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.