The process of CO₂ waterless fracturing and enhanced production of shale gas involves a physical and chemical reaction between supercritical carbon dioxide (SC-CO₂), brine, and shale rock, and this reaction can alter the physical and mechanical properties of shale rock. However, there has been limited investigation into the evolution of anisotropic mechanical characteristics. Therefore, uniaxial compression experiments were conducted on shale samples with varying bedding angles, soaked in SC-CO₂ + brine for different durations. The evolution of shale strength, elasticity, failure mode, acoustic emission (AE) signal, and fractal dimension under varying bedding angles and soaking times was analyzed, and the evolution characteristics of shale anisotropy were defined. The results indicate that: An increase in soaking time results in a notable softening of the complete stress-strain curve, accompanied by a gradual decline in uniaxial strength and elastic modulus, a gradual increase in peak strain and Poisson's ratio, and a gradual intensification of the shale dilatation phenomenon. The AE signals in the compaction and yield failure stages are significantly enhanced following soaking. The AE fractal dimension is observed to increase with the increase of bedding inclination and soaking time. This indicates that the complexity and irregularity of shale deformation and failure are stronger after soaking. The shale failure mode is closely related to the bedding inclination and soaking time. For bedding inclinations of 45° and 60°, shear failure along the bedding plane is the predominant mode of failure, and the shale failure that occurs after soaking is prone to produce more secondary cracks, resulting in a more thorough degree of shale failure. Following prolonged immersion of SC-CO₂ + brine, the anisotropy of shale strength, elasticity, acoustic emission signal, and acoustic emission fractal dimension is markedly augmented. This phenomenon can be attributed to the ease with which SC-CO₂ + brine invades along the bedding plane, thereby continuously weakening interbedding cementation. This, in turn, results in a gradual increase in the difference between the bedding plane and the matrix, which significantly enhances the anisotropy.

Horizontal in-situ stress is the key basic parameter of wellbore stability analysis and hydraulic fracturing, but the geological environment of deep formations is complicated and hidden, which makes it difficult to predict the horizontal in-situ stress accurately and quickly. Considering that the traditional logging interpretation and the neural network model cannot describe the spatial correlation between logging data and in-situ stress, a horizontal in-situ stress prediction method based on a Bidirectional Long Short-Term Memory neural network (Bi LSTM) was proposed. Taking two vertical wells in the CL gas field in the Sichuan Basin as an example, two vertical wells were taken as the training well and test well respectively, and the nonlinear mapping relationship between logging parameters and in-situ stress was established through the training well, so as to realize the prediction of horizontal in-situ stress of the test well. Combined with the correlation of logging parameters and the actual geological meaning, the prediction effect of horizontal in-situ stress under different combination modes of logging parameters was investigated. The results indicated that: (1) Comparing the logging interpretation and core differential strain testing results, it is found that the logging interpretation error of vertical stress is 0.39%, the logging interpretation error of maximum horizontal in-situ stress is 0.18%~0.64%, and the logging interpretation error of minimum horizontal in-situ stress is 0.29%, which indicated that the logging interpretation is in good agreement with the actual in-situ stress. (2) The order of in-situ stress in the working area is vertical stress＞maximum horizontal in-situ stress＞minimum horizontal in-situ stress, which belongs to potential normal fault stress state. (3) There is a strong positive correlation between horizontal in-situ stress and true vertical depth (TVD), density (DEN), and natural gamma ray (GR), and a negative correlation between horizontal in-situ stress and interval transit time of P-wave (DTC), borehole diameter (CAL), compensated neutron (CNL) and interval transit time of S-wave (DTS). (4) Different combination modes of logging parameters have different prediction effects on horizontal in-situ stress, the optimal combination of logging parameters is TVD, CAL, DEN, CNL, GR, and DTC. (5) Orthogonal experiments are designed to optimize hyper parameters, and the average absolute percentage errors of maximum and minimum horizontal in-situ stress are 0.48‰ and 0.50‰, respectively. It is concluded that the BiLSTM model can effectively capture the variation trend of logging parameters with depth and the correlation information of logging parameters, and it can realize the accurate prediction of horizontal in-situ stress.

The progressive application of artificial intelligence technology within oil and gas exploration has resulted in an inevitable shift towards the transformation of geomechanical parameter prediction from a traditional to an intelligent approach. This paper presents a comprehensive review and critical analysis of machine learning algorithms in the direct and indirect prediction of rock mechanics parameters, pre-drilling prediction, monitoring while drilling and post-drilling evaluation of formation pore pressure, 1D in-situ stresses and 3D in-situ stresses field prediction. Furthermore, the paper compared machine learning models, input parameters, sample data volume, output parameters, and model prediction performance under different tasks. It has been demonstrated that machine learning algorithms exhibit superior performance in terms of accuracy, timeliness, and applicability in geomechanical parameter prediction compared to laboratory tests, field tests, and empirical model calculations. The current research emphasis is on hybrid models, deep learning models, and physical-constrained neural network models, which have been validated as highly accurate, robust, capable of generalization, and easily interpretable. However, the existing research primarily concerns the prediction of 1D geomechanical parameters post-drilling. Consequently, it is not possible to effectively predict 3D geomechanical parameters prior to drilling or during the drilling process. In order to facilitate the digital and intelligent transformation of geomechanical parameters, an intelligent prediction framework for geomechanical parameters is proposed in this paper. This framework considers the influence of multi-source data, including seismic, logging, and mud log data on the prediction of geomechanical parameters. The machine learning model, which is driven by data and physics, enables the prediction of 3D geomechanical parameters. This model is updated in real-time through the most recent drilling data, thus allowing for the pre-drilling prediction, monitoring while drilling and post-drilling evaluation of regional 3D geomechanical parameters. In addition, the key technical problems facing the intelligent prediction of geomechanical parameters are identified: (1) The transformation of unstructured data types should be minimized, the complexity of the data set should be reduced, and the consistency and comparability of the data should be ensured. (2) Multi-source data fusion should be conducted, and multi-source data sets, including seismic, logging, mud log, laboratory tests, and field test data, should be constructed. Subsequently, data processing and feature selection should be performed. (3) Machine learning models should be enhanced to improve performance, integrated models should be adopted to improve prediction accuracy, and mechanism models and domain knowledge should be integrated to enhance model robustness and explainability.