Skip to main content
SpringerLink
Log in

Porous Structure Reconstruction Using Convolutional Neural Networks

Mathematical Geosciences volume 50, pages 781–799 (2018)Cite this article

Abstract

The three-dimensional high-resolution imaging of rock samples is the basis for pore-scale characterization of reservoirs. Micro X-ray computed tomography (µ-CT) is considered the most direct means of obtaining the three-dimensional inner structure of porous media without deconstruction. The micrometer resolution of µ-CT, however, limits its application in the detection of small structures such as nanochannels, which are critical for fluid transportation. An effective strategy for solving this problem is applying numerical reconstruction methods to improve the resolution of the µ-CT images. In this paper, a convolutional neural network reconstruction method is introduced to reconstruct high-resolution porous structures based on low-resolution µ-CT images and high-resolution scanning electron microscope (SEM) images. The proposed method involves four steps. First, a three-dimensional low-resolution tomographic image of a rock sample is obtained by µ-CT scanning. Next, one or more sections in the rock sample are selected for scanning by SEM to obtain high-resolution two-dimensional images. The high-resolution segmented SEM images and their corresponding low-resolution µ-CT slices are then applied to train a convolutional neural network (CNN) model. Finally, the trained CNN model is used to reconstruct the entire low-resolution three-dimensional µ-CT image. Because the SEM images are segmented and have a higher resolution than the µ-CT image, this algorithm integrates the super-resolution and segmentation processes. The input data are low-resolution µ-CT images, and the output data are high-resolution segmented porous structures. The experimental results show that the proposed method can achieve state-of-the-art performance.

This is a preview of subscription content, access via your institution.

Access options

Buy single article

Instant access to the full article PDF.

USD 39.95

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

References

  • Adler PM, Jacquin CG, Quiblier JA (1990) Flow in simulated porous media. Int J Multiph Flow 16:691–712. https://doi.org/10.1016/0301-9322(90)90025-E

    Article  Google Scholar 

  • Adler PM, Jacquin CG, Thovert JF (1992) The formation factor of reconstructed porous media. Water Resour Res 28:1571–1576. https://doi.org/10.1029/92WR00059

    Article  Google Scholar 

  • Arns CH, Knackstedt MA, Pinczewski WV, Mecke KR (2001) Euler-Poincaré characteristics of classes of disordered media. Phys Rev E 63:031112

    Article  Google Scholar 

  • Arns CH, Knackstedt MA, Mecke KR (2004) Characterisation of irregular spatial structures by parallel sets and integral geometric measures. Colloids Surf A Physicochem Eng Aspects 241:351–372. https://doi.org/10.1016/j.colsurfa.2004.04.034

    Article  Google Scholar 

  • Arns CH, Knackstedt MA, Mecke K (2010) 3D structural analysis: sensitivity of Minkowski functionals. J Microsc 240:181–196. https://doi.org/10.1111/j.1365-2818.2010.03395.x

    Article  Google Scholar 

  • Biswal B, Hilfer R (1999) Microstructure analysis of reconstructed porous media. Phys A Stat Mech Appl 266:307–311

    Article  Google Scholar 

  • Bryant S, Blunt M (1992) Prediction of relative permeability in simple porous media. Phys Rev A 46:2004–2011

    Article  Google Scholar 

  • Čapek P, Hejtmánek V, Brabec L, Zikánová A, Kočiřík M (2009) Stochastic reconstruction of particulate media using simulated annealing: improving pore connectivity. Transp Porous Media 76:179–198. https://doi.org/10.1007/s11242-008-9242-8

    Article  Google Scholar 

  • Chaoben D, Shesheng G (2018) Multi-focus image fusion with the all convolutional neural network. Optoelectron Lett 14:71–75

    Article  Google Scholar 

  • Cheong JY, Park IK (2017) Deep CNN-based super-resolution using external and internal examples. IEEE Signal Process Lett 24:1252–1256

    Article  Google Scholar 

  • Coelho D, Thovert JF, Adler PM (1997) Geometrical and transport properties of random packings of spheres and aspherical particles. Phys Rev E 55:1959–1978

    Article  Google Scholar 

  • Comunian A, Renard P, Straubhaar J (2012) 3D multiple-point statistics simulation using 2D training images. Comput Geosci 40:49–65. https://doi.org/10.1016/j.cageo.2011.07.009

    Article  Google Scholar 

  • Deepak AVS, Ghanekar U (2017) RDCN-SR: Integrating regression model with deep convolutional networks for image super-resolution. In: 2017 international conference on intelligent computing and control systems (ICICCS), 15–16 June 2017, pp 623–628. https://doi.org/10.1109/iccons.2017.8250537

  • Deng J, Dong W, Socher R, Li LJ, Kai L, Li F-F (2009) ImageNet: a large-scale hierarchical image database. In: Paper presented at the 2009 IEEE conference on computer vision and pattern recognition, 20–25 June 2009

  • Dong C, Loy CC, He K, Tang X (2016) Image super-resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell 38:295–307. https://doi.org/10.1109/TPAMI.2015.2439281

    Article  Google Scholar 

  • Frederic B, Dominique J (2004) Modelling a food microstructure by random sets. Image Anal Stereol 23:33–44

    Google Scholar 

  • Guo Y, Liu Y, Oerlemans A, Lao S, Wu S, Lew MS (2016) Deep learning for visual understanding: a review. Neurocomputing 187:27–48. https://doi.org/10.1016/j.neucom.2015.09.116

    Article  Google Scholar 

  • Hilfer R (1992) Local-porosity theory for flow in porous media. Phys Rev B 45:7115–7121

    Article  Google Scholar 

  • Hiroshi O (2004) Pore-scale modelling of carbonates. Imperial College London, London

    Google Scholar 

  • Jain V, Seung S (2008) Natural image denoising with convolutional networks. In: Bottou DKaDSaYBaL (ed) Advances in neural information processing systems, 21. Curran Associates, Inc., pp 769–776

  • Jia X, Xu X, Cai B, Guo K (2017) Single image super-resolution using multi-scale convolutional. Neural Netw. ArXiv e-prints 1705

  • Kaiming H, Zhang X, Ren S, Sun J (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37:1904–1916. https://doi.org/10.1109/TPAMI.2015.2389824

    Article  Google Scholar 

  • Krizhevsky A, Sutskever I, Hinton GE (2017) ImageNet classification with deep convolutional neural networks. Commun ACM 60:84–90. https://doi.org/10.1145/3065386

    Article  Google Scholar 

  • Latham J-P, Lu Y, Munjiza A (2001) A random method for simulating loose packs of angular particles using tetrahedra. Géotechnique 51:871–879. https://doi.org/10.1680/geot.2001.51.10.871

    Article  Google Scholar 

  • Latief FDE, Biswal B, Fauzi U, Hilfer R (2010) Continuum reconstruction of the pore scale microstructure for Fontainebleau sandstone. Phys A Stat Mech Appl 389:1607–1618. https://doi.org/10.1016/j.physa.2009.12.006

    Article  Google Scholar 

  • LeCun Y, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W, Jackel LD (1989) Backpropagation applied to handwritten zip code recognition. Neural Comput 1:541–551

    Article  Google Scholar 

  • LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86:2278–2324

    Article  Google Scholar 

  • LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444

    Article  Google Scholar 

  • Liang ZR, Fernandes CP, Magnani FS, Philippi PC (1998) A reconstruction technique for three-dimensional porous media using image analysis and Fourier transforms. J Petrol Sci Eng 21:273–283. https://doi.org/10.1016/S0920-4105(98)00077-1

    Article  Google Scholar 

  • Liu F, Lin G, Shen C (2015) CRF learning with CNN features for image segmentation. Pattern Recogn 48:2983–2992. https://doi.org/10.1016/j.patcog.2015.04.019

    Article  Google Scholar 

  • Liu D, Wang Z, Wen B, Yang J, Han W, Huang TS (2016) Robust Single Image Super-Resolution via Deep Networks With Sparse Prior. IEEE Trans Image Process 25:3194–3207

    Article  Google Scholar 

  • Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Paper presented at the CVPR2015

  • Lucia FJ, Kerans C, Jennings JW Jr (2003) Carbonate reservoir characterization. J Petrol Technol. https://doi.org/10.2118/82071-JPT

    Article  Google Scholar 

  • Manwart C, Torquato S, Hilfer R (2000) Stochastic reconstruction of sandstones. Phys Rev E 62:893–899

    Article  Google Scholar 

  • Mosser L, Dubrule O, Blunt MJ (2017) Reconstruction of three-dimensional porous media using generative adversarial neural networks. Phys Rev E 96:043309

    Article  Google Scholar 

  • Okabe H, Blunt MJ (2004) Prediction of permeability for porous media reconstructed using multiple-point statistics. Phys Rev E 70:066135

    Article  Google Scholar 

  • Okabe H, Blunt M (2007) Pore space reconstruction of vuggy carbonates using microtomography and multiple-point statistics. Water Resour Res 43:179–183

    Article  Google Scholar 

  • ØREN P-E, Bakke S (2002) Process based reconstruction of sandstones and prediction of transport properties. Transp Porous Media 46:311–343. https://doi.org/10.1023/a:1015031122338

    Article  Google Scholar 

  • Ouyang W et al. (2015) DeepID-Net: deformable deep convolutional neural networks for object detection. In: Proceedings of the CVPR

  • Pant LM, Mitra SK, Secanell M (2015) Multigrid hierarchical simulated annealing method for reconstructing heterogeneous media. Phys Rev E 92:063303

    Article  Google Scholar 

  • Quiblier JA (1984) A new three-dimensional modeling technique for studying porous media. J Colloid Interface Sci 98:84–102. https://doi.org/10.1016/0021-9797(84)90481-8

    Article  Google Scholar 

  • Rintoul MD, Torquato S (1997) Reconstruction of the structure of dispersions. J Colloid Interface Sci 186:467–476. https://doi.org/10.1006/jcis.1996.4675

    Article  Google Scholar 

  • Roberts AP (1997) Statistical reconstruction of three-dimensional porous media from two-dimensional images. Phys Rev E 56:3203–3212

    Article  Google Scholar 

  • Roberts AP, Torquato S (1999) Chord-distribution functions of three-dimensional random media: approximate first-passage times of Gaussian processes. Phys Rev E 59:4953–4963

    Article  Google Scholar 

  • Samuel S, Christian L, Horst B (2015) Fast and accurate image upscaling with super-resolution forests. In: Paper presented at the 2015 IEEE conference on computer vision and pattern recognition (CVPR), 7–12 June 2015

  • Spanne P, Thovert JF, Jacquin CJ, Lindquist WB, Jones KW, Adler PM (1994) Synchrotron computed microtomography of porous media: topology and transports. Phys Rev Lett 73:2001–2004

    Article  Google Scholar 

  • Springenberg JT, Dosovitskiy A, Brox T, Riedmiller M (2014) Striving for simplicity: the all convolutional Net. ArXiv e-prints 1412

  • Tahmasebi P, Sahimi M (2016a) Enhancing multiple-point geostatistical modeling: 1. Graph theory and pattern adjustment. Water Resour Res 52:2074–2098. https://doi.org/10.1002/2015WR017806

    Article  Google Scholar 

  • Tahmasebi P, Sahimi M (2016b) Enhancing multiple-point geostatistical modeling: 2. Iterative simulation and multiple distance function. Water Resour Res 52:2099–2122. https://doi.org/10.1002/2015WR017807

    Article  Google Scholar 

  • Tahmasebi P, Javadpour F, Sahimi M (2015) Multiscale and multiresolution modeling of shales and their flow and morphological properties. Sci Rep 5:16373. https://doi.org/10.1038/srep16373

    Article  Google Scholar 

  • Tahmasebi P, Javadpour F, Sahimi M (2016) Stochastic shale permeability matching: three-dimensional characterization and modeling. Int J Coal Geol 165:231–242. https://doi.org/10.1016/j.coal.2016.08.024

    Article  Google Scholar 

  • Tahmasebi P, Sahimi M, Andrade JE (2017) Image-based modeling of granular porous media. Geophys Res Lett 44:4738–4746. https://doi.org/10.1002/2017GL073938

    Article  Google Scholar 

  • Talukdar MS, Torsaeter O, Ioannidis MA, Howard JJ (2002) Stochastic reconstruction of chalk from 2D images. Transp Porous Media 48:101–123. https://doi.org/10.1023/a:1015650705205

    Article  Google Scholar 

  • Wang Y, Rahman SS, Arns CH (2018) Super resolution reconstruction of μ-CT image of rock sample using neighbour embedding algorithm. Phys A Stat Mech Appl 493:177–188

    Article  Google Scholar 

  • Wu K, Nunan N, Crawford JW, Young IM, Ritz K (2004) An efficient Markov chain model for the simulation of heterogeneous soil structure. Soil Sci Soc Am J 68:6

    Article  Google Scholar 

  • Wu K et al (2006) 3D stochastic modelling of heterogeneous porous media—applications to reservoir rocks. Transp Porous Media 65:443–467. https://doi.org/10.1007/s11242-006-0006-z

    Article  Google Scholar 

  • Xuejiao W, Qiuyan T, Lianghao W, Dongxiao L, Ming Z (2015) Deep convolutional architecture for natural image denoising. In: Paper presented at the 2015 international conference on wireless communications & signal processing (WCSP), Nanjing, China

  • Yamanaka J, Kuwashima S, Kurita T (2017) Fast and accurate image super resolution by deep CNN with skip connection and network in network. ArXiv e-prints 1707

  • Yeong CLY, Torquato S (1998a) Reconstructing random media. Phys Rev E 57:495–506

    Article  Google Scholar 

  • Yeong CLY, Torquato S (1998b) Reconstructing random media. II. Three-dimensional media from two-dimensional cuts. Phys Rev E 58:224–233

    Article  Google Scholar 

  • Zeiler MD, Fergus R (2013) Stochastic pooling for regularization of deep convolutional neural networks. ArXiv e-prints 1301

  • Zhang K, Zuo W, Chen Y, Meng D, Zhang L (2017) Beyond a Gaussian Denoiser: residual learning of deep CNN for image denoising. IEEE Trans Image Process 26:3142–3155. https://doi.org/10.1109/TIP.2017.2662206

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Petroleum Engineering, University of New South Wales, Sydney, 2052, Australia

    Yuzhu Wang, Christoph H. Arns & Sheik S. Rahman

  2. Research School of Physics and Engineering, Australian National University, Canberra, 0200, Australia

    Ji-Youn Arns

Authors
  1. Yuzhu Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Christoph H. Arns
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sheik S. Rahman
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ji-Youn Arns
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yuzhu Wang.

Rights and permissions

Reprints and Permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, Y., Arns, C.H., Rahman, S.S. et al. Porous Structure Reconstruction Using Convolutional Neural Networks. Math Geosci 50, 781–799 (2018). https://doi.org/10.1007/s11004-018-9743-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11004-018-9743-0

Keywords

search

Navigation