Deep coalbed methane (CBM) development faces significant challenges due to extreme geological conditions (high stress, elevated pressure, high temperature) that differ fundamentally from shallow reservoirs. Traditional productivity models developed for shallow CBM often fail to accurately predict deep reservoir performance. The complex “stress-desorption-flow” multi-field coupling mechanism, intensified under deep conditions, critically controls production dynamics but remains poorly understood. This study develops a multi-layer, commingled, coupled geomechanical-flow model for the Hujiertai deep CBM block (2140~2170 m) in Xinjiang, China. The model, integrating gas-water two-phase flow, Langmuir adsorption, and transient geostress evolution, was validated against field production data, achieving a low relative error of 1.2% in the simulated average daily gas rate. Results indicate that: (1) Geomechanical coupling is critical. The dynamic competition between effective stress compaction and matrix shrinkage limits fracture porosity reduction to ~2%, enabling a characteristic “rapid incline, 1–2-year plateau, gradual decline” production profile and significantly enhancing cumulative gas production. (2) Porosity (10~30%) is positively correlated with productivity: a 10-percentage-point increase raises the peak gas rate by 2.1% and cumulative production by 2.8%. Conversely, high initial cleat permeability boosts early rates but accelerates geomechanical damage (cleat closure), lowering long-term productivity. (3) Stimulation parameters show a trade-off. SRV only dictates short-term, near-wellbore production. Higher fracture permeability (peak rate +17% per 500 mD) boosts early output but accelerates depletion and stress-induced closure. The multi-field coupling mechanisms revealed and the robust model developed provide a theoretical basis for optimizing fracturing design and production strategies for analogous deep CBM plays.

The study of the mechanical properties of moderately consolidated sandstones is crucial for engineering safety assessments. As an effective research tool, the discrete element method (DEM) encounters challenges during the modeling phase, such as a large number of micromechanical parameters, low modeling efficiency, and unclear coupling mechanisms among multiple parameters. To address these issues, this paper proposes a calibration method for the micromechanical parameters of DEM models for moderately consolidated sandstones. By integrating orthogonal experimental design with a multivariate analysis of variance, the influence of micromechanical parameters on macroscopic mechanical properties is quantified, and a parameter prediction model is constructed using an intelligent dynamic regression selection mechanism, significantly improving the efficiency and accuracy of micromechanical parameter calibration. The results show that the macroscopic elastic modulus E is primarily controlled by the effective modulus ($\overline{E}$), stiffness ratio (k), and particle size ratio (R_max/R_min), following a linear relationship. The influence of the particle size ratio decreases significantly once it exceeds a threshold value. The macroscopic uniaxial compressive strength (UCS) is dominated by cohesion ($\overline{c}$) and tensile strength (${\overline{\mathrm{\sigma }}}_c$), exhibiting a polynomial relationship, where a stronger synergistic effect is generated when both parameters are at higher levels. Poisson’s ratio ($\mu$) is significantly correlated only with the stiffness ratio (k), following a logarithmic relationship. An iterative correction method for micromechanical parameter calibration is proposed. The errors between the three groups of simulation results and laboratory test results are all less than 10%, and the crack distribution patterns show a high degree of consistency. The findings of this study provide a theoretical foundation and technical means for exploring the mechanical behavior and damage mechanism of moderately consolidated sandstones.

Subglacial drilling through polar ice–rock transitional zones is frequently hindered by severe load fluctuations and instability induced by strong formation heterogeneity. This study investigates the coupled drilling mechanics across pure ice, an ice–rock mixture, and bedrock using a fracture-mechanics-based finite–discrete element method (F-DEM) with a strain-softening constitutive model for brittle ice. The simulations quantify the evolution of drilling force components and torque under varying gravel content, weight on bit (WOB), and rotational speed. Results show that drilling responses are strongly governed by formation-dependent mechanical behavior, transitioning from stable periodic fluctuations in pure ice to impact-dominated irregular variations in mixtures, and finally to high-level continuous resistance in bedrock. Rotational speed significantly influences drilling stability through its interaction with formation properties; lower speeds effectively suppress transient load fluctuations in pure ice and mixtures, whereas moderate speeds mitigate stick–slip effects in rock. Conversely, WOB primarily controls axial penetration while also influencing load fluctuation characteristics. The optimal WOB is identified as 10 kN for stable shearing in pure ice, reduced to 7.5 kN in mixtures to buffer lateral impacts, and increased to 10 kN in rock for efficient penetration and stable cutting. Furthermore, increasing gravel content amplifies force and torque sensitivity, transitioning the system from stable periodic behavior to impact-driven instability. These findings emphasize the necessity of a layer-dependent adaptive control strategy, providing a quantitative framework to optimize parameters and drill-bit design for safer, more efficient subglacial operations.

Ultra-deep shale in the Mahu Sag, characterized by difficult-to-drill formations, exhibits high resistivity. This study uses XRD and petrophysical testing on 12 dry core samples (depths 4600–5000 m) to characterize mineral composition and evaluate resistivity-influencing factors. Mineralogical analysis reveals that brittle minerals, dominated by quartz and feldspar (>50%), constitute the primary components of the ultra-deep shale in the Mahu Sag, with quartz, feldspar, and carbonates collectively accounting for ~80%. Clay (~6%) and pyrite (<5%) contents are notably low, resulting in elevated resistivities of 10⁵–10⁷ Ω·m. Resistivity correlates negatively with pyrite (r = −0.588) and feldspar (r = −0.319) but positively with dolomite (r = 0.209), quartz (r = 0.017), and porosity (r = 0.749). At elevated temperatures (100 °C), resistivity declines owing to enhanced ionic conduction. These findings clarify high-resistivity mechanisms, supporting resistivity-based drilling parameter optimization.

In China, a majority of the proven crude oil reserves are found in clastic rock reservoirs, which typically exhibit low natural energy levels. Water injection has become the most widely adopted technique for maintaining reservoir pressure and enhancing oil recovery in such formations. However, conventional water injection strategies heavily rely on empirical knowledge, often failing to accurately characterize the dynamic inter-well connectivity between injection and production wells. This limitation hinders the effective management of fluid injection and production processes. To address this challenge, we propose an intelligent optimization method for water allocation in high-water cut, low-permeability reservoirs. Our approach employs a Bidirectional Long Short-Term Memory (BiLSTM) neural network to learn the complex patterns from historical injection data in a data-driven manner. Furthermore, we design a well distance and time joint attention mechanism, which is integrated after the dual BiLSTM layers to enhance the model’s ability to capture the critical dynamic relationships among wells. This mechanism decouples temporal pattern recognition and the spatial physical constraints, laying the foundation for interpretable injection strategy optimization. We name this architecture “AttBiLSTM”, which is designed for optimizing injection strategies for individual layers in separate-layer water injection wells (The layer refers to the basic geological unit or flow unit within a vertically heterogeneous reservoir that is delineated and requires independent water injection regulation). Using field data from the Xinjiang Oilfield, we validate the proposed method and compare its performance against traditional water injection schemes and mainstream data-driven models. The experimental results demonstrate that the AttBiLSTM model effectively establishes a nonlinear mapping between the injection volumes and oil production rates, showing strong performance in both production prediction and injection optimization. An independent numerical reservoir simulation verification confirms that the optimized scheme increases well group oil production by over 3.6%, with no premature water breakthrough risk in a 5-year development cycle. This study provides a novel and practical technical framework for efficiently developing low-porosity, low-permeability, and highly heterogeneous reservoirs.