Gas permeability, which is measured mainly through gas permeability experiments, is a critical technical index in many engineering fields. In this study, permeability is firstly calculated based on information from a digital image and an improved permeability prediction model. The calculated results are experimentally verified. Subsequently, a self-developed image-processing program is used to extract feature parameters from a scanning electron microscopy image. Meanwhile, an extreme learning machine algorithm is used to input the image feature parameters obtained using the image-processing program into the extreme learning machine algorithm for machine learning. Additionally, we compare several typically used machine learning algorithms, which confirmed the reliability and accuracy of our algorithm. The best activation function can be obtained by comparing the predicted permeability using an appropriate number of neuron nodes. Experimental results show that the program can accurately identify the features of the microscopy image. Combining the program with an extreme learning machine neural network algorithmgas permeability results to be obtained with high accuracy. This method yields good predictions of permeability in certain cases and has been adapted to other geomaterials.

The shape, size, and connectivity of porous structures control the overall storage capacity and flow in oil and gas reservoirs. The mercury intrusion capillary pressure (MICP) technique is widely utilized to measure capillary pressure and calculate pore size distribution of core samples in the geo-energy industry. Combining the MICP capillary pressure data with parameters from other experimental methods (such as scanning electron microscopy, and nuclear magnetic resonance) or theoretical approaches (such as fractal theory) can more accurately describe the pore structure of reservoirs. In this paper, the latest advances on the application of primary drainage MICP curves from reservoir porous structures are reviewed in three main aspects: The measurement and calculation of MICP capillary pressure, estimation of pore size distributions making use of fractal characteristics, and determination of permeability. Experimental measurements and numerical simulation methods of MICP capillary pressure with its influencing factors are also discussed. MICP capillary pressure combined with other methods are argued to be one of the main directions for future research on reservoir pore structures.

Supercritical carbon dioxide (ScCO₂)-based fracturing technology associating with CO₂ enhanced shale gas recovery is a promising technology to reduce the water consumption and could provide the potential for CO₂ sequestration. Advancing the understanding of complex gas shale reservoir behavior in the presence of multiphase and multicomponent gases (ScCO₂, gaseous CO₂ and CH₄ etc.) via laboratory experiments, theoretical model development and field validation studies is very important. In this paper, the progress of some key scientific problems such as the mechanism of ScCO₂ drilling and completion, the ScCO₂ fracturing technology, the competition adsorption behaviors of CO₂/CH₄ in shale, the coupled multiphase and multicomponent CO₂/CH₄ flow during the CO₂ enhanced shale gas recovery process and the CO₂ sequestration potential in shale formation were discussed. The results indicated that the ScCO₂ jet has a stronger rock erosion ability and requires much lower threshold pressure than water jet. The fracture initiation pressure of ScCO₂ is about 50% lower than that of hydraulic fracturing, and the volume of rock fractured by ScCO₂ is several times larger than that of hydraulic fracturing. Field test shown that the shale gas production rate was significant increased by the ScCO₂-based fracturing technology. Finally, the challenges of the technique will face and the further research is needed in the future is exposed.