Shale pore volume is a critical parameter for reservoir evaluation. Accurate and rapid determination of this parameter is essential for identifying sweet spots and performing reliable reserve estimations. Currently, laboratory experiments remain the standard for determining pore volume; however, these methods are typically time-consuming, costly, and labor-intensive. To complement traditional experimental approaches, we developed a Gaussian Process Regression (GPR) model to estimate shale pore volume based on mineralogical compositions. The model is specifically tailored for the Longmaxi shale, utilizing six input features: the contents of Total Organic Carbon (TOC), clay, quartz, feldspar, carbonate, and pyrite. The GPR model achieved a mean absolute percentage error (MAPE) of 9.97% on the testing dataset, while it yielded an MAPE of 17.66% when applied to an additional independent validation set. Finally, a sensitivity analysis using the Shapley additive explanations was conducted to elucidate the influence of mineralogical constituents on shale pore volume.

Clay minerals are significant constituents of shale reservoirs, yet the confinement-induced phase behavior of hydrocarbons within clay nanopores has received comparatively less attention than in carbonaceous materials. In this study, Grand Canonical Monte Carlo (GCMC) simulations were performed to investigate the confinement-induced shifts in the critical properties of hydrocarbons within illite slit pores ranging from 2 to 20 nm. The simulation results indicate apparent reductions in both critical temperature (T_c) and critical pressure (P_c) under confined conditions. The relative shift in critical properties is more pronounced for n-pentane than for methane, which is attributed to the larger molecular size and complex chain-like structure of n-pentane compared to methane. The simulation results also show that the extent of these shifts varies among different pore geometries and materials due to the differences in fluid–solid interactions and specific surface areas. Illite exerts a weaker confinement effect than graphite, while cylindrical pores intensify the shift compared to slit pores. As the pore size increases from 2 to 20 nm, the nanoconfinement-induced shifts in the critical properties of alkanes in illite slit pores progressively diminish, and the critical properties approach their corresponding bulk values at a pore size of 20 nm. Finally, new correlations are proposed to quantify the critical property shifts in illite slit nanopores. Overall, this study provides a quantitative characterization of confinement-induced critical-property shifts for the investigated hydrocarbons in illite slit nanopores.