Accurate evaluation of total organic carbon (TOC) content and porosity is of paramount significance for assessment and target interval selection for shale reservoirs. This study takes shales from the western Chongqing area as an exemplary case to delve into the applicability and reliability of ensemble learning in evaluating TOC content and porosity. The results indicate that although both Light Gradient Boosting Machine (LightGBM) and Random Forest (RF) algorithms are suitable for evaluating TOC content and porosity in shales, LightGBM algorithm is preferred due to its comprehensive advantages, including higher accuracy, stronger generalization capability, and faster operating speed. For TOC content evaluation, the four most important logging parameters identified by LightGBM and RF are consistent, but exhibit different orders: DEN (compensated density) > GR (gamma ray) > U (uranium) > CNL (compensated neutron) and DEN > U > GR > CNL, respectively. For porosity evaluation, LightGBM and RF identify the same type and order of the three most important logging parameters: AC (acoustic transit time) > DEN > U. This similarity may be attributed to the fact that both algorithms utilize Classification and Regression Tree (CART) as base learners. The dependence plots between SHAP (SHapley Additive exPlanations) values and logging parameters reveal that the role of each logging parameter in the evaluation model is segmented, rather than exhibiting a continuous linear contribution. In conclusion, given the exceptional performance of ensemble learning algorithms, they, especially LightGBM algorithm, are highly recommended for shale evaluation.

Conventional methods, represented by multivariate linear/nonlinear regression, empirical formulas, and petrophysical models, struggle to adequately capture the complex high-dimensional nonlinear relationships between logging responses and reservoir parameters, resulting in inherent limitations in shale reservoir type predictions. This work focuses on deep shale reservoirs from the Upper Ordovician Wufeng Formation (O₃ w) and the Lower Silurian Longmaxi Formation, Member 1, Submember 1 (S₁ l ₁ ¹) in the western Chongqing area, Sichuan Basin. Two schemes that identify deep shale reservoir types based on Light Gradient Boosting Machine (LightGBM) algorithm were established, followed by rigorous selection of the optimal scheme. Subsequently, the SHapley Additive exPlanations (SHAP) algorithm was implemented to quantitatively evaluate the importance of logging curves. The optimized model was ultimately deployed for comprehensive reservoir grading evaluation in the target area. The results demonstrate that compared to regression-based scheme, classification-based scheme not only substantially reduces model complexity for deep shale reservoir identification but also achieves remarkable improvements in computational efficiency and predictive performance. For the classification-based scheme, weighted precision (WP) and weighted recall (WR) metrics on the testing data set attained 90.5% and 90.4%, respectively, outperforming those of the regression-based scheme at 85.9% and 86.1%, respectively. Feature importance analysis via SHAP revealed that compensated density (DEN), gamma ray (GR), and compensated neutron (CNL), exert the most significant influence on type I and III reservoir identification, while DEN, acoustic transit time (AC), and GR dominate type II reservoir identification. The dependence plots elucidate complex nonlinear relationships between logging responses and reservoir classification outcomes. The grading evaluation in the target area indicates that type I reservoirs predominantly occur in the Upper O₃ w and bed 1 of S₁ l ₁ ¹ (S₁ l ₁ ¹-1). The Bayesian-optimized LightGBM algorithm enables efficient and accurate identification of deep shale reservoir types, providing a novel approach for grading evaluation of deep shale reservoirs.

A breakthrough has been achieved in shale gas exploration of the Lower Carboniferous Shale in the Yaziluo Rift Trough, Dianqiangui Basin, with Well SY-1 yielding a daily gas production of 1.1 × 10⁴ m³. To clarify the main controls and evolutionary patterns of shale pore structure, shale samples from different sedimentary environments were analyzed using TOC content, X-ray diffraction (XRD), low-pressure gas adsorption (CO₂ and N₂), and field emission-scanning electron microscopy (FE-SEM). The results show that shale from the basin sedimentary environment (BSE) exhibits the highest TOC, is dominated by siliceous minerals (quartz + feldspar), and contains minor carbonate minerals (calcite + dolomite). Shale from the upper slope sedimentary environment (USSE) has the lowest TOC and is rich in carbonate minerals. The lower slope sedimentary environment (LSSE) shows intermediate compositions. From BSE to USSE, pore volume and specific surface area decrease, while fracture development increases. A quantitative model for volumes of organic pores, clay mineral-associated pores, and brittle mineral-associated pores was established. Organic pores dominate in BSE shale (65.42%), followed by clay mineral-associated and brittle mineral-associated pores, while inorganic pores dominate in USSE shale (63%). Pore structure in BSE and LSSE is primarily controlled by TOC content, with pore volume and surface area increasing with TOC content, while mesopore development is influenced by organic matter type and mineral compositions. In USSE, pore structure is mainly governed by inorganic minerals, with clay minerals promoting pore volume and surface area development, whereas brittle minerals facilitate the preservation of macropores. Evolutionary models of pore development were established for these distinct sedimentary environments.