Because of its benefits in terms of high speed, non-destructiveness, and three-dimensionality, as well as ease of integration with computer simulation, computed tomography (CT) technology is widely applied in reservoir geology research. However, rock imaging is restricted by the device used as there is not a win–win for both the image receptive field and corresponding resolution. Convolutional neural network-based super-resolution reconstruction has become a hot topic in improving the performance of CT images. With the help of a convolution kernel, it can effectively extract characteristics and ignore disturbance information. The dismal truth is that convolutional neural networks still have numerous issues, particularly unclear texture details. To address these challenges, a generative adversarial network (RDCA-SRGAN) was designed to improve rock CT image resolution using the combination of residual learning and a dual-channel attention mechanism. Specifically, our generator employs residual attention to extract additional features; similarly, the discriminator builds on dual-channel attention and residual learning to distinguish generated contextual information and decrease computational consumption. Quantitative and qualitative analyses demonstrate that the proposed model is superior to earlier advanced frameworks and is capable to constructure visually indistinguishable high-frequency details. The quantitative analysis shows our model contributes the highest value of structural similarity, enriching the more detailed texture information. From the qualitative analysis, in enlarged details of the reconstructed images, the edges of the images generated by the RDCA-SRGAN can be shown to be clearer and sharper. Our model not only performs well in subtle coal cracks but also enriches more dissolved carbonate and carbon minerals. The RDCA-SRGAN has substantially enhanced the reconstructed image resolution and our model has great potential to be used in geomorphological study and exploration.

Frac‐packing is an attractive technique to stimulate production for gas hydrate reservoirs with the additional benefit of solving the problematic sand production problems. So far, there have been no documented mathematical models to predict the propagation of fractures and to forecast gas production for frac‐packed gas wells. An analytical model was derived to predict the propagation of a horizontal fracture and to assess the well productivity in frac‐packed gas wells in a gas hydrate reservoir. The model assumes a steady, single‐gas, Darcy flow in the matrix and fracture. Case analyses were performed for key design and operational parameters with the analytical model. The result shows that it is easy to control the relationship between the wellbore fracturing pressure and injecting flow rate, and thus, fractures of any length can be produced in the fracture penetration process of frac‐packed wells. Case analysis also shows that the gas production rate increases nonlinearly with the fracture propagation and increases linearly with the fracture width. The increase in fracture width turns out to be surprisingly effective in improving well productivity without threshold within the investigated range of width. It was also found that the increase in fracture permeability contributes more to the productivity of the frac‐packed wells than the increase in matrix permeability. The model also assumes no flow at the boundary of the reservoir, which may underestimate those gas hydrate reservoirs with pressure supply. This work uses a theoretical approach to estimate the productivity of the frac‐packed gas hydrate reservoirs, which may benefit in solving the sand production issue during the production process as well.