A fast and flexible algorithm for microstructure reconstruction combining simulated annealing and deep learning

The microstructure analyses of porous media have considerable research value for the study of macroscopic properties. As the premise of conducting these analyses, the accurate reconstruction of microstructure digital model is also an important component of the research. Computational reconstruction algorithms of microstructure have attracted much attention due to their low cost and excellent performance. However, it is still a challenge for computational reconstruction algorithms to achieve faster and more efficient reconstruction. The bottleneck lies in computational reconstruction algorithms, they are either too slow (traditional reconstruction algorithms) or not flexible to the training process (deep learning reconstruction algorithms). To address these limitations, we proposed a fast and flexible computational reconstruction algorithm, neural networks based on improved simulated annealing framework (ISAF-NN). The proposed algorithm is flexible and can complete training and reconstruction in a short time with only one two-dimensional image. By adjusting the size of input, it can also achieve reconstruction of arbitrary size. Finally, the proposed algorithm is experimentally performed on a variety of isotropic and anisotropic materials to verify the effectiveness and generalization.

[1]  P. Withers,et al.  A spherical harmonic-random field coupled method for efficient reconstruction of CT-image based 3D aggregates with controllable multiscale morphology , 2023, Computer Methods in Applied Mechanics and Engineering.

[2]  Zhiwei Zhu,et al.  Microstructural Classification and Reconstruction of the Computational Geometry of Steamed Bread Using Descriptor-Based Approach , 2022, Transport in Porous Media.

[3]  H. Wessels,et al.  Three-dimensional microstructure generation using generative adversarial neural networks in the context of continuum micromechanics , 2022, Computer Methods in Applied Mechanics and Engineering.

[4]  Zhi Xu,et al.  Fast reconstruction of multiphase microstructures based on statistical descriptors. , 2022, Physical review. E.

[5]  V. Krutko,et al.  Generative adversarial networks for reconstruction of three-dimensional porous media from two-dimensional slices. , 2022, Physical review. E.

[6]  Chenfeng Li,et al.  Stochastic reconstruction of 3D microstructures from 2D cross-sectional images using machine learning-based characterization , 2022, Computer Methods in Applied Mechanics and Engineering.

[7]  W. Tao,et al.  Pore-scale modeling of complex transport phenomena in porous media , 2022, Progress in Energy and Combustion Science.

[8]  Xixin Wang,et al.  Two parameter optimization methods of multi-point geostatistics , 2022, Journal of Petroleum Science and Engineering.

[9]  Ting Zhang,et al.  3D reconstruction of digital cores based on a model using generative adversarial networks and variational auto-encoders , 2021 .

[10]  Ting Zhang,et al.  3D reconstruction of porous media by combining scaling transformation and multi-scale discrimination using generative adversarial networks , 2021, Journal of Petroleum Science and Engineering.

[11]  Alexander Raßloff,et al.  Descriptor-based reconstruction of three-dimensional microstructures through gradient-based optimization , 2021, Acta Materialia.

[12]  M. Sahimi,et al.  Reconstruction, optimization, and design of heterogeneous materials and media: Basic principles, computational algorithms, and applications , 2021, Physics Reports.

[13]  Qizhi Teng,et al.  3D-PMRNN: Reconstructing three-dimensional porous media from the two-dimensional image with recurrent neural network , 2021, Journal of Petroleum Science and Engineering.

[14]  M. Baghani,et al.  A New Statistical Descriptor for the Physical Characterization and 3D Reconstruction of Heterogeneous Materials , 2021, Transport in Porous Media.

[15]  N. Xiao,et al.  Novel cooling–solidification annealing reconstruction of rock models , 2021, Acta Geotechnica.

[16]  Yongming Liu,et al.  Ultra-efficient reconstruction of 3D microstructure and distribution of properties of random heterogeneous materials containing multiple phases , 2021 .

[17]  Anthony R. Kovscek,et al.  RockFlow: Fast Generation of Synthetic Source Rock Images Using Generative Flow Models , 2020, Energies.

[18]  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 .

[19]  Sergio Damas,et al.  Stochastic reconstruction of 3D porous media from 2D images using generative adversarial networks , 2020, Neurocomputing.

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

[21]  Gregoire Mariethoz,et al.  QuickSampling v1.0: a robust and simplified pixel-based multiple-point simulation approach , 2020, Geoscientific Model Development.

[22]  Pejman Tahmasebi,et al.  Hybrid geological modeling: Combining machine learning and multiple-point statistics , 2020, Comput. Geosci..

[23]  J. Caers,et al.  A Tree‐Based Direct Sampling Method for Stochastic Surface and Subsurface Hydrological Modeling , 2020, Water Resources Research.

[24]  Shuaibing Song,et al.  An improved simulated annealing algorithm for reconstructing 3D large-scale porous media , 2019, Journal of Petroleum Science and Engineering.

[25]  Lei Song,et al.  Efficient 3D reconstruction of random heterogeneous media via random process theory and stochastic reconstruction procedure , 2019, Computer Methods in Applied Mechanics and Engineering.

[26]  Li Zhang,et al.  A review of microscopic seepage mechanism for shale gas extracted by supercritical CO2 flooding , 2019, Fuel.

[27]  Z. Jiao,et al.  High-throughput 3D reconstruction of stochastic heterogeneous microstructures in energy storage materials , 2019, npj Computational Materials.

[28]  Marina V Karsanina,et al.  Hierarchical Optimization: Fast and Robust Multiscale Stochastic Reconstructions with Rescaled Correlation Functions. , 2018, Physical review letters.

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

[30]  Ming Yang,et al.  New algorithms for virtual reconstruction of heterogeneous microstructures , 2018, Computer Methods in Applied Mechanics and Engineering.

[31]  Wing Kam Liu,et al.  Computational microstructure characterization and reconstruction: Review of the state-of-the-art techniques , 2018, Progress in Materials Science.

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

[33]  Xiaoping Zhou,et al.  3D Numerical Reconstruction of Porous Sandstone Using Improved Simulated Annealing Algorithms , 2018, Rock Mechanics and Rock Engineering.

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

[35]  Karim Faez,et al.  PCTO-SIM: Multiple-point geostatistical modeling using parallel conditional texture optimization , 2017, Comput. Geosci..

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

[37]  W Chen,et al.  Characterization and reconstruction of 3D stochastic microstructures via supervised learning , 2016, Journal of microscopy.

[38]  Ali Q. Raeini,et al.  The impact of porous media heterogeneity on non-Darcy flow behaviour from pore-scale simulation , 2016 .

[39]  Xiaohai He,et al.  Pattern density function for reconstruction of three-dimensional porous media from a single two-dimensional image. , 2016, Physical review. E.

[40]  XiaoHai He,et al.  Reconstruction of three-dimensional porous media from a single two-dimensional image using three-step sampling. , 2015, Physical review. E, Statistical, nonlinear, and soft matter physics.

[41]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

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

[43]  Pejman Tahmasebi,et al.  MS-CCSIM: Accelerating pattern-based geostatistical simulation of categorical variables using a multi-scale search in Fourier space , 2014, Comput. Geosci..

[44]  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.

[45]  Bin Li,et al.  Recent Progress in Redox Flow Battery Research and Development , 2012 .

[46]  Changying Zhao,et al.  Review on thermal transport in high porosity cellular metal foams with open cells , 2012 .

[47]  Gregoire Mariethoz,et al.  The Direct Sampling method to perform multiple‐point geostatistical simulations , 2010 .

[48]  Hiroshi Iwai,et al.  Quantification of SOFC anode microstructure based on dual beam FIB-SEM technique , 2010 .

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

[50]  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.

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

[52]  R. Hilfer,et al.  Three-dimensional local porosity analysis of porous media , 1998, cond-mat/9803012.

[53]  Salvatore Torquato,et al.  Morphology and physical properties of Fontainebleau sandstone via a tomographic analysis , 1996 .

[54]  Salvatore Torquato,et al.  Two‐point cluster function for continuum percolation , 1988 .

[55]  J. Martin,et al.  Reconstruction , 1980, The Lancet.

[56]  Song Cen,et al.  Statistical characterization and reconstruction of heterogeneous microstructures using deep neural network , 2021, Computer Methods in Applied Mechanics and Engineering.

[57]  D. Wildenschild,et al.  X-ray imaging and analysis techniques for quantifying pore-scale structure and processes in subsurface porous medium systems , 2013 .

[58]  Sebastien Strebelle,et al.  Conditional Simulation of Complex Geological Structures Using Multiple-Point Statistics , 2002 .

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

[60]  S. Torquato,et al.  Lineal-path function for random heterogeneous materials. , 1992, Physical review. A, Atomic, molecular, and optical physics.