Slice-to-voxel stochastic reconstructions on porous media with hybrid deep generative model

Abstract Three-dimensional (3D) microstructures are useful for studying the spatial structures and physical properties of porous media. A number of stochastic reconstructions are essential to discover the geometry and topology of the porous media and the its flow behavior. While several deep-learning based generative models have been proposed to deal with the issue, the obstacles about stable training and difficulty in convergence limit the application of these models. To address these problems, a hybrid deep generative model for 3D porous media reconstruction is proposed. The hybrid model is composed of a variant autoencoder (VAE) and a generative adversarial network (GAN). It receives a two-dimensional image as input and generates 3D porous media. The encoder from VAE characterizes the statistical and morphological information of input image and generates a low-dimensional feature vector for generator. Benefiting from the hybrid model, the training becomes more stable and the generative capability is enhanced as well. Furthermore, a simple but useful loss function is used to help improve accuracy. The proposed model is tested on both isotropic and anisotropic porous media. The results show the synthetic realizations have good agreement to the targets on visual inspection, statistical functions and two-phase flow simulation.

[1]  Yang Li,et al.  Reconstruction of three-dimensional heterogeneous media from a single two-dimensional section via co-occurrence correlation function , 2018 .

[2]  Alexei A. Efros,et al.  Generative Visual Manipulation on the Natural Image Manifold , 2016, ECCV.

[3]  M. Blunt,et al.  Pore space reconstruction using multiple-point statistics , 2005 .

[4]  Xiaohai He,et al.  Reconstruction of multiphase microstructure based on statistical descriptors , 2014 .

[5]  F. Stillinger,et al.  A superior descriptor of random textures and its predictive capacity , 2009, Proceedings of the National Academy of Sciences.

[6]  Pejman Tahmasebi,et al.  Enhancing multiple‐point geostatistical modeling: 2. Iterative simulation and multiple distance function , 2016 .

[7]  Chao Ren,et al.  Dictionary optimization and constraint neighbor embedding-based dictionary mapping for superdimension reconstruction of porous media. , 2019, Physical review. E.

[8]  Karen Abrinia,et al.  Efficient three‐phase reconstruction of heterogeneous material from 2D cross‐sections via phase‐recovery algorithm , 2016, Journal of microscopy.

[9]  Xiaohai He,et al.  Markov prior-based block-matching algorithm for superdimension reconstruction of porous media. , 2018, Physical review. E.

[10]  Marc Secanell,et al.  Stochastic reconstruction using multiple correlation functions with different-phase-neighbor-based pixel selection. , 2014, Physical review. E, Statistical, nonlinear, and soft matter physics.

[11]  Simon K. Alexander,et al.  Hierarchical Annealing for Synthesis of Binary Images , 2009 .

[12]  Sebastien Strebelle,et al.  Solving Speed and Memory Issues in Multiple-Point Statistics Simulation Program SNESIM , 2014, Mathematical Geosciences.

[13]  Pejman Tahmasebi,et al.  Reconstruction of three-dimensional porous media using a single thin section. , 2012, Physical review. E, Statistical, nonlinear, and soft matter physics.

[14]  M. Sahimi,et al.  Machine learning in geo- and environmental sciences: From small to large scale , 2020, Advances in Water Resources.

[15]  Muhammad Sahimi,et al.  Linking Morphology of Porous Media to Their Macroscopic Permeability by Deep Learning , 2020, Transport in Porous Media.

[16]  Gabor T. Herman,et al.  Fundamentals of Computerized Tomography: Image Reconstruction from Projections , 2009, Advances in Pattern Recognition.

[17]  Tao Wu,et al.  Reconstruction of three-dimensional anisotropic media based on analysis of morphological completeness , 2019, Computational Materials Science.

[18]  Anthony Roberts.  Statistical reconstruction of three-dimensional porous media from two-dimensional images , 1997 .

[19]  Tao Huang,et al.  GPU-based SNESIM implementation for multiple-point statistical simulation , 2013, Comput. Geosci..

[20]  S. Torquato,et al.  Reconstructing random media. II. Three-dimensional media from two-dimensional cuts , 1998 .

[21]  T. Tang,et al.  A pixel selection rule based on the number of different‐phase neighbours for the simulated annealing reconstruction of sandstone microstructure , 2009, Journal of microscopy.

[22]  Pejman Tahmasebi,et al.  HYPPS: A hybrid geostatistical modeling algorithm for subsurface modeling , 2017 .

[23]  Martin J. Blunt,et al.  Reconstruction of three-dimensional porous media using generative adversarial neural networks , 2017, Physical review. E.

[24]  Liang Yang,et al.  GOSIM: A multi-scale iterative multiple-point statistics algorithm with global optimization , 2016, Comput. Geosci..

[25]  Yukai Wang,et al.  CT-image Super Resolution Using 3D Convolutional Neural Network , 2018, Comput. Geosci..

[26]  Marcel Utz,et al.  Efficient reconstruction of multiphase morphologies from correlation functions. , 2001 .

[27]  Pejman Tahmasebi,et al.  Accelerating geostatistical simulations using graphics processing units (GPU) , 2012, Comput. Geosci..

[28]  Zhi Xu,et al.  Stable-phase method for hierarchical annealing in the reconstruction of porous media images. , 2014, Physical review. E, Statistical, nonlinear, and soft matter physics.

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

[30]  Qizhi Teng,et al.  Accelerating multi-point statistics reconstruction method for porous media via deep learning , 2018, Acta Materialia.

[31]  Pejman Tahmasebi,et al.  Multiple-point geostatistical modeling based on the cross-correlation functions , 2012, Computational Geosciences.

[32]  J. Quiblier.  A new three-dimensional modeling technique for studying porous media , 1984 .

[33]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[34]  F. Javadpour,et al.  Nanoscale Gas Flow in Shale Gas Sediments , 2007 .

[35]  Xiaohai He,et al.  Super-dimension-based three-dimensional nonstationary porous medium reconstruction from single two-dimensional image , 2019, Journal of Petroleum Science and Engineering.

[36]  M. Sahimi,et al.  Cross-correlation function for accurate reconstruction of heterogeneous media. , 2013, Physical Review Letters.

[37]  Martin J. Blunt,et al.  Computations of Absolute Permeability on Micro-CT Images , 2012, Mathematical Geosciences.

[38]  Pejman Tahmasebi,et al.  Enhancing multiple‐point geostatistical modeling: 1. Graph theory and pattern adjustment , 2016 .

[39]  Jonathan Cagan,et al.  A simulated annealing-based algorithm using hierarchical models for general three-dimensional component layout , 1998, Comput. Aided Des..

[40]  R. M. Srivastava,et al.  Multivariate Geostatistics: Beyond Bivariate Moments , 1993 .

[41]  F. Stillinger,et al.  Modeling heterogeneous materials via two-point correlation functions: basic principles. , 2007, Physical review. E, Statistical, nonlinear, and soft matter physics.

[42]  S. Torquato,et al.  Reconstructing random media , 1998 .

[43]  S. Mitra,et al.  Understanding the micro structure of Berea Sandstone by the simultaneous use of micro-computed tomography (micro-CT) and focused ion beam-scanning electron microscopy (FIB-SEM). , 2011, Micron.

[44]  P. Bleuet,et al.  Advances in synchrotron hard X-ray based imaging , 2008 .

[45]  Ramin Bostanabad,et al.  Reconstruction of 3D Microstructures from 2D Images via Transfer Learning , 2020, Comput. Aided Des..

[46]  Martin J. Blunt,et al.  Coupled generative adversarial and auto-encoder neural networks to reconstruct three-dimensional multi-scale porous media , 2020 .

[47]  Martin J Blunt,et al.  Pore-network extraction from micro-computerized-tomography images. , 2009, Physical review. E, Statistical, nonlinear, and soft matter physics.

[48]  A. Safekordi,et al.  A multiple-point statistics algorithm for 3D pore space reconstruction from 2D images , 2011 .

[49]  Hao Liang,et al.  Accelerating simulation for the multiple-point statistics algorithm using vector quantization. , 2018, Physical review. E.

[50]  Leon A. Gatys,et al.  Image Style Transfer Using Convolutional Neural Networks , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[51]  Pejman Tahmasebi,et al.  Nanoscale and multiresolution models for shale samples , 2018 .

[52]  Muhammad Sahimi,et al.  Flow and Transport in Porous Media and Fractured Rock: From Classical Methods to Modern Approaches , 1995 .

[53]  Yong Xu,et al.  A Spatio–Temporal Pixel-Swapping Algorithm for Subpixel Land Cover Mapping , 2014, IEEE Geoscience and Remote Sensing Letters.

[54]  M. Sahimi,et al.  Quantifying accuracy of stochastic methods of reconstructing complex materials by deep learning. , 2020, Physical review. E.

[55]  Yang Li,et al.  An end-to-end three-dimensional reconstruction framework of porous media from a single two-dimensional image based on deep learning , 2020 .

[56]  Yang Li,et al.  Accurate and Fast reconstruction of Porous Media from Extremely Limited Information Using Conditional Generative Adversarial Network , 2019, Physical review. E.

[57]  Kyle J. Lange,et al.  PEM fuel cell CL characterization using a standalone FIB and SEM: Experiments and simulation , 2012 .

[58]  Truong Q. Nguyen,et al.  Deep Wide-Activated Residual Network Based Joint Blocking and Color Bleeding Artifacts Reduction for 4:2:0 JPEG-Compressed Images , 2019, IEEE Signal Processing Letters.

[59]  Muhammad Sahimi,et al.  Enhancing images of shale formations by a hybrid stochastic and deep learning algorithm , 2019, Neural Networks.

[60]  Chao Ren,et al.  CISRDCNN: Super-resolution of compressed images using deep convolutional neural networks , 2017, Neurocomputing.

[61]  Pejman Tahmasebi,et al.  Accurate modeling and evaluation of microstructures in complex materials. , 2018, Physical review. E.