Shaohua You

Stable diffusion for high-quality image reconstruction in digital rock analysis

The permeability of porous materials determines the fluid flow rate and aids in the prediction of their mechanical properties. This study developed a novel approach that combines the discrete cosine transform (DCT) and artificial neural networks (ANN) for permeability analysis and prediction in digital rock images, focusing on nanoscale porous materials in shale formations. The DCT effectively captured the morphology and spatial distribution of material structure at the nanoscale and enhanced the computational efficiency, which was crucial for handling the complexity and high dimensionality of the digital rock images. The ANN model, trained using the Levenberg–Marquardt algorithm, preserved essential features and demonstrated exceptional accuracy for permeability prediction from the DCT-processed rock images. Our approach offers versatility and efficiency in handling diverse rock samples, from nanoscale shale to microscale sandstone. This work contributes to the comprehension and exploitation of unconventional resources, especially those preserved in nanoscale pore structures.

Calculation of REV (representative elementary volume) properties of geological porous media refers to the process of creating a 3D digital representation of a rock sample, typically obtained from imaging techniques such as X-ray microtomography. This technique allows for a detailed analysis of the internal structure and the properties of rocks, as well as precise calculation of various flow parameters. However, one major challenge with calculation of REV properties of geological porous media is the high computational cost required to generate accurate results, especially for large and complex samples. In this study, we constructed 3D digital cores of dune sand and fractured shale using CT scanning technology, and then used two image processing techniques, namely digital core image resampling and cutting, to reduce the computational cost of calculating digital core permeability. Next, a fast permeability calculation method is employed to reduce the complexity of permeability calculation. Finally, we summarized the applicability of different image processing methods to different rock samples, and provided prerequisites for high computational cost digital core permeability calculation.