A comparative analysis of super-resolution techniques for enhancing micro-CT images of carbonate rocks

Soltanmohammadi, Ramin; Faroughi, Salah A.

doi:10.1016/j.acags.2023.100143

Cited by 16 publications

(1 citation statement)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Capturing high-resolution micro-CT images of carbonate rock samples from a broad perspective is crucial for accurately modeling the fluid flow at the pore scale. If the resolution of the captured images is limited by the scanner, it may not be sufficient for detailed modeling of pore-scale features [32,33]. The presence of pores, whether saturated with fluid or isolated, can reduce the velocity of P-waves to varying degrees [34].…”

Section: Extraction Of Pore Structure and Rock Mineral Characteristic...mentioning

confidence: 99%

Numerical Simulation Analysis of Control Factors on Acoustic Velocity in Carbonate Reservoirs

He,

Zhang,

Zhao

et al. 2024

Minerals

View full text Add to dashboard Cite

The conventional Archie formula struggles with the interpretation of water saturation from resistivity well log data due to the increasing complexity of exploration targets. This challenge has prompted researchers to explore alternative physical parameters, such as acoustic characteristics, for breakthroughs. Clarifying the influencing factors of porous media acoustic characteristics is one of the most important approaches to help understanding the mechanism of acoustic characteristics of carbonate reservoirs. The article uses digital rock technology to characterize the pore structure, quantitatively identify fractures and pore structures in carbonate rocks, and establish digital models. Through conventional acoustic testing, the pressure wave (P-wave) and shear wave (S-wave) velocities of rock samples at different water saturations are obtained, and the dynamic elastic modulus is calculated. A finite element calculation model is established using the digital rock computational model to provide a basis for fluid saturation calculation methods. Based on real digital rock models, different combinations of virtual fractures are constructed, and factors affecting acoustic parameters are analyzed. The study finds that as porosity increases, the velocity difference between porous cores and fractured cores also increases. These findings provide important technical support and a theoretical basis for interpreting acoustic well logging data and evaluating carbonate reservoirs with different pore and fracture types.

show abstract

Section: Extraction Of Pore Structure and Rock Mineral Characteristic...mentioning

confidence: 99%

Numerical Simulation Analysis of Control Factors on Acoustic Velocity in Carbonate Reservoirs

He,

Zhang,

Zhao

et al. 2024

Minerals

View full text Add to dashboard Cite

show abstract

ESM data downscaling: a comparison of super-resolution deep learning models

Pawar,

Soltanmohammadi,

Mahjour

et al. 2024

Earth Sci Inform

View full text Add to dashboard Cite

Climate projections at fine spatial resolutions are required to conduct accurate risk assessment for critical infrastructure and design adaptation planning. Generating these projections using advanced Earth system models (ESM) requires significant computational resources. To address this issue, various statistical downscaling techniques have been introduced to generate fine-resolution data from coarse-resolution simulations. In this study, we evaluate and compare five deep learning-based downscaling techniques, namely, super-resolution convolutional neural networks, fast super-resolution convolutional neural network ESM, efficient sub-pixel convolutional neural network, enhanced deep residual network (EDRN), and super-resolution generative adversarial network (SRGAN). These techniques are applied to a dataset generated by the Energy Exascale Earth System Model (E3SM), focusing on key surface variables such as surface temperature, shortwave heat flux, and longwave heat flux. Models are trained and validated using paired fine-resolution (0.25$$^{\circ }$$ ∘ ) and coarse-resolution (1$$^{\circ }$$ ∘ ) monthly data obtained from a 9-year simulation. Next, blind testing is performed using monthly data obtained from two different years outside of the training and validation set. To evaluate the efficiency of each technique, different statistical metrics are used, including mean squared error (MSE), peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and learned perceptual image patch similarity (LPIPS). The results show that EDRN outperforms other algorithms in terms of PSNR, SSIM, and MSE, but struggles to capture fine-scale features in the data. In contrast, SRGAN, a generative model that uses perceptual loss, excels in capturing fine details at boundaries and internal structures, resulting in lower LPIPS than other methods.

show abstract

Resolution enhancement and segmentation of polar bubbly ice micro CT scans via 3D convolutional neural network

Bagherzadeh,

Freitag,

Frese

et al. 2024

Applied Computing and Geosciences

View full text Add to dashboard Cite

A comparative analysis of super-resolution techniques for enhancing micro-CT images of carbonate rocks

Cited by 16 publications

References 59 publications

Numerical Simulation Analysis of Control Factors on Acoustic Velocity in Carbonate Reservoirs

Numerical Simulation Analysis of Control Factors on Acoustic Velocity in Carbonate Reservoirs

ESM data downscaling: a comparison of super-resolution deep learning models

Resolution enhancement and segmentation of polar bubbly ice micro CT scans via 3D convolutional neural network

Contact Info

Product

Resources

About