Super-resolution for electron microscope scanning images of shale via spatial-spectral domain attention network

Abstract

The evaluation of adsorption states and shale gas content in shale fractures and pores relies on the analysis of these fractures and pores. Scanning electron microscopy images are commonly used for shale analysis; however, their low resolution, particularly the loss of high-frequency information at pore edges, presents challenges in analyzing fractures and pores in shale gas reservoirs. This study introduced a novel neural network called the spatial-spectral domain attention network (SSDAN), which employed spatial and spectral domain attention mechanisms to extract features and restore information in parallel. The network generated super-resolution images through a fusion module that included CNN-based spatial blocks for pixel-level image information recovery, spectral blocks to process Fourier transform information of images and enhance high-frequency recovery, and an adaptive vision transformer to process Fourier transform block information, eliminating the need for a preset image size. The SSDAN model demonstrated exceptional performance in comparative experiments on marine shale and marine continental shale datasets, achieving optimal performance on key indicators such as peak signal-to-noise ratio, structural similarity, learned perceptual image patch similarity, and Frechet inception distance while also exhibiting superior visual performance in pore recovery. Ablation experiments further confirmed the effectiveness of the spatial blocks, channel attention, spectral blocks, and frequency loss function in the model. The SSDAN model showed remarkable capability in enhancing the resolution of shale gas reservoir images and restoring high-frequency information at pore edges, thereby validating its effectiveness in unconventional natural gas reservoir analyses.