Super resolution reconstruction of<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="mml22" display="inline" overflow="scroll" altimg="si1.gif"><mml:mi mathvariant="normal">μ</mml:mi></mml:math>-CT image of rock sample using neighbour embedding algorithm

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

doi:10.1016/j.physa.2017.10.022

Cited by 43 publications

(15 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed super-resolution method fits within the group of techniques that attempts to mitigate or solve the resolution versus sample-size trade-off. Up to now, these super-resolution methods have not often received attention for geological applications and were mainly addressed by Wang et al [82,83,85] and Wu et al [75] who attempted classical super-resolution methods like neighbour embedding [75,82,[156][157][158] and sparse representation [83,159], although Wang et al [84,85] were also the first to use convolutional neural networks to address the super-resolution problem for geological materials. Compared to these networks, the presented research used deeper neural networks, an encoder-decoder architecture with residual connections and generative training to better conform to approaches in recent super-resolution literature [93,96,100].…”

Section: Super Resolution Models and Their Impact On Fluid Flow Simulmentioning

confidence: 99%

“…Thirdly, super-resolution methods aim to introduce high resolution patterns into low resolution images by mapping a translation of low resolution features to high resolution equivalents. These methods could use self-similarity of images to improve details [79][80][81] or construct dictionaries linking low and high resolution image patch pairs through neighbour embedding [75,82] or sparse representation [83] by finding the closest matching high resolution image patch (e.g., 7 × 7 pixels) to a low resolution patch. These methods work in 2D using Materials 2020, 13, 1397 3 of 33 high resolution scanning electron microscopy (SEM) images and low resolution CT slices [75,82] and 3D, for which two CT scans at different resolutions were used [83].…”

mentioning

confidence: 99%

“…These methods could use self-similarity of images to improve details [79][80][81] or construct dictionaries linking low and high resolution image patch pairs through neighbour embedding [75,82] or sparse representation [83] by finding the closest matching high resolution image patch (e.g., 7 × 7 pixels) to a low resolution patch. These methods work in 2D using Materials 2020, 13, 1397 3 of 33 high resolution scanning electron microscopy (SEM) images and low resolution CT slices [75,82] and 3D, for which two CT scans at different resolutions were used [83]. Additionally, the translation from low to high resolution features could be addressed through neural networks [84][85][86][87].…”

mentioning

confidence: 99%

“…These methods would be too computationally expensive to generate 3D simulations. This is problematic because porosity and fluid flow are 3D properties, thus they should be simulated in 3D.This research builds on the efforts of Wang et al [82,83,85] and Shams et al[88] to super-resolve, or improve the resolution, of lower resolution scans and it will more specifically be applying 3D generative adversarial neural networks. In order to have the most solid neural network, two CT scans taken at different resolution of exactly the same volume are used for training, because artificial downsampling of a high-resolution image to get a low resolution image is not performed without the risk of oversimplifying the problem [32,89].…”

mentioning

confidence: 99%

See 3 more Smart Citations

Computed Tomography 3D Super-Resolution with Generative Adversarial Neural Networks: Implications on Unsaturated and Two-Phase Fluid Flow

2020

View full text Add to dashboard Cite

Fluid flow characteristics are important to assess reservoir performance. Unfortunately, laboratory techniques are inadequate to know these characteristics, which is why numerical methods were developed. Such methods often use computed tomography (CT) scans as input but this technique is plagued by a resolution versus sample size trade-off. Therefore, a super-resolution method using generative adversarial neural networks (GANs) was used to artificially improve the resolution. Firstly, the influence of resolution on pore network properties and single-phase, unsaturated, and two-phase flow was analysed to verify that pores and pore throats become larger on average and surface area decreases with worsening resolution. These observations are reflected in increasingly overestimated single-phase permeability, less moisture uptake at lower capillary pressures, and high residual oil fraction after waterflooding. Therefore, the super-resolution GANs were developed which take low (12 µm) resolution input and increase the resolution to 4 µm, which is compared to the expected high-resolution output. These results better predicted pore network properties and fluid flow properties despite the overestimation of porosity. Relevant small pores and pore surfaces are better resolved thus providing better estimates of unsaturated and two-phase flow which can be heavily influenced by flow along pore boundaries and through smaller pores. This study presents the second case in which GANs were applied to a super-resolution problem on geological materials, but it is the first one to apply it directly on raw CT images and to determine the actual impact of a super-resolution method on fluid predictions.Materials 2020, 13, 1397 2 of 33 examples requires detailed knowledge on fluid storage and flow properties which could be estimated through experiments, either carried out in specialized laboratories or deduced from digital rocks. Laboratory measurements, however, require expensive and complex set-ups, take a long time to complete, are often destructive, do not always entirely capture the studied properties and on top of that, experiments often fail to produce reproducible results between laboratories [9,[12][13][14][15][16][17][18][19]. Therefore, numerical solutions have been developed allowing to compute fluid storage and flow properties on digital rocks [7,[20][21][22][23]. Such digital rocks are acquired through direct imaging or numerical simulations of rocks.Computed tomography (CT) is a technique to rapidly capture the three-dimensional structure of materials [22,24,25]. However, like any imaging technique, CT is plagued by a sample size versus resolution trade-off, which is adversely affecting fluid flow simulations. Both a high resolution and sufficiently large volume are required for accurate fluid flow estimations at the pore-scale [9,[26][27][28]. Resolution impacts how well pore network topology and pore surfaces are resolved. At lower resolution, i.e., lower resolving power, pore sizes are often overestimated and specific surf...

show abstract

Section: Super Resolution Models and Their Impact On Fluid Flow Simulmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Computed Tomography 3D Super-Resolution with Generative Adversarial Neural Networks: Implications on Unsaturated and Two-Phase Fluid Flow

2020

View full text Add to dashboard Cite

show abstract

“…On the contrary, HR images are usually with a small FOV, thereby resulting in decreased representativeness. Recent studies [7][8][9][10][11] show that this bottleneck can be addressed to some extent via super-resolution (SR), which maps a LR input to a space of higher resolution [12]. HR rock MCT images with a large FOV can be obtained by applying SR algorithms to the collected LR MCT images.…”

Section: Introductionmentioning

confidence: 99%

Super-resolution of real-world rock microcomputed tomography images using cycle-consistent generative adversarial networks

Chen

Teng

et al. 2020

Phys. Rev. E

View full text Add to dashboard Cite

Digital rock imaging plays an important role in studying the microstructure and macroscopic properties of rocks, where microcomputed tomography (MCT) is widely used. Due to the inherent limitations of MCT, a balance should be made between the field of view (FOV) and resolution of rock MCT images-a large FOV at low resolution (LR) or a small FOV at high resolution (HR). However, large FOV and HR are both expected for reliable analysis results in practice. Super-resolution (SR) is an effective solution to break through the mutual restriction between the FOV and resolution of rock MCT images, for it can reconstruct an HR image from a LR observation. Most of the existing SR methods cannot produce satisfactory HR results on real-world rock MCT images. One of the main reasons for this is that paired images are usually needed to learn the relationship between LR and HR rock images. However, it is challenging to collect such a dataset in a real scenario. Meanwhile, the simulated datasets may be unable to accurately reflect the model in actual applications. To address these problems, we propose a cycle-consistent generative adversarial network (CycleGAN)-based SR approach for real-world rock MCT images, namely, SRCycleGAN. In the off-line training phase, a set of unpaired rock MCT images is used to train the proposed SRCycleGAN, which can model the mapping between rock MCT images at different resolutions. In the on-line testing phase, the resolution of the LR input is enhanced via the learned mapping by SRCycleGAN. Experimental results show that the proposed SRCycleGAN can greatly improve the quality of simulated and real-world rock MCT images. The HR images reconstructed by SRCycleGAN show good agreement with the targets in terms of both the visual quality and the statistical parameters, including the porosity, the local porosity distribution, the two-point correlation function, the lineal-path function, the two-point cluster function, the chord-length distribution function, and the pore size distribution. Large FOV and HR rock MCT images can be obtained with the help of SRCycleGAN. Hence, this work makes it possible to generate HR rock MCT images that exceed the limitations of imaging systems on FOV and resolution.

show abstract

X-ray image super-resolution reconstruction based on a multiple distillation feedback network

Jia

Cui

et al. 2021

Appl Intell

View full text Add to dashboard Cite

Super resolution reconstruction ofμ-CT image of rock sample using neighbour embedding algorithm

Cited by 43 publications

References 26 publications

Computed Tomography 3D Super-Resolution with Generative Adversarial Neural Networks: Implications on Unsaturated and Two-Phase Fluid Flow

Computed Tomography 3D Super-Resolution with Generative Adversarial Neural Networks: Implications on Unsaturated and Two-Phase Fluid Flow

Super-resolution of real-world rock microcomputed tomography images using cycle-consistent generative adversarial networks

X-ray image super-resolution reconstruction based on a multiple distillation feedback network

Contact Info

Product

Resources

About