CO₂-enhanced oil recovery (CO₂-EOR) with water-alternating-gas (WAG) injection offers the dual benefit of boosted oil production and CO₂ storage, addressing both energy needs and climate goals. However, designing CO₂-WAG schemes is challenging; maximizing oil recovery, CO₂ storage, and economic returns (net present value, NPV) simultaneously under a limited simulation budget leads to conflicting trade-offs. We propose a novel closed-loop multi-objective framework that integrates high-fidelity reservoir simulation with stacking surrogate modeling and active learning for multi-objective CO₂-WAG optimization. A high-diversity stacking ensemble surrogate is constructed to approximate the reservoir simulator. It fuses six heterogeneous models (gradient boosting, Gaussian process regression, polynomial ridge regression, k-nearest neighbors, generalized additive model, and radial basis SVR) via a ridge-regression meta-learner, with original control variables included to improve robustness. This ensemble surrogate significantly reduces per-evaluation cost while maintaining accuracy across the parameter space. During optimization, an NSGA-II genetic algorithm searches for Pareto-optimal CO₂-WAG designs by varying key control parameters (water and CO₂ injection rates, slug length, and project duration). Crucially, a decision-space diversity-controlled active learning scheme (DCAF) iteratively refines the surrogate: it filters candidate designs by distance to existing samples and selects the most informative points for high-fidelity simulation. This closed-loop cycle of “surrogate prediction → high-fidelity correction → model update” improves surrogate fidelity and drives convergence toward the true Pareto front. We validate the framework of the SPE5 benchmark reservoir under CO₂-WAG conditions. Results show that the integrated “stacking + NSGA-II + DCAF” approach closely recovers the true tri-objective Pareto front (oil recovery, CO₂ storage, NPV) while greatly reducing the number of expensive simulator runs. The method’s novelty lies in combining diverse stacking ensembles, NSGA-II, and active learning into a unified CO₂-EOR optimization workflow. It provides practical guidance for economically aware, low-carbon reservoir management, demonstrating a data-efficient paradigm for coordinated production, storage, and value optimization in CO₂-WAG EOR.

Understanding the CO₂ displacement mechanism in ultra-low-permeability reservoirs is essential for improving oil recovery. In this research, a series of displacement experiments were conducted on sandstone core samples from the Chang 6 reservoir in the Huaziping area using a multifunctional core displacement apparatus and Nuclear Magnetic Resonance (NMR) technology. The experiments were designed under conditions of constant pressure, variable pressure, and constant effective confining stress to simulate various reservoir scenarios. The results indicated that the distribution characteristics of the pore structure in the rock samples significantly influenced the CO₂ displacement efficiency. Specifically, under identical conditions, rock cores with a higher macropore ratio exhibited a significantly enhanced recovery rate, reaching 68.21%, which represents a maximum increase of 31.97% compared to cores with a lower macropore ratio. Though fractures can facilitate CO₂ flowing through pores, the confining pressure applied during displacement caused a partial closure of fractures, resulting in reduced rock permeability. Based on the oil-to-gas ratio and oil recovery in the outlet section of the fractured rock samples, the CO₂ displacement process exhibited five stages of no gas, a small amount of gas, gas breakthrough, large gas channeling, and gas fluctuation. Although the displacement stage of different cores varies, the breakthrough stage consistently occurs within the range of 2 PV. These insights not only enhance our understanding of CO₂ displacement mechanisms in low-permeability reservoirs but also provide actionable data to inform the development of more effective CO₂-EOR strategies, significantly impacting industrial practices.

Understanding the CO2 displacement mechanism in ultra-low permeability reservoirs is essential for improving oil recovery. In this research, a series of displacement experiments were conducted on sandstone core samples from the Chang 6 reservoir in the Huaziping area, using a multifunctional core displacement apparatus and Nuclear Magnetic Resonance (NMR) technology under conditions of constant pressure, variable pressure, and constant effective confining stress. The results revealed that the distribution characteristics of pore structure in the rock samples were critical factors influencing CO2 displacement efficiency. Under the same conditions, cores with more large pores exhibited higher oil recovery. Though fractures can facilitate CO2 flowing through pores, but the confining pressure applied during displacement caused partial closure of fractures, resulting in reduced rock permeability. Based on the oil-to-gas ratio and oil recovery in the outlet section of fractured rock samples, the CO2 displacement process exhibited five stages of no gas，a small amount of gas, gas breakthrough, large gas channeling, and gas fluctuation. Although the displacement stage of different cores is different, it is in the breakthrough stage in the range of 2PV.

Compressed air energy storage in aquifers (CAESA) is a promising technology for large-scale, long-duration energy storage. The initial bubble, also known as cushion gas, is a prerequisite for system operation, as it creates the storage space and provides pressure support. However, the optimal amount of cushion gas needed to satisfy both energy storage scale and system cycle time (SCT) remains insufficiently studied. In this work, we investigate the relationship between cushion-gas masses and SCT under various energy storage scales using numerical simulations, and further analyze its impact on the maximum achievable energy storage scale through an orthogonal design encompassing nine geological conditions. Simulation results indicate that aquifer permeability, depth, and thickness impose a physical upper limit on achievable storage scales. Below this threshold, increasing cushion-gas mass approximately linearly enhances SCT, while beyond it, performance gains saturate. The effect of the air bubble on system performance is also influenced by well screen length. Sensitivity analysis suggests that larger injection masses are beneficial under high-permeability and deeper burial conditions, whereas excessive injection under unfavorable geological conditions can lead to inefficiency and wasted resources. Based on these findings, the recommended injection gas masses for different energy storage scales under the ideal model are provided, along with suggestions for gas injection configurations based on various geological conditions. This work provides a new approach for the design of initial bubble injection for a CAESA system.

Defining the near-surface signal reflecting the deep sub-surface leakage is a critical challenge in the risk assessment of geologic carbon storage (GCS) projects, often exacerbated by decoupled deep-to-shallow modeling. This study quantifies the mass distribution and phase evolution of leaked CO₂ through deep reservoir-caprocks, intermediate aquifer, and near-surface soil, thereby showing the sub-surface retention characteristics and the detectability of near-surface signals. A geological model from the deep reservoir to the soil layer was constructed to simulate CO₂ leakage through the caprock and migration into overlying strata in 1000 years. Using the simulator of GPSFLOW, this study evaluates the evolution of fluid phases and the mass distribution during the injection for 100 years and the post-injection periods. The results indicate that (1) at the moment the injection ceases, 87.43–99.06% of the CO₂ remaining within the system is retained within the reservoirs, with less than 8.42% reaching the intermediate aquifer. Remarkably, although the CO₂ ultimately reaching the near-surface soil is less than 0.00073% of the total mass retained within the system, this mass accumulation translates to a concentration anomaly with a signal-to-noise ratio of 368 relative to the background baseline. (2) Sensitivity analysis reveals that the injection rate affects the timing of fluid transport—a tenfold increase in injection rate (from 3.17 to 31.7 kg/s) accelerates the upward movement of CO₂, advancing its arrival at the near-surface by 15 years without changing the overall mass partitioning. The permeability anisotropy ratio affects CO₂ migration and phase distribution—decreasing the vertical to horizontal permeability ratio (1, 0.5, 0.25, 0.125) reduces connectivity, which delays the upward transfer and increases the amount of the aqueous CO₂. However, specifically in the soil layer, the aqueous CO₂ accumulation reveals a non-monotonic trend that peaks at an intermediate ratio of 0.25. (3) CO₂ shows a cascading distribution across formations where reservoirs provide the primary storage, and the intermediate aquifer reduces the mass available for near-surface accumulation. This attenuation effect significantly reduces the CO₂ mass that reaches the soil layer, thereby controlling the strength and duration of near-surface environmental signals. This work offers a theoretical reference for formulating near-surface monitoring strategies for CO₂ leakage in GCS.