In view of the low accuracy of existing tomographic detection methods, in order to improve the accuracy of tomographic detection, a tomographic detection method based on residual network and Faster R-CNN is proposed. First, input the image into the ResNet-50 feature extraction network to obtain the corresponding feature map, then use the RPN structure to generate the candidate frame, and project the candidate frame generated by the RPN to the feature map to obtain the corresponding feature matrix, and finally, through the ROI pooling layer, each of the feature matrix is scaled to a fixed-size feature map, and then the feature map is flattened through a series of fully connected layers to obtain the prediction result. ResNet-50 mainly solves the problem of network degradation and overfitting caused by deepening of the network layer when extracting the deep features of faults. Faster R-CNN realizes end-to-end training, combines the advantages of ResNet-50 and Faster R-CNN, and has a precise positioning efficiency. The accuracy of detecting faults reaches 90%. The data enhancement is further optimized, the generalization ability of the network is improved, the detection results of the network are optimized, and the accuracy of fault detection is effectively improved, and the feasibility of the method is verified by actual seismic data.

Seismic high-resolution processing is crucial to enhance the accuracy and reliability of seismic data, particularly in the exploration and development of complex hydrocarbon reservoirs. Conventional high-resolution processing methods, exemplified by sparse spike deconvolution (SSD), typically rely on the assumption of sparse reflectivity. Recent advancements in deep learning have introduced a deep convolutional neural network (DCNN) into high-resolution processing and relaxed it from rigorous physical assumptions. However, DCNN high-resolution processing often suffers from limited generalization capabilities, primarily due to the scarcity of labeled data and variations in data quality. In this study, we identify a frequency learning bias in DCNN high-resolution processing, in which the network initially prioritizes dominant-frequency components before gradually addressing lower and higher frequencies. This bias results in inadequate learning of high-frequency components. We develop a frequency-dependent multiscale network (FMN) informed by the frequency multiscale transformation theory. The FMN aims to improve the frequency learning direction of neural networks, enabling them to simultaneously and efficiently learn information across low-, dominant-, and high-frequency components. Our synthetic and 3D field data experiments demonstrate that our FMN outperforms SSD and DCNN methods, providing superior generalization and higher fidelity in producing high-resolution results.

Long‐term oil and gas exploitation in reservoir will lead to pore pressure depletion. The pore pressure depletion will result in changes of horizontal in‐situ stresses both in reservoirs and caprock formations. Using the geophysics logging data, the magnitude and orientation changes of horizontal stresses in caprock and reservoir are studied. Furthermore, the borehole stability can be affected by in‐situ stresses changes. To address this issue, the dehydration from caprock to reservoir and roof effect of caprock are performed. Based on that, the influence scope and magnitude of horizontal stresses reduction in caprock above the depleted reservoirs are estimated. The effects of development on borehole stability in both reservoir and caprock are studied step by step with the above geomechanical model.

Borehole instability problems are commonly encountered while drilling highly deviated and horizontal shale gas wells within the shale formations associated with high-dip bedding planes. An integrated rock mechanical study is described in this paper to evaluate the risk of the borehole instability problems in this area. First, a set of uniaxial compressive tests are carried out to measure the strength of the bedding shales on cores with different angles between the load direction and the bedding planes. A critical strength criterion is then proposed based on the test results. Next, the stress state of the borehole with arbitrary inclination and azimuth is determined through coordinate transformations. Finally, through combining the strength criterion and the stress state of the borehole, the risk of borehole instability is investigated for deviated and horizontal wells in shale formations with different bedding dips (0–90°) and dip directions (45° and 90° to the direction of minimum horizontal stress ${\sigma }_h$). The results show the dependence of borehole instability on the orientation of bedding planes of the formation as well as inclination and azimuth of the well. The most desirable borehole trajectory from the viewpoint of borehole stability is at the direction normal to the bedding planes. For a horizontal well specifically, if the bedding direction is perpendicular to the direction of ${\sigma }_h$, the risk of instability is relatively high for most drilling directions except drilling along the dip direction of the bedding planes. However, if there is a moderate acute angle (e.g., 45°) between the dip direction and the direction of ${\sigma }_h$, the risk of instability is relatively low for most drilling directions unless drilling along the direction of ${\sigma }_h$.

Deep drilling can lead to the encounter of complex geological conditions, with significant overburden pressure leading to a narrow safety window for mud density. In this study, we deviated wellbore instability conditions using the Mohr–Coulomb and tensile failure criteria, solving for collapse, shear, and fracture pressure using Newton’s method. The safe mud density window is defined between the maximum value of pore and collapse pressures and the minimum value of shear and fracture pressures. The analysis of the Anderson fault stress model, utilizing this method, enables a comprehensive investigation of how the safety mud density window varies with wellbore inclination and azimuth angles under various stress conditions. Additionally, applications in Chinese oilfields illustrate that this methodology can accurately calculate and analyze extremely narrow safety mud density windows at depths ranging from 2000 to 3000 m. In conclusion, this method enables rapid and accurate prediction of mud density limits, improving wellbore stability and reducing drilling risks.