. Rev. Lett. 57, 2564 (1986)
Kak, A.C., Slaney, M.S.: Principles of Computerized Tomographic Imaging. IEEE Press, New York (1988)
Kamrava, S., Tahmasebi, P., Sahimi, M.: Enhancing images of shale formations by a hybrid stochastic and deep learning algorithm. Neural Networks 118, 310 (2019)
Karimpouli, S., Tahmasebi, P.: Image-based velocity estimation of rock using convolutional neural networks. Neural Netw. 111, 89–97 (2019)
Karimpouli, S., Tahmasebi, P., Saenger, E.H.: Coal cleat/fracture segmentation using convolutional neural networks. Nat. Resour. Res. (2019). https://doi.org/10.1007/s11053-019-09536-y
Katz, A.J., Thompson, A.H.: Quantitative prediction of permeability in porous rock. Phys. Rev. B 34, 8179 (1986)
Katz, A.J., Thompson, A.H.: Prediction of rock electrical conductivity from mercury injection measurements. J. Geophys. Res. B 92, 599 (1987)
Kim, K.G.: Deep learning. Health Inform. Res. 22, 351 (2016)
Kinney, J.H., Nichols, M.C.: X-ray tomographic microscopy (XTM) using synchrotron radiation. Annu. Rev. Mater. Sci. 22, 121 (1992)
Koplik, J., Lin, C., Vermette, M.: Conductivity and permeability from microgeometry. J. Appl. Phys. 56, 3127 (1984)
Lecun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436 (2015)
Maturana, D., Scherer, S.: 3D convolutional neural networks for landing zone detection from LiDAR. In: IEEE International Conference on Robotics and Automation, IEEE (2015)
Mosser, L., Dubrule, O., Blunt, M.J.: Reconstruction of three-dimensional porous media using generative adversarial neural networks. Phys. Rev. E 96, 043309 (2017)
Mosser, L., Dubrule, O., Blunt, M.J.: Stochastic reconstruction of an oolitic limestone by generative adversarial networks. Transp. Porous Media 125, 81 (2018)
Mostaghimi, P., Blunt, M.J., Bijeljic, B.: Computations of absolute permeability on micro-CT images. Math. Geosci. 45, 103 (2013)
Mourzenko, V.V., Thovert, J.F., Adler, P.M.: Trace analysis for fracture networks with anisotropic orientations and heterogeneous distributions. Phys. Rev. E 83, 031104 (2011)
Mukhopadhyay, S., Sahimi, M.: Calculation of the effective permeabilities of field-scale porous media. Chem. Eng. Sci. 55, 4495 (2000)
Nielsen, M.A.: Neural networks and deep learning (2015). http://static.latexstudio.net/article/2018/ 0912/neuralnetworksanddeeplearning.pdf
Okabe, H., Blunt, M.J.: Prediction of permeability for porous media reconstructed using multiple-point statistics. Phys. Rev. E 70, 066135 (2004)
Prodanović, M., Mehmani, A., Sheppard, A.P.: Imaged-based multiscale network modelling of microporosity in carbonates. Geol. Soc. Lond. Spec. Publ. 406, 95–113 (2015)
Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv:1511.06434v2 [cs.LG] (7 Jan. 2016)
Remy, N., Alexandre, B., Jianbing, W.: Applied Geostatistics with SGeMS: A User’s Guide. Cambridge University Press, London (2009)
Revil, A., Cathles, L.M.: Permeability of shaly sands. Water Resour. Res. 35, 651 (1999)
Richesson, S., Sahimi, M.: Hertz–Mindlin theory of contacting grains and the effective-medium approximation for the permeability of deforming porous media. Geophys. Res. Lett. 46, 8034 (2019)
Ruder, S.: An overview of gradient descent optimization algorithms. arXiv:1609.04747v2 (2017)
Sahimi, M.: Heterogeneous Materials I. Springer, New York (2003)
Sahimi, M.: Flow and Transport in Porous Media and Fractured Rock, 2nd edn. Wiley-VCH, Weinheim (2011)
Schittenkopf, C., Deco, G., Brauer, W.: Two strategies to avoid overfitting in feedforward networks. Neural Netw. 10, 505 (1997)
Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85 (2015)
Skaggs, T.H.: Assessment of critical path analyses of the relationship between permeability and electrical conductivity of pore networks. Adv. Water Resour. 34, 1335 (2011)
Sola, J., Sevilla, J.: Importance of input data normalization for the application of neural networks to complex industrial problems. IEEE Trans. Nucl. Sci. 44, 1464 (1997)
Srivastava, N., Hinton, G., Krizhevsky, A., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929 (2014)
Tahmasebi, P., Kamrava, S.: Rapid multiscale modeling of flow in porous media. Phys. Rev. E 98, 052901 (2018)
Tahmasebi, P., Sahimi, M.: Reconstruction of three-dimensional porous media using a single thin section. Phys. Rev. E 85, 066709 (2012)
Tahmasebi, P., Sahimi, M.: Cross-correlation function for accurate reconstruction of heterogeneous media. Phys. Rev. Lett. 110, 078002 (2013)
Tahmasebi, P., Sahimi, M.: Enhancing multiple-point geostatistical modeling: 1. Graph theory and pattern adjustment. Water Resour. Res. 52, 2074 (2016a)
Tahmasebi, P., Sahimi, M.: Enhancing multiple-point geostatistical modeling: 2. Iterative simulation and multiple distance function. Water Resour. Res. 52, 2099 (2016b)
Tahmasebi, P., Sahimi, M., Caers, J.: MS-CCSIM: accelerating pattern-based geostatistical simulation of categorical variables using a multi-scale search in Fourier space. Comput. Geosci. 67, 75 (2014)
Tahmasebi, P., Javadpour, F., Sahimi, M.: Multiscale and multiresolution modeling of shales and their flow and morphological properties. Sci. Rep. 5, 16373 (2015)
Tahmasebi, P., Javadpour, F., Sahimi, M.: Data mining and machine learning for identifying sweet spots in shale reservoirs. Expert Syst. Appl. 88, 435 (2017)
Thompson, A.H.: Fractals in rock physics. Annu. Rev. Earth Planet. Sci. 19, 237 (1991)
Thovert, J.F., Yousefian, F., Spanne, P., Jacquin, C.G., Adler, P.M.: Grain reconstruction of porous media: application to a low-porosity Fontainebleau sandstone. Phys. Rev. E 63, 061307 (2001)
van der Linden, J.H., Narsilio, G.A., Tordesillas, A.: Machine learning framework for analysis of transport through complex networks in porous, granular media: a focus on permeability. Phys. Rev. E 94, 022904 (2016)
Wu, Z., Jiang, Y.-G., Wang, J., Pu, J., Xue, X.: Exploring inter-feature and inter-class relationships with deep neural networks for video classification. In: Proceedings of the ACM International Conference on Multimedia - MM14 (2014)
Xu, P., Yu, B.: Developing a new form of permeability and Kozeny–Carman constant for homogeneous porous media by means of fractal geometry. Adv. Water Resour. 31, 74 (2008)
Yadav, N., Yadav, A., Kumar, M.: An Introduction to Neural Network Methods for Differential Equations. Springer, Berlin (2015)
Yang, Z., Yabansu, Y.C., Al-Bahrani, R., Liao, W., Choudhary, A.N., Kalidindi, S.R., Agrawal, A.: Deep learning approaches for mining structure–property linkages in high contrast composites from simulation datasets. Comput. Mater. Sci. 151, 278 (2018)
Yang, Z., Yabansu, Y.C., Jha, D., Liao, W., Choudhary, A.N., Kalidindi, S.R., Agrawal, A.: Establishing structure-property localization linkages for elastic deformation of three-dimensional high contrast composites using deep learning approaches. Acta Mater. 166, 335 (2019)
Yeong, C.L.Y., Torquato, S.: Reconstructing random media. Phys. Rev. E 57, 495 (1998a)
Yeong, C.L.Y., Torquato, S.: Reconstructing random media. II. Three-dimensional media from two-dimensional cuts. Phys. Rev. E 58, 224 (1998b)
Zachary, C.E., Torquato, S.: Improved reconstructions of random media using dilation and erosion processes. Phys. Rev. E 84, 056102 (2011)
Acknowledgements
Work at USC was supported in part by the Petroleum Research Fund, administered by the American Chemical Society. We thank an anonymous reviewer whose critical comments helped us improve the manuscript.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Kamrava, S., Tahmasebi, P. & Sahimi, M. Linking Morphology of Porous Media to Their Macroscopic Permeability by Deep Learning. Transp Porous Med 131, 427–448 (2020). https://doi.org/10.1007/s11242-019-01352-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11242-019-01352-5