This paper studied the fracability of tight sandstone reservoirs by means of incorporating geomechanics properties and surrounding in situ stresses into a new model. The new fracability evaluation model consists of variables such as brittleness index, critical strain energy release rate index, horizontal stress difference, and minimum horizontal principal stress gradient. The probability of interconnection of a complex fracture network was quantitatively studied by the brittleness index and horizontal principal stress difference index. The probability of obtaining a large stimulated reservoir volume was evaluated by the critical strain energy release rate index and minimum horizontal principal stress gradient which also quantifies conductivity. This model is more capable of evaluating fracability, i.e., it agrees better with the history of production with a high precision and had correlation coefficients (R²) of 0.970 and 0.910 with liquid production of post-fracturing well testing and the average production of six months of post-fracturing, respectively. It is convenient that all model inputs were obtained by means of loggings. Using this model, tight sandstone reservoirs were classified into three groups according to fracability: Frac ≥ 0.3 MPa⁻¹·m for Type-I, 0.22 MPa⁻¹·m ≤ Frac < 0.3 MPa⁻¹·m for Type-II, and Frac < 0.22 MPa⁻¹·m for Type-III.

Horizontal well drills are difficult to operate and require high borehole cleaning operations. The impact of cuttings accumulation on friction and torque cannot be ignored. In the process of horizontal well drilling, it is very easy to form a cuttings bed in the highly inclined eccentric annulus. The formation of the cuttings bed will not only increase the friction torque but also have a greater impact on the annulus flow. Based on the application of gas drilling in horizontal wells, this paper uses laboratory experiments to study the influence of cuttings with different particle sizes and lithology on the friction coefficient between the drill string and the borehole wall of the horizontal well section. In addition, in view of the difficulty in the migration of cuttings in gas drilling horizontal wells and the formation of cuttings deposits, this paper carries out an experimental study on the effect of the cuttings bed on drill pipe coating height and cuttings bed thickness on friction coefficient. Experimental results show that the friction coefficient of gas drilling horizontal wells is about 0.44–0.58. When the coating height of the cuttings on the drill pipe exceeds a certain value (26 mm), the friction coefficient tends to be stable, but its value is as high as about 0.55. When the thickness of the accumulation of cuttings exceeds a certain value (10 mm), the subsidence hindering effect between the particles in the cuttings bed is weakened, so the friction coefficient of the casing section and the open hole section tends to be stable, about 0.53.

Accurate prediction of pore pressure is crucial for ensuring drilling safety and improving the efficiency of oil and gas development. However, regarding feature selection, most existing studies focus primarily on the correlations among features, with little consideration given to inter-well distribution differences; this may result in insufficient model generalization capabilities for cross-well prediction tasks. To improve cross-well prediction accuracy, this paper introduces the DASP (Domain Adaptation with SHAP-guided Particle Swarm Optimization) method for feature selection. Using 20 logging and rock mechanical parameters as input features, a four-stage selection process reduces the number of features to 12, achieving approximately 40% feature dimensionality reduction. In terms of model performance comparison, models such as RF (Random Forest), XGB (eXtreme Gradient Boosting), LGB (Light Gradient Boosting Machine), and CNN (Convolutional Neural Network) were constructed for comparative analysis. The results indicate that LGB performs better during the validation phase, while in the cross-well testing phase, RF achieves the best prediction accuracy among the base models, demonstrating strong generalization stability. Addressing the issue that CNNs still have room for further optimization in cross-well prediction, this study further refines their architecture by introducing an attention mechanism to enhance the model’s adaptive weighting capability for key features and combining it with a physical constraint mechanism to suppress non-physical prediction fluctuations, thereby improving the model’s stability and geological plausibility. Experimental results demonstrate that the improved model shows significant improvements in both error metrics and fitting capabilities. The combination of the DASP-based feature selection method and the improved CNN model effectively enhances the accuracy of cross-well pore pressure prediction, providing new technical insights and data support for intelligent pore pressure prediction and drilling safety decision-making.

By employing molecular dynamic (MD) and density functional theory (DFT) calculations, the adsorptions of CO₂, N₂, CO, H₂S, CH₄, and H₂O onto methane hydrate (MH) surface are compared in this work. The methane hydrate planes of (001) and (110) and various cleaving sites are compared with cleavage energies. MH(001) has more tendency to form when compared with MH(110) in thermodynamics. Two different terminations of MH(001) surfaces are compared, and MH(001)-I (terminated with CH₄+H₂O) leads to more negative adsorption energies when compared with MH(001)-II (terminated with H₂O only). The priority sequence of the adsorptions can be queued as: H₂O > H₂S > CO₂ > N₂ > CH₄ > CO. Namely, CO₂, N₂, and H₂S have potential to replace CH₄ in methane hydrate. The interfacial hydrogen bond and electronic interactions are clarified for the adsorptions of CO₂, N₂, and H₂S. The hydrogen bonds tend to form between O-H atom pairs of CO₂-H₂O, N-H atom pairs of N₂-H₂O, and S-H and H-O atom pairs of H₂S-H₂O, respectively. The bonds are mainly contributed from the dispersion interaction between the O-2p in CO₂ and H-1s in H₂O, N-2p in N₂ and H-1s in H₂O, S-3p in H₂S and H-1s in H₂O, and H-1s in H₂S and O-2p in H₂O, respectively.

In order to adapt to high requirements of undergraduates majored in petroleum engineering, this paper conducted a detailed analysis of problems currently existing in undergraduate teaching of rock mechanics in petroleum engineering. Based on this, it discussed about corresponding reform measures from aspects of teaching materials, teaching method, experimental setting and so on, expecting to improve undergraduate teaching quality of rock mechanics in petroleum engineering and cultivate applied talents meeting strategic requirements of China oil gas with engineering practice ability and innovative ability in theory and technology.

Formation pressure labels are often stored as equivalent mud weight (EMW), whereas engineering analysis requires true pressure and validation strategies that account for the strong depth dependence of borehole data. This study develops a dimensionally consistent pressure ratio symbolic regression framework in which vertical overburden stress provides the pressure scale and a compact dimensionless correction is learned from reference-scaled borehole variables. After converting EMW-based labels to MPa and applying transparent quality control criteria, 1877 of 2025 depth-indexed records were retained. Redundant and deterministically derived variables were identified through correlation analysis, variance inflation factors, principal component analysis, and deterministic relation checks and were excluded from the compact symbolic search. Five contiguous depth blocks with a 20 m purge zone were used for leakage-resistant validation, with symbolic-structure selection repeated within each outer training fold. The selected four-coefficient expression, comprising an intercept and three predictor-dependent terms, retained only depth and acoustic slowness. Fixed-structure depth-block validation yielded a coefficient of determination (R²) of 0.3008, a root mean square error (RMSE) of 3.5439 MPa, a mean absolute error (MAE) of 2.6964 MPa, and a mean absolute relative error (MARE) of 10.02%, while the conservative nested symbolic pipeline yielded MARE = 11.60%. External zero-shot evaluation on 974 samples from an external well, 98.36% of which were outside the calibration depth range, yielded R² = 0.0265, RMSE = 7.0024 MPa, MAE = 5.5723 MPa, and MARE = 11.51% against an independent D-exponent-based engineering pressure reference (PP_DX). Sparse local recalibration using 10 depth-spaced PP_DX engineering reference points, with ±20 m neighborhoods excluded from evaluation, improved performance to R² = 0.8684, RMSE = 2.8431 MPa, MAE = 2.1108 MPa, and MARE = 4.39% on the remaining 564 samples. These results indicate that the proposed framework provides an explicit and independently auditable pressure equation that preserves the overall pressure scale under substantial depth domain shift and can be efficiently recalibrated using sparse local pressure information. Site-specific calibration remains necessary for accurate reproduction of local pressure variations.