Deep Learning of Multiresolution X-Ray Micro-Computed-Tomography Images for Multiscale Modeling

Jackson, Samuel J.; Niu, Yufu; Manoorkar, Sojwal; Mostaghimi, Peyman; Armstrong, Ryan T.

doi:10.1103/physrevapplied.17.054046

Cited by 26 publications

(7 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Resolution recovery networks were then trained using a modification of well-established image-to-image regression techniques [7], [8], with loss functions, network structures and data augmentation tailored to the 3D tomographic imaging problem, modified to ensure rapid convergence and high performance even with early stopping [9]. Network structures were adapted from the U-Net architecture [10].…”

Section: Methodsmentioning

confidence: 99%

Fully automated deep-learning-based resolution recovery

Andrew

Andreyev²,

Yang³

et al. 2022

7th International Conference on Image Formation in X-Ray Computed Tomography

View full text Add to dashboard Cite

A novel automated workflow for the recovery of image resolution using deep convolutional neural networks (CNNs) trained using spatially registered multiscale data is presented. Spatial priors, coupled with high order voxel-based image registration, are used to correct for uncertainties in image magnification and position. A network is then trained to remove the effects of point spread from the low-resolution data, improving resolution while reducing image noise & artefact levels. While benchmarking on real materials, including biological, materials science and electronics samples, we find that resolution recovery improves quantitative and qualitative measurements, even if certain image details cannot be easily identified from the original low-resolution data.

show abstract

Section: Methodsmentioning

confidence: 99%

Fully automated deep-learning-based resolution recovery

Andrew

Andreyev²,

Yang³

et al. 2022

7th International Conference on Image Formation in X-Ray Computed Tomography

View full text Add to dashboard Cite

show abstract

“…High-frequency information can be well preserved by introducing deep learning methods, which are widely used in nature images, medical images, satellite aerial images, military fields, and robotics [2][3][4][5]. This is also true in the field of geophysics [6][7][8][9][10]. However, the traditional pixel loss function in deep learning methods often results in the generated images looking too smooth and lacking details, which predisposes them to being less capable of reconstructing texture in high-frequency images such as thin slices.…”

Section: Introductionmentioning

confidence: 99%

OmniSR-M: A Rock Sheet with a Multi-Branch Structure Image Super-Resolution Lightweight Method

Liu,

Xu,

Tang

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

With the rapid development of digital core technology, the acquisition of high-resolution rock thin section images has become crucial. Due to the limitation of optical principles, thin section imaging involves a contradiction between resolution and field of view. In order to solve this problem, this paper proposes a lightweight, fully aggregated network with multi-branch structure for super resolution of rock thin section images. The experimental results on the rock thin section dataset demonstrate that the improved method, called OmniSR-M, achieves significant enhancement compared to the original OmniSR method and also surpasses other state-of-the-art methods. OmniSR-M effectively recovers image details while maintaining its lightweight nature. Specifically, OmniSR-M reduces the number of parameters by 26.56% and the computation by 27.66% compared to OmniSR. Moreover, this paper quantitatively analyzes both the facies porosity rate and grain size features in the application scenario. The results show that the images generated by OmniSR-M successfully recover key information about the rock thin section.

show abstract

“…More advanced multi-component studies suffer from small fields of view (1.5 mm 2 ) or poor voxel resolution (5 μm) issues 68 , 69 (see Supplementary Table 1b ). Similarly, memory scaling limitations in 3D super-resolution (4 times super-resolution results in 64 times memory increase) have restricted its applications to the generation of small super-resolved cubes for analysis and upscaling 20 , 70 . Therefore, although large-scale high-resolution imaging and multi-label simulations of PEMFCs are necessary to drive the next technological innovation, the domain size is currently restricted by limitations in both experimental imaging and computational modelling resources.…”

Section: Introductionmentioning

confidence: 99%

Large-scale physically accurate modelling of real proton exchange membrane fuel cell with deep learning

et al. 2023

Self Cite

View full text Add to dashboard Cite

Proton exchange membrane fuel cells, consuming hydrogen and oxygen to generate clean electricity and water, suffer acute liquid water challenges. Accurate liquid water modelling is inherently challenging due to the multi-phase, multi-component, reactive dynamics within multi-scale, multi-layered porous media. In addition, currently inadequate imaging and modelling capabilities are limiting simulations to small areas (<1 mm2) or simplified architectures. Herein, an advancement in water modelling is achieved using X-ray micro-computed tomography, deep learned super-resolution, multi-label segmentation, and direct multi-phase simulation. The resulting image is the most resolved domain (16 mm2 with 700 nm voxel resolution) and the largest direct multi-phase flow simulation of a fuel cell. This generalisable approach unveils multi-scale water clustering and transport mechanisms over large dry and flooded areas in the gas diffusion layer and flow fields, paving the way for next generation proton exchange membrane fuel cells with optimised structures and wettabilities.

show abstract

Deep Learning of Multiresolution X-Ray Micro-Computed-Tomography Images for Multiscale Modeling

Cited by 26 publications

References 54 publications

Fully automated deep-learning-based resolution recovery

Fully automated deep-learning-based resolution recovery

OmniSR-M: A Rock Sheet with a Multi-Branch Structure Image Super-Resolution Lightweight Method

Large-scale physically accurate modelling of real proton exchange membrane fuel cell with deep learning

Contact Info

Product

Resources

About