The precise determination of minimum miscible pressure is of great importance for CO₂ enhanced oil recovery and storage as it directly influences the efficiency of pore-scale oil displacement and CO₂ trapping. In this study, an interpretable machine learning framework is developed, enabling the reliable evaluation of nano-confined minimum miscible pressure. Four machine learning algorithms (Random Forest, Multi-layer Perceptron, Support Vector Regression, and eXtreme Gradient Boosting) are employed to accurately predict the nano-confined minimum miscible pressure of a CO₂-oil system. The results demonstrate that, excluding support vector regression, the determination coefficients for all models surpass 94%, signifying the robust predictive performance of our model. Subsequently, Shapley Additive exPlanations is used to analyze the feature importance ranking and the impact of each input feature on minimum miscible pressure in these models. Based on the interpretation results, our multi-layer perceptron model is superior in mining the input-output relationship and reflecting the petrophysical laws, rendering it highly suitable for predicting the minimum miscible pressure while considering nano-confinement. In addition, it is found that pore size significantly influences minimum miscible pressure prediction and that minimum miscible pressure decreases with decreasing pore size when the pore size is ≤75 nm. Single-factor sensitivity analysis is applied to validate the trend patterns between input features and minimum miscible pressure in the multi-layer perceptron model.

Despite the promising results obtained from the utilization of interfacial-active additives in enhancing imbibition-based oil recovery from tight reservoirs, the predominant mechanisms governing this process remain inadequately understood. In this work, a meticulously designed workflow is implemented to conduct experiments and modeling focusing on imbibition tests performed on tight sandstone cores while utilizing surfactant and microemulsion. Our primary objective is to investigate the response of oil recovery to these additives and to develop a robust and reliable model that incorporates the intricate interactions, thereby elucidating the underlying mechanisms. Two imbibition fluids are designed, namely, surfactant and microemulsion. A comprehensive investigation is performed to analyze the physicochemical properties of these fluids, encompassing phase behavior, density, viscosity, and wettability alteration, with the aim of establishing fundamental knowledge in the field. Three imbibition tests are carried out to observe the response of oil production and optimize the experimental methodology. A numerical model is developed that fully couples the evolution of relative permeability and capillary pressure with the dynamic processes of emulsification, solubilization and molecular diffusion. The results demonstrate the crucial role of emulsification/solubilization in the imbibition process.

The oil production rate decreases rapidly after a short period of high yield from acidizing or fracturing in low-permeability reservoirs. In this paper, nanospheres are applied before the fracturing step, which possess the ability to absorb water and expand in the water layer, reducing the flow capacity of bottom water and finally enhancing the oil recovery. The plugging performance is investigated by nanosphere displacement experiments in cores and sand-packs, which explores the plugging effect in the oil layer, the oil-water transition zones, the water layer and the fracturing zones. In addition, a nuclear magnetic resonance experiment is conducted to study the flow mechanism of nanospheres and determine the plugging rates, which can characterize the plugging performance of nanospheres in porous media. The results show that the plugging rate is 85.84% and 78.65% on the water layer and oil-water transition zone, respectively, and 94.36% in the fracturing zone. Meanwhile, the nanospheres cannot plug the oil layer. The formation pressure has a less considerable effect on the plugging performance of nanospheres. The nanospheres have good injectivity, and the intensity variations in small, medium and large pores account for 34.46%, 13.22% and 52.32%, respectively. Overall, this paper explores the feasibility of applying nanospheres for water plugging and enhanced oil recovery.