With the exploration and development of oil and gas into the ultra-deep reservoir, hydraulic fracture propagation under the condition of high stress difference is prone to occur large curvature deflection, leading to wellhead overpressure, sand plugging and other problems occur frequently. It is of great significance to clarify the mechanism and main control factors of hydraulic fracture propagation and deflection near wellbore in ultra-deep and high stress difference reservoir for safe and efficient development. Under the constraint of the continuity framework of classical thermodynamics, the sharp fracture on the discrete interface is smoothly described as a continuous damage dispersion fracture, and the Lagrange Energy Functional is constructed based on Griffith energy balance relation and fracture variational principle, and then the phase field hydraulic fracturing model of perforated well in anisotropic reservoir is established based on the principle of energy minimization. The validity of the phase-field model presented in this paper is verified by comparing with the classical Griffith crack opening profile equation. It is found that the hydraulic fracture starts to crack along an approximate straight line between perforation and maximum horizontal principal stress, and then deflects to the maximum horizontal principal stress direction. The specific direction of crack initiation is affected by in-situ stress difference, displacement and perforation angle. The increase of the in-situ stress difference will promote the hydraulic fracture deflection propagation near the wellbore, make the deflection angle increase and the deflection radius decrease; increasing the displacement can weaken the hydraulic fracture deflection, and making the deflection angle decrease and the deflection radius increase; with the increase of perforation angle, the angle between perforation and the maximum horizontal principal stress increases, which will aggravate the deflection degree of crack propagation so that the flow friction of fracturing fluid increases and the risk of sand plugging increases; the anisotropy characteristics of the reservoir can also significantly affect the deflection and propagation process of hydraulic fractures. In the model, the critical energy release rate in different directions is taken as the anisotropic parameter of fracture resistance. The results show that fractures tend to propagate in the direction of low resistance. The stronger the anisotropy of fracture resistance, the greater the deflection degree of hydraulic fractures. The anisotropic characteristics of reservoir fractures significantly affect the turning behavior of fractures. The phase-field hydraulic fracturing model in this paper provides a convenient method to study the propagation and steering behavior of hydraulic fractures without any fracture criteria, which is helpful to improve the understanding of near-well fracture steering in ultra-deep and high stress difference reservoirs, help to understand the fracture mechanism and fracture deflection behavior under different geological environments and fracturing conditions, and provide reference and suggestions for fracturing technology design and perforation scheme optimization.

Well logging curves are essential for recording the physical parameters of formations during drilling, providing vital information for analyzing rock properties, evaluating hydrocarbon reservoirs, and understanding reservoir distribution. As oil and gas exploration continues to progress, the complexity of subtle and hidden reservoirs has increased, posing challenges for traditional exploration techniques. Despite their importance, conventional well logging data suffer from low resolution, which significantly limits their ability to address the requirements of detailed reservoir characterization. In particular, the inability to precisely identify modification points in thin interbedded reservoirs remains a critical bottleneck in reservoir analysis. To overcome these limitations, developing high-resolution interpretation methods for well logging data has become an urgent priority in the field of reservoir analysis and geological exploration. This study proposes a novel reservoir prediction model based on the ResNet50 regression algorithm. By integrating vertically continuous optical thin-section data, which can capture fine-scale and complex vertical geological features, with five conventional well logging parameters, the proposed model aims to improve the resolution and accuracy of reservoir analysis. This combination leverages the strengths of image-based geological analysis and traditional well logging to deliver a more precise interpretation of subsurface formations. The model was validated using data collected from five intervals of the Permian formation in a specific well area. A total of 570 continuous geological image samples, combined with their corresponding well logging data, were utilized for model training and prediction. The results demonstrate that the model effectively enhances the resolution of well logging data, improving it from the traditional 12.5 cm to 6.25 cm. This significant improvement not only increases the precision of well logging interpretation but also provides a more detailed understanding of reservoir characteristics. The model’s performance was rigorously evaluated using three widely recognized metrics: the coefficient of determination (R²), root mean square error (RMSE), and mean absolute error (MAE). The results revealed that the model excels in predicting parameters such as acoustic time (AC), compensated neutron (CNL), resistivity (RT), and gamma ray (GR), achieving an average prediction error below 0.094. This highlights the model’s reliability and superior performance in reservoir prediction tasks. However, challenges remain in predicting density (DEN), where the model’s accuracy is impacted in intervals with significant lithological heterogeneity or complex geological conditions.