The estimated ultimate recovery (EUR) of a single well must be predicted to achieve scale-effective shale gas extraction. Accurately forecasting EUR is difficult due to the impact of various geological, engineering, and production factors. Based on data from 200 wells in the Weiyuan block, this paper used Pearson correlation and mutual information to eliminate the factors with a high correlation among the 31 EUR influencing factors. The RF-RFE algorithm was then used to identify the six most important factors controlling the EUR of shale gas wells. XGBoost, RF, SVM, and MLR models were built and trained with the six dominating factors screened as features and EUR as labels. In this process, the model parameters were optimized, and finally the prediction accuracies of the models were compared. The results showed that the thickness of a high-quality reservoir was the dominating factor in geology; the high-quality reservoir length drilled, the fracturing fluid volume, the proppant volume, and the fluid volume per length were the dominating factors in engineering; and the 360−day flowback rate was the dominating factor in production. Compared to the SVM and MLR models, the XG Boost and the RF models based on integration better predicted EUR. The XGBoost model had a correlation coefficient of 0.9 between predicted and observed values, and its standard deviation was closest to the observed values’ standard deviation, making it the best model for EUR prediction among the four types of models. Identifying the dominating factors of shale gas single-well EUR can provide significant guidance for development practice, and using the optimized XGBoost model to forecast the shale gas single-well EUR provides a novel idea for predicting shale gas well production.

The transitional shale system of the Longtan Formation (LTF) is widely distributed in the Sichuan Basin. However, the lithofacies of the LTF shale system exhibit vertical variations, with frequent interbedding of blocks, and shale–sand–coal sequences, which makes identifying “sweet spots” a challenging task. To address this issue, lithofacies associations were investigated based on well log analysis from 30 wells, and experimental data from 19 well samples, including X-ray diffraction, total organic carbon (TOC), pore structure characterization, and methane isothermal adsorption tests. Four lithofacies associations were classified: carbon–shale interbedding (I-1), shale(carbon)–coal interbedding (I-2), shale–sand interbedding (II), and shale–sand–coal assemblage (III). A favorable lithofacies association index (Com) was developed, providing a quantitative method for identifying favorable lithofacies. The results indicate that among the four lithofacies associations, I-2 is the most favorable lithofacies association. The Com index threshold for favorable lithofacies is defined as 0.6, and for the most favorable lithofacies, it is 0.7. Overall, favorable lithofacies are primarily distributed in the Suining-Dazu and Lujiao areas.

Transitional marine–continental shale reservoirs are typified by intricate pore architectures and pronounced heterogeneity; accurate characterization of their pore network and fluid mobility underpins reservoir appraisal and sweet-spot forecasting. Focusing on the Longtan Formation transitional shales in the Sichuan Basin, this study integrates NMR T₂ spectrometry, geochemical–mineralogical assays and multifractal analysis to elucidate multi-scale heterogeneity of the pore framework and its governing mechanisms. Results reveal that the investigated shales are characterized by low porosity (0.46–7.43%) and high bound fluid saturation (66.77–97.28%). Multifractal spectral width (Δα) and degree of multifractality (ΔD) serve as robust metrics of pore heterogeneity, correlating closely with rock composition (e.g., TOC and clay content). By combining multifractal indices, mineralogical assemblage and fluid movability, the samples are classified into three reservoir archetypes, with Type I (weakly heterogeneous—high quality) identified as the prospective developmental sweet spot. This work provides a theoretical and methodological backbone for quality assessment and play-ranking of transitional marine–continental shale reservoirs.

This study integrates microthermometry and laser-Raman spectroscopy of individual fluid inclusions with basin modelling to reconstruct the hydrocarbon-fluid evolution and multistage re-mobilisation of the Permian Longtan Formation transitional marine–terrestrial shale in the YJ-LJ area, southern Sichuan Basin. Systematic analysis of aqueous two-phase, methane-rich, and associated bitumen inclusions hosted in fracture-fill veins and sandy partings identifies four fluid episodes, enabling subdivision of petroleum evolution into five stages. Results show trapping pressure increasing with temperature to a maximum of 107.77 MPa, equivalent vitrinite reflectance (EqVR) between 1.49% and 2.49%, and formation-water salinity that first rises then falls, remaining within the high-salinity continental-leaching brine field. Coupled with thermal-history modelling, shale-oil/gas evolution is divided into: (1) low-pressure slow burial, (2) over-pressured rapid burial, (3) sustained over-pressured deep burial, (4) high-pressure uplift adjustment, and (5) late uplift adjustment. The study demonstrates that over-pressure has been partially preserved, providing critical palaeo-fluid and pressure evidence for exploring transitional marine-terrestrial shale gas.

Currently, pore fractal characteristics of deep marine–terrestrial transitional coal-measure mudstones in the central Sichuan Basin remain poorly understood. To clarify the pore fractal characteristics and their controlling factors, seven representative deep mudstone samples were collected from the Longtan Formation of Well NT1H in the Suining area, central Sichuan Basin. These samples were subjected to total organic carbon (TOC) content determination, vitrinite reflectance (Ro) measurement, X-ray diffraction (XRD) analysis of whole-rock and clay minerals, and low-pressure nitrogen adsorption (LPN₂A) experiments. Pore fractal dimensions were calculated based on the Frenkel–Halsey–Hill (FHH) theoretical model. The influences of mineral composition, organic geochemical characteristics, and pore structural parameters on pore fractal dimensions were analyzed. The results indicate that shale pores in the study area are predominantly developed as mesopores, exhibiting dual fractal characteristics; fractal dimension D1 (structural fractal dimension at high-pressure segment) ranges from 2.6662 to 2.7366, and fractal dimension D2 (surface fractal dimension at low-pressure segment) ranges from 2.5895 to 2.6363. Mineral composition exerts differential control over pore fractal dimensions. The effects of organic matter content and thermal evolution degree on fractal dimensions exhibit stage-dependent characteristics. Correlations between pore structural parameters and fractal dimensions indicate that small-aperture pores (micropores and mesopores) constitute the primary factor controlling pore heterogeneity in shales. These findings provide a theoretical basis for “reservoir evaluation” and “sweet spot” optimization of deep marine–terrestrial transitional coal-measure shales in central Sichuan Basin.

Characterization of shale pore architecture forms the scientific basis for effective shale gas exploitation. Deep LMX FM shale from the Luzhou area was analyzed using SANS, LTPA, XRD, and SEM. This study quantitatively characterized the pore structure, focusing on closed-pore development and connectivity, and explored lithological controls. Pore-size distribution shows that micropores and small mesopores dominate the pore volume, with an average median pore diameter of 5.17 nm. Closed pores are abundant, indicated by a high average closed-pore ratio of 28.98%, reflecting generally poor connectivity. Pores smaller than 5 nm contribute 88.12% of the total SSA. Both pore volume and SSA correlate positively with TOC. In organic-rich and moderately organic-rich siliceous shales, these parameters also correlate positively with quartz content. In contrast, for organic-rich mixed shales, they correlate positively with clay mineral content. Among the lithofacies, organic-rich siliceous shale possesses relatively larger pore volume and SSA, along with better pore connectivity, making it the most favorable reservoir facies. Based on pore-structure characteristics and the regional structural setting, we recommend adopting close-spacing hydraulic fracturing with reduced cluster spacing in structurally stable areas to enhance stimulation. In structurally complex areas, engineering designs should prioritize risk mitigation to ensure operational success.