Low Permeability Oil Reservoirs Research Articles

Future potential research hotspots on the precise integration of geology and engineering in low-permeability oil reservoirs

Future potential research hotspots on the precise integration of geology and engineering in low-permeability oil reservoirs

Gas channeling control with CO2-responsive gel system in fractured low-permeability reservoirs: Enhancing oil recovery during CO2 flooding

During the CO2 flooding process in fractured low-permeability oil reservoirs, the injected CO2 is prone to channeling along fractures due to severe reservoir heterogeneity, resulting in poor development effect. The CO2-responsive gel system shows dual advantages in achieving CO2 capture and plugging gas channeling to enhance oil recovery. This paper constructed a system with good CO2 sensitivity based on long-chain alkyl amide propyl dimethyl tertiary amine first. Subsequently, the properties of the system before and after the response were evaluated through rheological test, and its microstructure was characterized by Cryo-TEM. The system exhibited good CO2 responsiveness, transitioning from low-viscosity solution system to high-viscosity CO2-responsive gel system upon contact with CO2, with its viscosity increasing by nearly five orders of magnitude. The CO2-responsive gel demonstrated excellent shear resistance, viscoelasticity and shear self-repairing ability. The change of microstructure further verified the mechanism of molecules self-assembly in the system under the action of CO2. Then, a series of core physical simulation experiments were carried out to comprehensively evaluate the effects of different factors on the injection capacity, plugging characteristics, dynamic filtration damage performance and EOR effect of CO2-responsive gel. The gel maintained injectability while achieving an exceptional deep plugging effect, and the plugging rate reached 98.77%. It showed good characteristics of low filtration and permeability damage in low permeability reservoirs, effectively ensuring the fracture plugging effect. After the fracture was plugged by gel, the sweep range of CO2 to the matrix significantly expanded, and the gas flooding recovery increased by 18.19–21.7%. Finally, the matrix-fracture dual-media chip model was used to conduct microfluidic experiment, the oil displacement characteristics in different displacement stages were visually clarified, and the synergistic plugging and oil displacement mechanism between the CO2-responsive gel and CO2 was summarized. The research results can provide important insights for the green and efficient application of CO2-responsive gel in fractured low-permeability reservoirs.

Experimental analysis of acidizing in Weizhou X low permeability reservoir

AbstractAiming at the problem of increased water injection pressure and poor water injection effect during the water injection operation of Weizhou X offshore low permeability oil reservoir. The cause of clogging was clarified using cast thin section experiments, water quality compatibility experiments and reservoir sensitivity experiments, and corresponding deblocking agents were configured based on the experimental results. The experimental results show that Weizhou X oilfield has strong velocity sensitivity (damage rate 85.35%) and strong salt sensitivity (damage rate 63.02%), and there is a phenomenon of water quality incompatibility. Analysis shows that the excessive velocity of the injected water causes the core particles to fall off and the water quality is incompatible with the calcium carbonate precipitation to cause pore throat blockage as the fluid migrates to the small roar, which is the main reason for the increase in water injection pressure. Based on the analysis results, the acid solution formula was optimized and determined to be: 12% HCl + 0.5% HF + 3% CH3COOH + 0.5% C6H12N4. Indoor test results show that the acid has good clay swelling prevention and reservoir modification effects, and the average reservoir modification rate is 129.21%. The plug‐removing effect is remarkable and can be promoted in similar oil fields.

Analysis of reservoir damage and microscopic seepage simulation in low permeability oil and gas reservoirs based on pore topology structure

This paper investigates the potential factors contributing to reservoir damage in low permeability reservoirs, based on the micro-characteristics of pore throats. Through the utilization of numerical simulations, we investigate the micro-permeability behavior of fluids within these low permeability reservoirs. The simulations produce a micro-numerical field distribution of fluid within the reservoir (comprising velocity field, pressure field, and phase field), facilitating an analysis of evolving patterns and influencing mechanisms between oil and water phases during displacement processes. The simulation results indicate that with an increase in the number and diameter of plugged pores, there is a significant decrease in reservoir permeability. The permeability of pores smaller than 3.0 μm decreases to 92% of the original value, while that of pores smaller than 3.5 μm drops to 87%, and that of pores smaller than 5.0 μm decreases to 82%. The rock stress sensitivity effect leads to a reduction in permeability, with a 94% decrease when pore deformation reaches 95%, and an 86.5% decrease at a deformation level of 85%. Leveraging these simulation results and considering potential formation damage that may occur during oil and gas field development processes, we propose targeted formation damage controlling measures to provide theoretical underpinning for efficient development strategies in low permeability reservoirs.

Development and performance evaluation of a novel SiO2-enhanced seawater-based temperature-resistant clean fracturing fluid

Hydraulic fracturing has been proposed as a potential technology for the development of low-permeability oil reservoirs and also has promising application prospects offshore. In this study, a novel SiO2-enhanced seawater-based temperature-resistant clean fracturing fluid was formulated. The fracturing fluid main agents, additives and reducing agents were screened. Besides, the physical and chemical properties (rheology) as well as application (i.e., sand-carrying, gel-breaking, dynamic fluid loss, dynamic damage and anti-swelling) performance of the proposed SiO2-enhanced seawater-based temperature-resistant clean fracturing fluid were systematically investigated. It was revealed that 3.2 wt% AASB-17+1.92 wt% NaSal+0.1 wt% SC-107+0.1 wt% TS3 was the optimal SiO2-enhanced seawater-based clean fracturing fluid system formula. The SiO2-enhanced seawater-based temperature-resistant clean fracturing fluid exhibited remarkable rheological characteristics, the temperature and shear resistance was increased by 28 %, with a maximum temperature resistance of 90ºC. This system can be applied to the fracturing development of most oil reservoirs in the Bohai Bay. In addition, the presence of SiO2 nanoparticles significantly improved the sand-carrying properties of the proposed clean fractuirng fluid system. The experimental results also suggested that the SiO2-enhanced seawater-based temperature-resistant clean fracturing fluid showed excellent performance of shear recovery (fixed shear viscosity recovery rate was 100 %), gel breaking (30 min,1 mPa·s), filter loss (Cw=4.75×10−4 m/min1/2), anti-swelling (anti-swelling rate was 77.78 %) and salt tolerance. This study provides fundamental technical support for the application of SiO2-enhanced seawater-based temperature-resistant clean fracturing fluid in offshore fracturing.

Application of Machine Learning and Optimization of Oil Recovery and CO2 Sequestration in the Tight Oil Reservoir

Summary In recent years, shale and tight reservoirs have become an essential source of hydrocarbon production since advanced multistage and horizontal drilling techniques were developed. Tight oil reservoirs contain huge oil reserves but suffer from low recovery factors. For tight oil reservoirs, CO2-water alternating gas (CO2-WAG) is one of the preferred tertiary methods to enhance the overall cumulative oil production while also sequestering significant amounts of injected CO2. However, the evaluation of CO2-WAG is strongly dependent on the injection parameters, which renders numerical simulations computationally expensive. In this study, a novel approach has been developed that utilized machine learning (ML)-assisted computational workflow in optimizing a CO2-WAG project for a low-permeability oil reservoir considering both hydrocarbon recovery and CO2 storage efficacies. To make the predictive model more robust, two distinct proxy models—multilayered neural network (MLNN) models coupled with particle swarm optimization (PSO) and genetic algorithms (GAs)—were trained and optimized to forecast the cumulative oil production and CO2 storage. Later, the optimized results from the two algorithms were compared. The optimized workflow was used to maximize the predefined objective function. For this purpose, a field-scaled numerical simulation model of the Changqing Huang 3 tight oil reservoir was constructed. By December 2060, the base case predicts a cumulative oil production of 0.368 million barrels (MMbbl) of oil, while the MLNN-PSO and MLNN-GA forecast 0.389 MMbbl and 0.385 MMbbl, respectively. As compared with the base case (USD 150.5 million), MLNN-PSO and MLNN-GA predicted a further increase in the oil recovery factor by USD 159.2 million and USD 157.6 million, respectively. In addition, the base case predicts a CO2 storage amount of 1.09×105 tons, whereas the estimates from MLNN-PSO and MLNN-GA are 1.26×105 tons and 1.21×105 tons, respectively. Compared with the base case, CO2 storage for the MLNN-PSO and MLNN-GA increased by 15.5% and 11%, respectively. In terms of the performance analysis of the two algorithms, both showed remarkable performance. PSO-developed proxies were 16 times faster and GA proxies were 10 times faster as compared with the reservoir simulation in finding the optimal solution. The developed optimization workflow is extremely efficient and computationally robust. The experiences and lessons will provide valuable insights into the decision-making process and in optimizing the Changqing Huang 3 low-permeability oil reservoir.

Study on Micro-Pressure Drive in the KKM Low-Permeability Reservoir

Kazakhstan has abundant resources of low-permeability oil reservoirs, among which the KKM low-permeability oil reservoir has geological reserves of 3844 × 104 t and a determined recoverable reserve of 1670 × 104 t. However, the water flooding efficiency is only 68%, and the recovery efficiency is as low as 32%. The development of the reservoir faces challenges such as water injection difficulties and low oil production from wells. In order to further improve the oil recovery rate of this reservoir, our team developed micro-pressure-driven development technology based on pressure-driven techniques by integrating theories of fluid mechanics and artificial intelligence. We also combined this with subsequent artificial lift schemes, resulting in a complete set of micro-pressure-driven process technology. The predicted results indicate that after implementing micro-pressure-driven techniques, a single well group in the KKM oilfield can achieve a daily oil production increase of 32.08 t, demonstrating a good development effect.

Advancing PetroChina’s Development Strategies for Low-Permeability Oil Reservoirs

Based on PetroChina’s status and situation of low-permeability oil reservoir development, this paper analyzes the key common issues in the production capacity construction of new oilfields, the stable production of old oilfields, and enhanced oil recovery, and, in connection with the progress made in major development technologies and the results of major development tests for low-permeability oil reservoirs in recent years, puts forward the technical countermeasures and development directions. For optimizing the development of low-grade reserves, a comprehensive life-cycle development plan is essential, alongside experimenting with gas injection and energy supplementation in new fields. Addressing challenges in reservoir classification, multidisciplinary sweet spot prediction, and displacement–imbibition processes can significantly boost well productivity. In fine water flooding reservoirs, the focus should shift to resolving key technological challenges like dynamic heterogeneity characterization, and functional and nano-intelligent water flooding. For EOR, accelerating the application of carbon capture, utilization, and storage (CCUS) advancements, along with air injection thermal miscible flooding, and middle-phase microemulsion flooding, is crucial. This approach aims to substantially enhance recovery and establish a new model of integrated secondary and tertiary recovery methods.

Research on the properties of in situ emulsified active associative polymer with low molecular weight based on low permeability oil reservoirs

Research on the properties of in situ emulsified active associative polymer with low molecular weight based on low permeability oil reservoirs

CO2-enhanced oil recovery with CO2 utilization and storage: Progress and practical applications in China

CO2 capture, utilization, and storage (CCUS) is a strategic emerging technology that has undergone rapid development in recent years. CO2-Enhanced oil recovery with CO2 utilization and storage (CCUS-EOR) is currently the most practicable large-scale carbon reduction technology and has become a key tool for large-scale applications of CCUS. In the inceptive period, CCUS-EOR was targeted towards flooding, but has since been extensively adopted for industrialization. At present, CCUS-EOR is being developed for synergistic flooding and storage, and is expected to gradually transition to utilization in geological storage for supporting large-scale carbon reduction to achieve the goal of carbon neutrality. The primary mechanisms controlling CCUS-EOR differ for high-permeability, high-water-cut oil reservoirs; low-permeability oil reservoirs; extra-low permeability oil reservoirs; and tight and shale oil reservoirs. Therefore, identifying the main constraints in the CO2 flooding process and formulating effective development strategies are necessary for maximizing both oil recovery and storage. In the geological storage of CO2, attention must be paid to key factors such as the storage capacity, injectivity, and safety. The storage performance can be enhanced through methods such as synergistic CO2-enhanced water recovery and CO2 storage (CCS-EWR), as well as rapid carbon mineralization in basalt. Globally, CCUS projects have undergone rapid growth, with more than 90 % of operational projects led by or involving oil and gas companies. In China, CCUS-EOR is currently in the early stage of industrial application. The first million-ton CCUS project has recently been completed. China has great potential for CCUS-EOR. An advantage of CCUS-EOR is the early adoption to large-scale applications, while CO2 storage in saline aquifers provides a foundation for promoting large-scale development. In the future, multiple CCUS-EOR clusters are expected to be established in the Bohai Bay Basin, Songliao Basin, Ordos Basin, Yangtze River Delta, and Pearl River Delta regions, which will drive high-quality development of CCUS applications in China. ChineseLibrary Classification Number TE341. Document CodeA.

Numerical Simulation Study of Pressure-Driven Water Injection and Optimization Development Schemes for Low-Permeability Reservoirs in the G Block of Daqing Oilfield

Pressure-driven water injection technology shows significant potential in addressing the key challenges of low-permeability oil reservoirs, improving water flooding development efficiency. Grounded in FDEM theory, this study establishes fluid matrix constitutive equations and employs FDEM to resolve rock stress–strain fields. A numerical simulation method for pressure-driven water injection in low-permeability reservoirs is developed to study the impact of different well pattern densities. The results indicate that the 90° horizontal well pattern using the five-spot method yields optimal outcomes, with approximately 32.32% higher cumulative liquid production than vertical well patterns. The 45° horizontal well pattern with the reversed nine-spot method also performs well, with about 30% higher cumulative liquid production than single-row vertical wells. Pressure-driven water injection improves matrix oil–water permeability and expands water flooding coverage. Based on the pressure gradient distribution driven by different well patterns, an evaluation method for the inter-well utilization capacity and its effectiveness was established. This method quantitatively assesses the reservoir depletion under various horizontal well encryption schemes. For research on timing of water injection in pressure-driven water flooding. Compared to pressure-driven water injection after 90 days, there is increased cumulative oil production after 40 days, emphasizing the importance of early pressure maintenance for higher cumulative oil production and enhanced recovery rates in low-permeability reservoir development. These findings provide crucial theoretical and practical support.

Synthesis and characterization of in-situ self-growth mineralization-responsive dispersed gel nanoparticles

This study employed a reverse emulsion method to prepare dispersed nanoparticle gels that respond to mineralization and exhibit excellent characteristics such as small particle size, high dispersion, and strong stability by introducing catechol-like structures and temperature/salt-resistant functional monomers. Experimental results showed that the particle size of the dry dispersed gel particles ranged from tens to 100 nm, as observed by scanning electron microscopy. Laser particle size analyzer testing demonstrated that the size of the dispersed gel particles progressively increased with the mineralization degree of the dispersed particle gel, indicating a certain level of mineralization responsiveness. Additionally, these particles could maintain stable dispersion for up to 40 days in a solution with a mineralization degree of 20,000 mg/L. The rheology testing results indicate that the dispersed particle gels exhibited the properties of the pseudo-plastic fluid. Even under extreme conditions such as high temperature and mineralization, the strength of the dispersed particle gels remained intact, measuring 95.76 kPa after 40 days of aging. Using Materials Studio molecular simulation software, the stability and self-growth mechanism of dispersed gel particles were explained from the quantum mechanics perspective. The geometry of the dispersed gel particles was optimized using the Compass II force field, and the total energy of the model was calculated to be −757.579 kcal/mol, with the dihedral torsion energy contributing the most to the total energy. The molecular bond lengths in the polymer chain were then calculated, with the O–H bond being the shortest and the O-Na bond in the carboxylate sodium group being the longest. This indicated that the –OH group was more stable and the carboxylate sodium group was prone to hydrolysis, forming a –COOH group and increasing the dispersion stability. The charge distribution and molecular orbitals in the polymer molecule were also calculated, with the LUMO value being −7.405 eV and the HOMO value being −4.487 eV. This study used a reverse emulsion method to in-situ generate mineralization-responsive, multi-haired dispersed gel nanoparticles, which fundamentally solved the injection problem of low-permeability oil reservoirs and provided new materials for long-term plugging of high-temperature and high-salinity oil reservoirs.

The Influence of Micro-Heterogeneity on Water Injection Development in Low-Permeability Sandstone Oil Reservoirs

Micro-heterogeneity in low-permeability sandstone oil reservoirs significantly influences the uniformity of water injection during development. This leads to the formation of preferred channels for water injection, causing premature water breakthroughs in oil wells. Not only does this reduce oil displacement efficiency, but it also enriches residual oil in the formation, which ultimately impacts the overall recovery rate. This study employed various methods, including thin-section casting, qualitative analysis through scanning electron microscopy, quantitative analysis of X-ray diffraction, high-pressure mercury intrusion and particle size, and experimental techniques, such as wettability and micro-displacement, to investigate the impact mechanism of micro-heterogeneity on water injection development in low-permeability oil reservoirs. A typical low-permeability sandstone oil reservoir in the Ordos Basin was used as a case study. The results reveal that the reservoir’s micro-heterogeneity is determined by the heterogeneity of the interstitial material, porosity, and particle size. Micro-heterogeneity plays a critical role in the flow characteristics and oil displacement efficiency of low-permeability oil reservoirs. The less the micro-heterogeneity, the better the water injection development outcome. This study suggests a technical policy adjustment method that is critical for guiding the development of low-permeability water injection oil reservoirs, thereby improving the effectiveness of water injection development.

Predicting CO2-EOR and storage in low-permeability reservoirs with deep learning-based surrogate flow models

Addressing the greenhouse effect, enhancing carbon reduction and utilization has become globally imperative. China has ambitious goals to carbon peak by 2030 and achieve carbon neutrality by 2060. One promising method is CO2 enhanced oil recovery (EOR) technology, which bolsters the development of low-permeability oil reservoirs and offers potential for carbon storage. While numerical simulation can optimize production, multiphase flow simulations often come with considerable computational demands. This study introduces a novel workflow to develop a high-fidelity surrogate model tailored for CO2-EOR in low-permeability reservoirs. Adopting a data-driven methodology, we employ the Res U-Net neural architecture to craft this surrogate model, aiming to predict formation flow state variables. Critical parameters such as porosity, permeability, well location, control conditions, and discrete time intervals from raw data are transformed into 2D images, serving as input features for the model. We incorporate a structural similarity (SSIM) index into the loss function to effectively grasp the intricate spatiotemporal changes inherent in stratigraphic state variables. Additionally, a bespoke penalty scheme refines the surrogate model's performance in designated areas. Compared to numerical simulation results, the surrogate model can achieve high-fidelity prediction of CO2-EOR and storage in heterogeneous low-permeability oil reservoirs. In test set cases, the average MSE of the surrogate model for prediction results is less than 2.2 × 10−5, and the average MSSIM is more significant than 0.99. Based on a post-processing block, we have further predicted cumulative oil production and CO2 storage using the surrogate model, with an average relative error of less than 0.90% for predicted results.

Matching method between nanoparticle displacement agent size and pore throat in low permeability reservoir

Nano-particles possess desirable attributes such as small particle size, excellent injectivity, and migration performance, making them highly compatible and adaptable for addressing the water flooding requirements of the low-permeability oil reservoir. When selecting an oil displacement agent for enhancing water flooding and improving oil recovery, factors such as injectivity and migration need to be carefully considered. In this study, through a comprehensive analysis of the mechanism and technical characteristics of nano-particle oil displacement agents, the plugging and profile control mechanisms recognized by the mainstream of nano-particles are elucidated. By examining various elements including outcrop fractures, natural micro-fractures, artificial support fractures, and dynamic monitoring data, a reevaluation of the dominant channel scale governing water drive in low permeability reservoirs is conducted, thereby defining the target entities for profile control and flooding operations. Drawing upon Darcy’s percolation law and leveraging enhanced oil recovery techniques based on the classical Kozeny equation, a profile control and flooding mechanism is proposed that focuses on increasing the specific surface area of polymer particles while simultaneously reducing reservoir permeability. This innovative approach establishes a novel matching method between nano-polymer particles and the diverse media found within the reservoir. Lastly, the application of nanoparticle flooding technology in Changqing Oilfield is presented, highlighting its practical implementation and benefits.

Optimization Study of Injection-Production Parameters for CO2 Enhanced Oil Recovery and Storage in Low Permeability Oil Reservoirs

To address the difficulty of water injection in the late stage of developing a certain low-permeability reservoir, CO2 injection and fracturing parameter optimization were conducted. The Latin hypercube sampling and numerical simulation methods were used to study the five-spot well network model established, and evaluate the impact of injection and fracturing parameters on oil recovery and CO2 storage using a comprehensive evaluation factor of oil displacement and storage. The results show that the injection rate is the main controlling factor affecting the oil recovery and storage effect, and the optimal injection rate is 6000m3/d. There is a certain contradiction between the oil recovery and storage objectives at different stages of injection development, but after ten years of injection development, the objectives of oil recovery and storage are consistent. The optimal combination of ijection and fracturing parameters yields a recovery rate of 72.54% and a CO2 storage amount of 101635.81 tons. This paper proposes that there is a certain contradiction between the oil recovery and storage objectives at different stages and evaluates schemes with different injection development periods by constructing a comprehensive evaluation factor for oil displacement and storage, which has certain reference value for optimizing parameters in the CO2 injection development of low-permeability reservoirs.

Research and Development of Capillary Imbibition Regularity in Ultra-Low Permeability Oil Reservoirs

Nowadays, Chinese economy is growing rapidly, and the petroleum industry is developing swiftly. The demand for oil and gas resources is increasing day by day. As the development process goes deeper, a significant portion of our country’s oil fields has entered the stage of high-water content and high recovery. Consequently, the direction of oil and gas exploration is gradually shifting towards unconventional reservoirs. Special low-permeability oil reservoirs in China exhibit characteristics such as low porosity, low permeability, fine pores, and natural fractures. Their recovery rates are low. Hence, the exploration and development of these special low-permeability oil reservoirs have become a critical challenge in today’s petroleum engineering domain. The urgent task is to find ways for high-yield, high-efficiency, and sustainable development of such reservoirs. In the development process of these special low-permeability oil reservoirs, capillary action plays a significant role. Capillary action allows the transportation of high-density crude oil within the reservoir, potentially enhancing the recovery rates of special low-permeability oil reservoirs. In recent years, both domestically and internationally, there has been extensive research on the mechanisms and patterns of water injection and capillary action. This paper delivers the research on capillary action in special low-permeability oil reservoirs, summarizes and organizes the progress and achievements in this field, aiming to deepen the understanding of this area and provide insights into future research directions.

Study on SiO2 Nanofluid Alternating CO2 Enhanced Oil Recovery in Low-Permeability Sandstone Reservoirs

Study on SiO2 Nanofluid Alternating CO2 Enhanced Oil Recovery in Low-Permeability Sandstone Reservoirs

ANALYSIS OF HYDRODYNAMIC INTERACTION OF WELLS BASED ON DETERMINATION OF PRODUCTION AND INJECTION COMPENSATION BALANCE USING THE EXAMPLE OF RESERVOIR — BARREM CLINOFORM OF PRIOBSKY SEDIMENTATION BASIN

Abstract. Long-term development of oil fields using a reservoirpressure maintenance system by injecting water into the formation leadsto a number of features of well operation identified during fieldgeophysical and hydrodynamic studies. The combination and processingof parameters characterizing the field development indicators and theoperation of wells in the injection-production section make it possible toconduct a qualitative assessment of the processes occurring in the subsoil.The article describes the procedure for determining possible sources ofwater flooding of oil wells in a large multi-zone field in Western Siberia.In order to determine the compensatory balance of production andinjection taking into account the regional stress characteristic of the field,calculations were made using a geometric figure in the form of an ellipse.The drainage zone described in this way does not contradict the ratio ofthe number of injection and oil wells in the nine-point developmentsystem. The analysis of geological and field information and hydrodynamicstudies made it possible to identify a difference in the signs of increasedwater cut of the product with uncontrolled growth of a man-made fracturein the direction of regional stress and when overlying horizons, which areinterbedded with water-saturated sandy bodies formed under the Bystrinskyclay pack during the regression cycle of sedimentation, were included inthe development. From the point of view of the analysis results, one of thepossible reasons for the development of man-made fluid contacts betweenthe injected and formation water of the overlying formation is a violationof the cement support behind the production string of the injection well.And as a result, there is a top-down flow in the production wells. Theoccurrence of disturbances in the cement support is a technical reason andcan be associated with technological processes carried out on injectionwells during operation, or imperfection in adhesion during insulation andtechnical work. The methods used in the article to determine thehydrodynamic interaction of wells and the signs of formation ofinterformation fluid contacts made it possible to assess the possiblereasons for the increase in water cut in the complex, low-permeability oilreservoirs of the Goteriv-Barremian clinoform of the Priobskysedimentation basin.

Machine-Learning-Based Approach to Optimize CO2-WAG Flooding in Low Permeability Oil Reservoirs

One of the main applications of carbon capture, utilization, and storage (CCUS) technology in the industry is carbon-dioxide-enhanced oil recovery (CO2-EOR). However, accurately and rapidly assessing their application potential remains a major challenge. In this study, a numerical model of the CO2-WAG technique was developed using the reservoir numerical simulation software CMG (Version 2021), which is widely used in the field of reservoir engineering. Then, 10,000 different reservoir models were randomly generated using the Monte Carlo method for numerical simulations, with each having different formation physical parameters, fluid parameters, initial conditions, and injection and production parameters. Among them, 70% were used as the training set and 30% as the test set. A comprehensive analysis was conducted using eight different machine learning regression methods to train and evaluate the dataset. After evaluation, the XGBoost algorithm emerged as the top-performing method and was selected as the optimal approach for the prediction and optimization. By integrating the production prediction model with a particle swarm optimizer (PSO), a workflow for optimizing the CO2-EOR parameters was developed. This process enables the rapid optimization of the CO2-EOR parameters and the prediction of the production for each period based on cumulative production under different geological conditions. The proposed XGBoost-PSO proxy model accurately, reliably, and efficiently predicts production, thereby making it an important tool for optimizing CO2-EOR design.