Upscaling Permeability Using Multiscale X‐Ray‐CT Images With Digital Rock Modeling and Deep Learning Techniques

This study presents a workflow to predict the upscaled absolute permeability of the rock core direct from CT images whose resolution is not sufficient to allow direct pore‐scale permeability computation. This workflow exploits the deep learning technique with the data of raw CT images of rocks and their corresponding permeability value obtained by performing flow simulation on high‐resolution CT images. The permeability map of a much larger region in the rock core is predicted by the trained neural network. Finally, the upscaled permeability of the entire rock core is calculated by the Darcy flow solver, and the results showed a good agreement with the experiment data. This proposed deep learning based upscaling method allows estimating the permeability of large‐scale core samples while preserving the effects of fine‐scale pore structure variations due to the local heterogeneity.

[1]  A. Rabinovich,et al.  Modeling imbibition coreflooding in heterogeneous cores with sub-core scale hysteresis , 2022, Advances in Water Resources.

[2]  D. Varagnolo,et al.  Automated porosity estimation using CT-scans of extracted core data , 2022, Computational Geosciences.

[3]  T. Hashida,et al.  Data-Driven Geothermal Reservoir Modeling: Estimating Permeability Distributions by Machine Learning , 2022, Geosciences.

[4]  O. Ardakani,et al.  Reconstructing high fidelity digital rock images using deep convolutional neural networks , 2022, Scientific Reports.

[5]  Fei Jiang,et al.  A coupled LBM-DEM method for simulating the multiphase fluid-solid interaction problem , 2022, J. Comput. Phys..

[6]  Nan You,et al.  3D Carbonate Digital Rock Reconstruction Using Progressive Growing GAN , 2021, Journal of Geophysical Research: Solid Earth.

[7]  Ying Da Wang,et al.  Deep learning in pore scale imaging and modeling , 2021 .

[8]  Jian Hou,et al.  Prediction of three-phase relative permeabilities of Berea sandstone using lattice Boltzmann method , 2021, Physics of Fluids.

[9]  Ying Da Wang,et al.  Flow-Based Characterization of Digital Rock Images Using Deep Learning , 2021 .

[10]  Xian Chen,et al.  A GPU-accelerated fluid-structure-interaction solver developed by coupling finite element and lattice Boltzmann methods , 2021, Comput. Phys. Commun..

[11]  E. Anto-Darkwah,et al.  An improved procedure for sub-core property characterization using data from multiple coreflooding experiments , 2021, International Journal of Greenhouse Gas Control.

[12]  S. Geiger,et al.  Upscaling the porosity–permeability relationship of a microporous carbonate for Darcy-scale flow with machine learning , 2021, Scientific Reports.

[13]  Jin Hong,et al.  Rapid estimation of permeability from digital rock using 3D convolutional neural network , 2020, Computational Geosciences.

[14]  Hyuck-Jin Park,et al.  Migration characteristics of supercritical CO2 microbubble flow in the Berea sandstone revealed by voxel-based X-ray computed tomography imaging analysis , 2020 .

[15]  Duo Xu,et al.  PoreFlow-Net: A 3D convolutional neural network to predict fluid flow through porous media , 2020, Advances in Water Resources.

[16]  J. Sarout,et al.  Experimental Reactivation of Shear‐fractured Berea and Boise Sandstones by Brine or Liquid CO2 Injection at Depth , 2020, Journal of Geophysical Research: Solid Earth.

[17]  M. Deo,et al.  Pore system characterization of organic-rich shales using nanoscale-resolution 3D imaging , 2019 .

[18]  Peyman Mostaghimi,et al.  Enhancing Resolution of Digital Rock Images with Super Resolution Convolutional Neural Networks , 2019, Journal of Petroleum Science and Engineering.

[19]  E. Boek,et al.  Image-based simulations of absolute permeability with massively parallel pseudo-compressible stabilised finite element solver , 2019, Computational Geosciences.

[20]  Arash Rabbani,et al.  Hybrid pore-network and lattice-Boltzmann permeability modelling accelerated by machine learning , 2019, Advances in Water Resources.

[21]  Alexei Botchkarev,et al.  Performance Metrics (Error Measures) in Machine Learning Regression, Forecasting and Prognostics: Properties and Typology , 2018, Interdisciplinary Journal of Information, Knowledge, and Management.

[22]  M. Myers,et al.  Exporting Petrophysical Properties of Sandstones From Thin Section Image Analysis , 2018 .

[23]  F. Jiang,et al.  Estimation of three‐phase relative permeability by simulating fluid dynamics directly on rock‐microstructure images , 2017 .

[24]  E. Boek,et al.  Micro-computed tomography pore-scale study of flow in porous media: Effect of voxel resolution , 2016 .

[25]  Adrian Sheppard,et al.  Mapping permeability in low‐resolution micro‐CT images: A multiscale statistical approach , 2016 .

[26]  G. Debenest,et al.  A Comparison of Various Methods for the Numerical Evaluation of Porous Media Permeability Tensors from Pore-Scale Geometry , 2016, Mathematical Geosciences.

[27]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[28]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  Takeshi Tsuji,et al.  Impact of interfacial tension on residual CO2 clusters in porous sandstone , 2015 .

[30]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[31]  Takeshi Tsuji,et al.  Changes in pore geometry and relative permeability caused by carbonate precipitation in porous media. , 2014, Physical review. E, Statistical, nonlinear, and soft matter physics.

[32]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[33]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[34]  Changhong Hu,et al.  Elucidating the Role of Interfacial Tension for Hydrological Properties of Two-Phase Flow in Natural Sandstone by an Improved Lattice Boltzmann Method , 2014, Transport in Porous Media.

[35]  Christoph H. Arns,et al.  Permeability Upscaling for Carbonates From the Pore Scale by Use of Multiscale X-Ray-CT Images , 2013 .

[36]  Jianhui Yang,et al.  A comparison study of multi-component Lattice Boltzmann models for flow in porous media applications , 2013, Comput. Math. Appl..

[37]  Ali Q. Raeini,et al.  Modelling two-phase flow in porous media at the pore scale using the volume-of-fluid method , 2012, J. Comput. Phys..

[38]  Zhijie Xu,et al.  Homogenization and Upscaling for Diffusion, Heat Conduction, and Wave Propagation in Heterogeneous Materials , 2012 .

[39]  S. Benson,et al.  Modeling Permeability Distributions in a Sandstone Core for History Matching Coreflood Experiments , 2011 .

[40]  Hiroki Sone,et al.  Stress-dependence of the permeability and porosity of sandstone and shale from TCDP Hole-A , 2010 .

[41]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[42]  Edo S. Boek,et al.  Lattice-Boltzmann studies of fluid flow in porous media with realistic rock geometries , 2010, Comput. Math. Appl..

[43]  Ruben Juanes,et al.  Impact of relative permeability hysteresis on geological CO2 storage , 2006 .

[44]  Cass T. Miller,et al.  An evaluation of lattice Boltzmann schemes for porous medium flow simulation , 2006 .

[45]  X. Yuan,et al.  Kinetic theory representation of hydrodynamics: a way beyond the Navier–Stokes equation , 2006, Journal of Fluid Mechanics.

[46]  A. Costa,et al.  Permeability‐porosity relationship: A reexamination of the Kozeny‐Carman equation based on a fractal pore‐space geometry assumption , 2006 .

[47]  Christoph H. Arns,et al.  Accurate estimation of transport properties from microtomographic images , 2001 .

[48]  M. Blunt.  Flow in porous media — pore-network models and multiphase flow , 2001 .

[49]  Christoph Clauser,et al.  Permeability prediction based on fractal pore‐space geometry , 1999 .

[50]  P. Carman.  Fluid flow through granular beds , 1997 .

[51]  Martys,et al.  Universal scaling of fluid permeability for sphere packings. , 1994, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[52]  J. W. Martin,et al.  Pore geometry and transport properties of Fontainebleau sandstone , 1993 .

[53]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[54]  H. J. Ramey,et al.  The Effect of Temperature on Relative and Absolute Permeability of Sandstones , 1975 .

[55]  P. J. Huber.  Robust Estimation of a Location Parameter , 1964 .

[56]  T. Tsuji,et al.  Influence of pore space heterogeneity on mineral dissolution and permeability evolution investigated using lattice Boltzmann method , 2022 .

[57]  Haihu Liu,et al.  Deformation and breakup of a compound droplet in three-dimensional oscillatory shear flow , 2021 .

[58]  E. Boek,et al.  Investigation of viscous coupling effects in three-phase flow by lattice Boltzmann direct simulation and machine learning technique , 2021 .

[59]  M. Blunt,et al.  Pore-scale imaging and modelling , 2013 .

[60]  Subir K. Sanyal,et al.  FUTURE OF GEOTHERMAL ENERGY , 2010 .

[61]  Boming Yu,et al.  Developing a new form of permeability and Kozeny-Carman constant for homogeneous porous media by means of fractal geometry , 2008 .

[62]  Kurt M. Strack,et al.  Society of Exploration Geophysicists , 2007 .

[63]  Christoph H. Arns,et al.  Linear elastic properties of granular rocks derived from X‐ray‐CT images , 2007 .

[64]  S. Youssef,et al.  High Resolution CT And Pore-Network Models To Assess Petrophysical Properties Of Homogeneous And Heterogeneous Carbonates , 2007 .

[65]  Cordelia Schmid,et al.  IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2004, Washington, DC, USA, June 27 - July 2, 2004 , 2004, CVPR Workshops.

[66]  P. Worthington.  The effect of scale on the petrophysical estimation of intergranular permeability , 2004 .

[67]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[68]  B. Shizgal,et al.  Generalized Lattice-Boltzmann Equations , 1994 .

[69]  Frederick R. Forst,et al.  On robust estimation of the location parameter , 1980 .