The Longtan Formation of the Upper Permian in the Sichuan Basin has become a significant target for shale gas exploration in recent years. Multiple methods, including outcrop observations, thin sections, total organic matter content, X-ray diffraction and scanning electron microscopy were used to investigate the mineralogy, shale lithofacies assemblages and their relationships with the deposition environment. The mineral composition of the Longtan Formation has strong mineral heterogeneity. The TOC values of the Longtan Formation have a wide distribution range from 0.07% to 74.67% with an average value of 5.73%. Four types of shale lithofacies assemblages of the Longtan Formation could be distinguished, as clayey mudstone (CLS), carbonaceous shale (CAS), siliceous shale (SS) and mixed shale (MS) on the basis of mineral compositions. The TOC values of various types of shale lithofacies assemblages in the Longtan Formation varied widely. The shore swamp of the Longtan Formation is most influenced by the terrestrial input and mainly develops CLS and MS. The tidal flat is influenced by the terrestrial input and can also deposit carbonate minerals, developing CLS, CAS and MS. The shallow water melanged accumulation shelf develops CAS and MS, dominated by clay and carbonate minerals. The deep water miscible shelf develops CLS and SS, whose mineral composition is similar to that of the shore swamp, but the quartz minerals are mainly formed by chemical and biological reactions, which are related to the Permian global chert event. The depositional environment of the Longtan Formation controls the shale mineral assemblage of the Longtan Formation and also influences the TOC content.

Granular samples are often used to characterize the pore structure of shale. To systematically analyze the influence of particle size on pore characteristics, case studies were performed on two groups of organic-rich deep shale samples. Multiple methods, including small-angle neutron scattering (SANS), low-pressure nitrogen gas adsorption (LP-N₂GA), low-pressure carbon dioxide gas adsorption (LP-CO₂GA), and XRD analysis, were adopted to investigate how the crushing process would affect pore structure parameters and the fractal features of deep shale samples. The research indicates that with the decrease in particle size, the measurements from nitrogen adsorption and SANS experiments significantly increase, with relative effects reaching 95.09% and 51.27%, respectively. However, the impact on carbon dioxide adsorption measurements is minor, with a maximum of only 8.97%. This suggests that the comminution process primarily alters the macropore structure, with limited influence on the micropores. Since micropores contribute the majority of the specific surface area in deep shale, the effect of particle size variation on the specific surface area is negligible, averaging only 16.52%. Shales exhibit dual-fractal characteristics. The distribution range of the mass fractal dimension of the experimental samples is 2.658–2.961, which increases as the particle size decreases. The distribution range of the surface fractal dimension is 2.777–2.834, which decreases with the decrease in particle size.

Deep-learning-based (DL-based) seismic inversion has emerged as one of the state-of-the-art research areas in exploration geophysics with the development of artificial intelligence technology. Due to its good portability and high computational efficiency, this method has emerged as a data-driven approach for estimating subsurface properties. However, most of the current DL-based methods rely solely on seismic data, lacking the incorporation of prior information. In addition, these methods are usually performed trace-by-trace, resulting in insufficient horizontal constraints. These limitations make traditional methods less robust, particularly when dealing with high noise levels or limited data. To address these challenges, we propose a multi-input deep learning network for pre-stack inversion, which combines data-driven and model-driven approaches for optimization. The proposed method separately extracts features from the model and data, merging them to improve feature utilization. Moreover, by adopting a 2-D training unit, rather than a trace-by-trace approach, the method improves the horizontal continuity of the results. Tests on synthetic and real seismic data confirmed the robustness and improved stability of the proposed method, even under challenging conditions. This dual-driven approach significantly enhances the reliability of seismic inversion.

With the development of shale gas horizontal well-filling technology, by drilling infill wells between wells, the well spacing is continuously reduced to make shale reservoir reconstruction more effective. However, in shale gas reservoirs in China, the problem of inter-well interference is becoming increasingly serious, which not only affects the production of well groups but also causes wellbore damage. Currently, the process of interference in the production process is unclear. This study addresses the inter-well interference issue in deep shale gas reservoirs. An integrated numerical simulation method combining the Discrete Fracture Network, Finite Element Method, and Finite Difference Method is proposed. A comprehensive reservoir numerical model considering the production process is proposed. According to the actual reservoir model parameters and operation parameters, a multi-factor analysis model under multiple production conditions was established. Cumulative gas production and inter-well interference were analyzed. Finally, a field model was established, and the history matching of formation pressure was carried out. According to the history-matching results, the pressure expansion range in the production stage was analyzed. These research results provide a scientific basis and practical suggestions for the effective management and mitigation of inter-well interference and are expected to play an important role in practical engineering applications.

Shale gas is a critical energy resource, and estimating its ultimate recoverable reserves (EUR) is a key indicator for evaluating the development potential and effectiveness of gas wells. To address the challenges in accurately predicting shale gas EUR, this study analyzed production data from 200 wells in the CN block. Sixteen potential factors influencing EUR were considered, and key geological, engineering, and production factors were identified using Spearman correlation analysis and mutual information methods to exclude highly linearly correlated variables. An attention mechanism was introduced to weight input features prior to model training, enhancing the interpretability of feature contributions. The hyperparameters of the model were optimized using the Rabbit Optimization Algorithm (ROA), and 10-fold cross-validation was employed to improve the stability and reliability of model evaluation, mitigating overfitting and bias. The performance of four machine learning models was compared, and the optimal model was selected. The results indicated that the ROA-CatBoost-AM model exhibited superior performance in both fitting accuracy and prediction effectiveness. This model was subsequently applied for EUR prediction and for identifying the primary factors controlling productivity, providing effective guidance for development practices. The dominant factors and production forecasts determined by the model offer valuable references for optimizing block development strategies.

Ensuring the sustainability of energy is pivotal for achieving a harmonious balance between environmental conservation and economic growth. The mechanical behavior of deep shale reservoir rocks is intricate, presenting challenges in ascertaining their brittleness characteristics. To address this, the study employed a suite of evaluation techniques, encompassing analyses of stress-strain curve attributes, energy dissipation patterns, and mineral composition profiles. The overarching goal was to delineate the variations in deep shale brittleness as a function of depth. The findings indicate a general trend of decreasing shale brittleness with increasing depth. However, the brittleness indices derived from the three distinct evaluation methods varied, with the mineral composition approach yielding the most scattered results. This disparity underscores the heterogeneity of deep shale, likely due to its varied diagenetic history compared to shallower formations. In response to these observations, the study leveraged the principle of weighted averaging to devise a composite brittleness evaluation method. This innovative approach not only integrates the effects of multiple influencing factors but also accounts for the differential impact and weight of each method on the overall brittleness assessment. By doing so, it offers a more nuanced and holistic understanding of shale brittleness. The paper’s exploration of deep shale’s brittleness characteristics contributes valuable insights for the exploration and development of deep shale reservoirs, enhancing the strategic and operational frameworks within the energy sector. This comprehensive evaluation method serves as a foundation for more informed decision-making, ensuring that energy extraction is conducted in a manner that is both economically viable and environmentally responsible.