Development Of Gas Reservoirs Research Articles

A Review of Supercritical CO2 Fracturing Technology in Shale Gas Reservoirs

Shale gas reservoirs generally exhibit characteristics such as low porosity, permeability, and pore throat radius, with high airflow resistance. Currently, hydraulic fracturing is a commonly used method for commercial shale gas extraction; however, the hydraulic fracturing method has exhibited a series of issues, including water sensitivity and reservoir pollution in shale reservoirs. Therefore, the development of anhydrous fracturing technology suitable for shale gas reservoirs has become an urgent requirement. The supercritical carbon dioxide fracturing technique has the merits of reducing reservoir damage, improving recovery and backflow rates, and saving water resources. Moreover, this technique has broad application prospects and can achieve the effective extraction of shale gas. To enhance the understanding of the supercritical carbon dioxide fracturing technique, this review summarizes the progress of current research on this technique. Furthermore, this study analyzes the stage control technology of supercritical carbon dioxide during the fracturing process, the interaction characteristics between supercritical carbon dioxide and rocks, and the laws of rock initiation and crack growth in supercritical carbon dioxide fracturing. The outcomes indicate that after SC-CO2 enters the reservoir, CO2 water–rock interaction occurs, which alters the mineral composition and pore throat framework, weakens the mechanical characteristics of shale, reduces the rock fracturing pressure, and increases the complexity of the fracturing network. This article provides a reference for research related to supercritical carbon dioxide fracturing technology and is greatly significant for the development of shale gas reservoirs.

Solubility of H2S-CH4 mixtures in calcium chloride solution: Insight from molecular dynamics simulations

This study uses equilibrium molecular dynamics (EMD) simulations to gain microstructural insight into and predict crucial properties of gas-brine mixtures affecting sour gas reservoir development. The effects of pressure, temperature, gas composition and salinity on the solubility and density of H2S-CH4 mixtures in pure water and CaCl2 brine were investigated at industrially relevant conditions (temperature range of 280 − 340 K, pressures up to 20 MPa, and a salinity range of 4.78 − 17.32 wt%). The force fields used in the MD simulations were validated using experimental data for pure H2S and CH4. The results showed that the solubility of pure H2S and CH4 in pure water increases with pressure, with the latter having a higher solubility. For H2S-CH4 mixtures, the solubility of H2S increased while that of CH4 fell with increasing H2S mole fraction, with the solubilities of the two gases intersecting at an H2S mole fraction of 0.28. Further, the solubility of H2S shows a greater pressure dependence than that of CH4, and H2S gas tends to reach saturation in pure water. In calcium chloride solution, the gas solubility decreases as the ions reduce the interaction between water and gas molecules. The solubility of H2S gas is a stronger function of the ion concentration compared with CH4, and increases 6-fold as the H2S mole fraction increases from 0.5 to 0.8. The overall solubility ranges were 0.45 to 3.48 mol/kg for H2S and 0.15 to 0.25 mol/kg for CH4.

Review about evaluation methods of recoverable reserves of deep water drive gas reservoirs in China

It has been widely accepted that China is one of the biggest natural gas consumers. Related to the imports of LNG, China stands in a very uncomfortable situation. Most domestic gas reservoirs fall within deep water drive gas reservoirs inordinately, which has entered the production depletion stage. Accurate estimation of SEC recoverable reserves of deep water drive gas reservoirs is of great significance for gas consumption planning and peak shaving. The existing calculation methods of recoverable reserves mainly consist of static methods and dynamic methods. In the early stage of exploration and development, the volumetric method has often been utilized to calculate the recoverable reserves. With the continuous development of gas reservoirs, the main methods for evaluation are dynamic methods, including the successive subtraction of production method, water drive curve method, prediction model method, attenuation curve method, improved virtual curve method, and material balance method for deep gas reservoirs.

CO2 injection-based enhanced methane recovery from carbonate gas reservoirs via deep learning

CO2 injection is a promising technology for enhancing gas recovery (CO2-EGR) that concomitantly reduces carbon emissions and aids the energy transition, although it has not yet been applied commercially at the field scale. We develop an innovative workflow using raw data to provide an effective approach in evaluating CH4 recovery during CO2-EGR. A well-calibrated three-dimensional geological model is generated and validated using actual field data—achieving a robust alignment between history and simulation. We visualize the spread of the CO2 plume and quantitatively evaluate the dynamic productivity to the single gas well. We use three deep learning algorithms to predict the time histories of CO2 rate and CH4 recovery and provide feedback on production wells across various injection systems. The results indicate that CO2 injection can enhance CH4 recovery in water-bearing gas reservoirs—CH4 recovery increases with injection rate escalating. Specifically, the increased injection rate diminishes CO2 breakthrough time while concurrently expanding the swept area. The increased injection rate reduces CO2 breakthrough time and increases the swept area. Deep learning algorithms exhibit superior predictive performance, with the gated recurrent unit model being the most reliable and fastest among the three algorithms, particularly when accommodating injection and production time series, as evidenced by its smallest values for evaluation metrics. This study provides an efficient method for predicting the dynamic productivity before and after CO2 injection, which exhibits a speedup that is 3–4 orders of magnitudes higher than traditional numerical simulation. Such models show promise in advancing the practical application of CO2-EGR technology in gas reservoir development.

Pore-scale investigations of permeability of saturated porous media: Pore structure efficiency

Accurate estimation of permeability and the establishment of correlations with pore space properties have garnered attention due to the increasing demand for oil and gas reservoir development as well as geological carbon sequestration. However, prevailing theoretical and empirical models often rely on porosity and pore sizes as key pore space properties to predict permeability, overlooking the variability of pore structure. To delineate the intrinsic associations between permeability and pore space properties, a self-developed visualized experimental system with controllable pore space properties is used to measure permeability of porous media with varying porosity and particle arrangements. Various parameters, encompassing porosity, pore sizes (maximum pore diameter and pore throat diameter) and fractal parameters (pore fractal dimension, succolarity, and lacunarity) are extracted to quantify pore space properties, and further utilized to develop permeability models. Results demonstrate a positive correlation between permeability and porosity, maximum pore diameter, and average pore throat diameter. Additionally, particle arrangements yield pronounced anisotropy in permeability. Relying solely on porosity and pore sizes to portray pore space properties falls short of comprehensively characterizing permeability. Incorporating fractal characterization through metrics like succolarity and lacunarity emerges as a potent avenue for delineating heterogeneity and pore connectivity. This approach proves useful in characterizing the effect of pore structure variability on permeability. The established permeability model rooted in flow direction succolarity and normalized lacunarity aligns effectively with experimental data, capturing the essential physics of permeability variation.

Segmentation Study of Deep Shale Gas Horizontal Wells of the South Sichuan Shale Gas

Summary The low porosity and low permeability of shale gas reservoirs make fracturing technology an indispensable part of shale gas reservoir development. The initial stage of shale gas development is characterized by shallow direct wells, but with the advancement of drilling and completion technology in the development of unconventional oil and gas reservoirs, horizontal wells and fracturing technology have gradually become the key methods for the effective development of oil and gas reservoirs. “Geology-engineering integration” has gradually become a hot spot in the research of horizontal well fracturing. The factors affecting the development of shale gas reservoirs are subdivided into “geological sweet spot” and “engineering sweet spot” influencing factors. Geological sweet spot refers to the area where the reservoir is rich in hydrocarbons or organic matter; engineering sweet spot refers to the area with good fracturability in the later fracturing and reforming of the reservoir. The shale gas sweet spot area should have the characteristics of high gas content, high fracturable, and high efficiency. Comprehensively evaluating the physical properties and brittleness characteristics can provide certain guidance for shale gas horizontal well segmentation.

Experimental study on critical sand production pressure gradient at different production stages of high temperature and high pressure tight sandstone gas reservoir

AbstractSand production is a common issue in sandstone gas reservoir development, severely impacting the productivity of sandstone gas wells. In order to thoroughly investigate the sand production characteristics of high‐temperature and high‐pressure tight sandstone gas reservoirs, this study focuses on six core samples from tight sandstone gas reservoirs(three samples with fractures), under reservoir conditions (185 MPa, 160°C), sand production experiments were conducted to thoroughly investigate the sand production patterns in sandstone reservoirs under the combined influence of different effective stresses and production pressure differentials. The results indicate: (1) under the simultaneous increase of effective pressure and production pressure differential, sand production near the wellbore (r = 0.1 m) becomes more likely in the reservoir; (2) in actual reservoirs without fractures near the wellbore (r = 0.1 m), sand production phenomena do not occur; (3) reservoirs with fractures near the wellbore (r = 0.1 m) are more prone to sand production, under an effective stress of 90 MPa, with specimens containing fractures exhibiting a 76.48% lower critical sand production pressure gradient compared to those without fractures; (4) when the pore fluid pressure is 95 MPa, the maximum gas production rate for Well X without sand production is 12.4 × 104 m3/d. The experimental results have guiding significance for the rational production of gas wells in this type of reservoir.

Study on the Interaction Propagation Mechanism of Inter-Cluster Fractures under Different Fracturing Sequences

Horizontal-well multi-cluster fracturing is one of the most important techniques for increasing the recovery rate in unconventional oil and gas reservoir development. However, under the influence of complex induced stress fields, the mechanism of interaction and propagation of fractures within each segment remains unclear. In this study, based on rock fracture criteria, combined with the boundary element displacement discontinuity method, a two-dimensional numerical simulation model of hydraulic fracturing crack propagation in a planar plane was established. Using this model, the interaction and propagation process of inter-cluster fractures under different fracturing sequences within horizontal well segments and the mechanism of induced stress field effects were analyzed. The influence mechanism of cluster spacing, fracture design length, and fracture internal pressure on the propagation morphology of inter-cluster fractures was also investigated. The research results indicate that, when using the alternating fracturing method, it is advisable to appropriately increase the cluster spacing to weaken the inhibitory effect of induced stress around the fractures created by prior fracturing on subsequent fracturing. Compared to the alternating fracturing method, the propagation morphology of fractures under the symmetrical fracturing method is more complex. At smaller cluster spacing, fractures created by prior fracturing are more susceptible to being captured by fractures from subsequent fracturing. The findings of this study provide reliable theoretical support for the optimization design of fracturing sequences and fracturing processes in horizontal well segments.

Tight carbonate reservoir evaluation case study based on neural network assisted fracture identification and analytic hierarchy process

Comprehensive evaluation of reservoirs is an important link in gas reservoir exploration and development. The evaluation of tight carbonate reservoirs often focuses on the characteristics of porosity and permeability, ignoring the important factor of fractures, also the quantitative evaluation of reservoirs is relatively few. It is difficult to identify fractures and evaluate the reservoir factors qualitatively and quantitatively. Herein, the sedimentary microfacies and microporosity of the tight carbonate reservoir of the Ma55 submember in the eastern Sulige area are comprehensively studied by casting thin section, rock physical property, and capillary pressure test data. The backpropagation (BP) neural network algorithm is used to identify and predict fractures. Finally, through the analytic hierarchy process, the above reservoir influencing factors are modeled and quantitatively analyzed for reservoir evaluation. The results show that the highest probability of fracture development in the central and northwest areas of the study area can reach 0.92. The accuracy of the BP neural network model in identifying cracks can reach 80%, which is reliable and effective compared with the conventional logging identification method. Reservoirs can be classified into four types according to their quality. The synthetic weights of porosity, permeability and fracture development probability are 0.2, 0.2 and 0.216 respectively, which are the three most important evaluation parameters. This study improves the accuracy of fracture identification and prediction of tight reservoirs in comprehensive reservoir evaluation, which provides guidance and scheme for more detailed exploration and development of tight carbonate reservoirs.

Study on the Phase Behavior Simulation Method of High-Salinity Reservoirs.

The presence of salinity affects the accuracy of existing correlations used in the equation of state. Moreover, the variation of salinity is often ignored in the systematic analysis of the phase diagram, resulting in a large error in the final calculation result. It is obvious that the conventional phase equilibrium calculation is not applicable in a high-salinity reservoir. By introducing the hydrocarbon-brine binary interaction coefficient and α-function, combined with the definition of salinity, and considering the variation of salinity under different pressure and temperature conditions, a more perfect phase equilibrium calculation model was established. The complete phase diagram was drawn, and the calculation results of salinity distribution are obtained. The effect of the mole percentage of water and salt content on the phase behavior was simulated. Finally, the phase distribution simulation is carried out based on the measured data. The phase state and salinity variation law of a high-salinity reservoir are obtained. According to the fluid composition of different periods, the real phase state of the high-salinity reservoir can be monitored in real time. It can provide a theoretical basis for the gas reservoir development and the dynamic evaluation of gas storage injection and production with a hydrocarbon-brine two-phase system.

Gas mass transfer characteristics in shales: Insights from multiple flow mechanisms, effective viscosity, and poromechanics

Accurate characterization of gas transport behavior is indispensable for successful shale gas reservoir development. In this study, a fractal-theory-based apparent permeability (AP) model is developed to better characterize real gas mass transfer in shales. The proposed model involves multi-scale organic matter (OM) and inorganic matter (IOM) flow channels and incorporates poromechanics-related dynamic pore size, multiple gas transport mechanisms, and dynamic viscosity. The discrete integration method (DIM) is employed to address viscosity changes during fractal scaling up. Experimental data, molecular dynamics simulations, and published theoretical models were used to verify the proposed model and reasonable agreements have been achieved. Results indicate that as the pore pressure and size increase, dominant mechanisms for gas transport change from surface diffusion at low pressure (lower than switch pressure) to viscous flow at higher pressure and larger pore sizes. Furthermore, higher organic matter content makes the permeability curve more similar to OM type. Ignoring effective viscosity results in underestimation of permeability, which is more noticeable when pressure rises and pore shrinks. Poromechanical properties primarily affect pore size, larger elastic modulus and smaller Poisson's ratio leads to significantly lower permeability. The real gas effect on AP reduction cannot be ignored, especially at high pressure. This work provides insights into the gas transport characteristics in shales, which have practical implications for shale gas reservoir simulation and development.

A three-dimensional numerical well-test model for pressure transient analysis in fractured horizontal wells with secondary fractures

During oil and gas reservoir development, multi-stage horizontal wells (MFHWs) and hydraulic fracturing techniques can effectively increase estimated ultimate recovery. However, there still lacks an understanding of the three-dimensional (3D) pressure transient behaviors of multi-stage fractured horizontal wells with secondary fractures. To narrow this gap, a three-dimensional numerical well-test model based on a discrete fracture model and unstructured tetrahedral grids is developed to study the pressure transient behaviors of MFHWs with secondary fractures. The pressure transient solutions of MFHWs with secondary fractures have been demonstrated by model verifications. The results show that the proposed model can accurately capture the complex transient flow around fractures, including early radial flow that is not easily captured by two-dimensional numerical well test models. The proposed model classifies the flow regimes of a MFHW as: wellbore storage and skin effects, early radial flow, bilinear flow, linear flow, elliptical flow, pseudo radial flow, and pseudo-boundary dominated flow. It is found that the fracture geometry has a relatively large effect on the shape of the pressure derivative curve in this work. The hydraulic fracture half-length has the greatest impact on the pressure transient behaviors of the MFHW, followed by fracture height and secondary fracture half-length, as found in this study. Additionally, fracture parameters are evaluated, and actual well testing data are interpreted, taking into account the fracture height. This work is meaningful to understand the three-dimensional pressure transient behaviors of MFHWs with secondary fractures.

Study on Key Technologies of Geosteering for Shale Gas Horizontal Wells in the Complex Structural Area of Block H in Western Hubei-Eastern Chongqing.

Block H, located in western Hubei-eastern Chongqing, remains at a low exploration degree. Characterized by its complex structural attributes, the area presents adverse conditions such as a thin thickness of high-quality shale reservoir, rapid lateral formation occurrence, and poor stratigraphic correlation, challenging conventional geosteering methods. The primary shale gas reservoir in Block H corresponds to the Upper Permian Wujiaping Formation. To ensure that the shale gas horizontal wells in this block effectively penetrate high-quality gas reservoirs, this study delves into the geological characteristics of this stratigraphic unit, identifies principal challenges faced by current geosteering techniques, and introduces a tailored technical solution. This solution encompasses the application of real-time 3D geological modeling to track while drilling, identification of steering marker layers, optimization of steerable tools, and optimization of the steering trajectory while drilling. In the technology of optimization of the steering trajectory while drilling, a trajectory control calculation model based on the average angle technique was established for the first time. Additionally, a sectional control chart for marker layers and well inclination under different deflecting constraints was established. These methods have solved the problems of large error in target prediction and poor trajectory control effects by using the equal thickness method alone. The findings from this study can significantly enhance target prediction and trajectory control accuracy in complex structural areas, offering pivotal insights for the proficient development of analogous shale gas reservoirs in the future.

Single-Well Simulation for Horizontal Wells in Fractured Gas Condensate Reservoirs.

Fractured gas condensate reservoirs (FGCR) are a complex, special, and highly valuable type of gas reservoir, accounting for a significant proportion of gas reservoir development. In recent years, with the continuous advancement of horizontal well technology, it has become the main approach for the development of FGCR. The current model is unable to accurately represent the fluid distribution in the near-well area of horizontal wells due to the unique retrograde condensation phenomenon in GCR. Additionally, the presence of fractures complicates the solution of traditional analytical models. In response to this issue, this paper proposes a novel semianalytical model for horizontal wells in FGCR, which incorporates natural fractures, multiphase flow, and the influence of stress sensitivity on pressure response. A dual-porosity model is employed to simulate fractured reservoirs, and a four-region radial composite model is developed to characterize multiphase flow resulting from retrograde condensation in GCR. The pseudopressure transform, Pedrosa transform, Laplace transform, and Finite Cosine transform are utilized to address the nonlinear partial differential equation. A systematic verification of the semianalytical solution is confirmed through a comparison with the numerical solution from computer modeling group (CMG). We thoroughly explain the physical significance of the various features by identifying the 12 flow regimes of the typical curve. Furthermore, we offer a method for assessing the extent of retrograde condensation and the size of the retrograde condensate region based on the curve's characteristics. Finally, the pressure measurements recorded from the Bohai field are carried out to validate the accuracy of the proposed model. The results show that the predictions of the new model are in good agreement with the actual production data, demonstrating the proposed solution's applicability.

Seismic geological characteristics and gas reservoir distribution of Changxing Formation biological bio-reef reservoir in the Longhuichang-Tieshan area, northeastern Sichuan Basin, China

This research aims to address the ambiguity surrounding the extent of development of Changxing Formation bio-reef reservoirs in the Longhuichang-Tieshan area of the northeastern Sichuan Basin, China, and to elucidate the relationship between these reservoirs and gas distribution. Utilizing drilling and logging data, this study provides a comprehensive summary of the seismic geological characteristics of bio-reef reservoirs. Furthermore, it investigates the effects of reservoir parameters, structural location, and strike-slip faults on the development of bio-reef gas reservoirs. The research shows that bio-reef reservoirs in the area predominantly manifest vertical development in the middle and upper parts of the Changxing Formation, with horizontal expansion occurring along the platform margin and local highland areas. Notably, potential exploration areas are identified, particularly the western wing of the Longhuichang structure and the southwestern side of the Tieshannan structure. By comparing and analyzing the relationship between bio-reef gas reservoirs in the study area, the study aims to clarify the controlling effects of reservoir parameters, structural location, strike-slip faults, and other pertinent factors on the development of bio-reef gas reservoirs. It is observed that while these factors do not exhibit a clear strong linear relationship, they have a comprehensive effect on the development of gas reservoirs. The enrichment mode and failure mode of favorable gas reservoirs in the study area have been analyzed and established, providing crucial technical support to facilitate further exploration of Changxing Formation bio-reef gas reservoirs in the northeastern Sichuan Basin.

Numerical characterization of acid fracture wall etching morphology and experimental investigation on sensitivity factors in carbonate reservoirs

Carbonate reservoirs are marked by their low porosity and permeability, naturally occurring fractures that develop in a stochastic fashion and exhibit significant heterogeneity. Deep acidification techniques are essential for the efficient development of such oil and gas reservoirs. The effective distance of acid etching (acid etch fracture length) and the fracture conductivity stand as the two most critical parameters for assessing the efficacy of acidizing. The primary objective of using this technique is to extend the effective distance of the acid etch and enhance the fracture conductivity. The "relay-style" full-length acid etched fracture testing method is employed, achieving an accurate match between the testing temperature, pressure, fracture length, and the actual acid fracturing conditions. It employs a large-scale rock plate acid etching experimental device, in conjunction with 3D laser scanning technology, and utilizes orthogonal experimental design methods to conduct detailed numerical characterization of the rock plate fracture surfaces before and after etching with various acid fluid types, acid injection amounts, and acid injection rates. It quantifies the change in the concentration of the residual acid fluid after the acid-rock reaction, calculating the etching volume of the acid fluid and the length of the acidizing fracture. The experimental results demonstrate that both the gelled acid and the clean diverting acid exhibit long acidification distances and strong inhomogeneous etching capabilities. The etch morphology of the clean diverting acid is dominated by pitting-type and stripe-like dissociation, exhibiting a wavy pattern. In contrast, the etch morphology of the gelled acid appears band-like and groove-like. As the acid injection amount increases, the etch length increases. Under on-site working conditions, etch lengths of 46.42 m and 41.63 m were recorded for 20% gelled acid and clean diverting acid, respectively, after 60 min acid injection time. The factors affecting the etch length sensitivity are in the following order: acid injection rate > acid type > etching time. The optimal acid fracturing parameters to achieve the maximum etch length are: The etch is performed at a pump rate of 600 mL/min for 90 min using gelled acid. Quantitative characterization of acid etch fracture morphology can optimize designing parameters of acid fracturing techniques, enhance the efficiency of their modification, and further enhance the development benefits of oil and gas carbonate rock reservoirs.

Utilization method of low-grade thermal energy during drilling based on insulated Drill pipe

Downhole heat damage during drilling seriously restricts the exploration and development of deep oil and gas reservoirs and geothermal resources. The petroleum industry focuses on controlling the downhole heat damage during drilling while utilizing low-grade thermal energy and making it profitable. Therefore, a techno-economic coupling evaluation model is developed for a low-grade thermal energy utilization system developed for use during drilling along with a wellbore heat transfer model. Subsequently, based on the model, the influence of different lengths and installation positions of insulated drill pipe (IDP) on the downhole temperature is studied. Then, on the premise of satisfying the wellbore cooling target, the system is economically evaluated based on factors such as production time, government subsidy, and electricity price, and the corresponding measures are proposed to make the system profitable. Finally, a set of efficient IDP-based low-grade thermal energy utilization methods is developed. The case study presented herein shows that the IDP length that allows the system to reach the maximum profit in the 10th year is 4720 m for a horizontal well with a depth of 6200 m when the government one-off subsidy rate is 30% and electricity price is increased by 30%.

A dual-reciprocity boundary element method based transient seepage model with nonlinear distributed point source dual-porosity gas reservoir

As a result of advancements in gas reservoir development technologies and a deeper understanding of seepage theory, numerous nonlinear seepage problems have emerged. Consequently, conventional analytical solution models are no longer applicable. Moreover, existing semi-analytical and numerical solution models suffer from issues like high computational complexity and limited flexibility, significantly constraining their practical utility. For this purpose, a gas reservoir transient seepage model is established based on the dual-reciprocity boundary element method (DRBEM). This model couples the wellbore storage coefficients with skin factor and introduces a novel dual-porosity transient interporosity seepage algorithm, enabling the resolution of transient seepage problems in dual-porosity gas reservoirs with nonlinear point source distributions. Additionally, it investigates the dynamic behavior of bottomhole pressure during the early production stage of gas wells, while capturing the dynamic pressure distribution within the seepage field. This approach offers the advantages of semi-analyticity, meshless, and eliminates the need for Laplace transforms, resulting in a significant reduction in computational complexity. Ultimately, the application of our model to well-pattern production with the production system transition issues, in conjunction with the log-log type curves of bottomhole pressure, and the dynamics of gas reservoir pressure, enables the analysis of interference characteristics between injection-production wells. This showcases the practical advantages of the model's application. The findings of this study provide valuable assistance for modeling and solving transient seepage problems in dual-porosity oil and gas reservoirs production. The application of DRBEM in unsteady-state diffusion, heat conduction, stress fields, and other potential field problems is relevant for reference.

Prediction of ORF for Optimized CO2 Flooding in Fractured Tight Oil Reservoirs via Machine Learning

Tight reservoirs characterized by complex physical properties pose significant challenges for extraction. CO2 flooding, as an EOR technique, offers both economic and environmental advantages. Accurate prediction of recovery rate plays a crucial role in the development of tight oil and gas reservoirs. But the recovery rate is influenced by a complex array of factors. Traditional methods are time-consuming and costly and cannot predict the recovery rate quickly and accurately, necessitating advanced multi-factor analysis-based prediction models. This study uses machine learning models to rapidly predict the recovery of CO2 flooding for tight oil reservoir development, establishes a numerical model for CO2 flooding for low-permeability tight reservoir development based on actual blocks, studies the effects of reservoir parameters, horizontal well parameters, and injection-production parameters on CO2 flooding recovery rate, and constructs a prediction model based on machine learning for the recovery. Using simulated datasets, three models, random forest (RF), extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM), were trained and tested for accuracy evaluation. Different levels of noise were added to the dataset and denoised, and the effects of data noise and denoising techniques on oil recovery factor prediction were studied. The results showed that the LightGBM model was superior to other models, with R2 values of 0.995, 0.961, 0.921, and 0.877 for predicting EOR for the original dataset, 5% noise dataset, 10% noise dataset, and 15% noise dataset, respectively. Finally, based on the optimized model, the key control factors for CO2 flooding for tight oil reservoirs to enhance oil recovery were analyzed. The novelty of this study is the development of a machine-learning-based method that can provide accurate and cost-effective ORF predictions for CO2 flooding for tight oil reservoir development, optimize the development process in a timely manner, significantly reduce the required costs, and make it a more feasible carbon utilization and EOR strategy.

A Novel Method for the Quantitative Evaluation of Retrograde Condensate Pollution in Condensate Gas Reservoirs

During the development of condensate gas reservoirs, the phenomenon of retrograde condensation seriously affects the production of gas wells. The skin factor caused by retrograde condensation pollution is the key to measuring the consequent decrease in production. In this study, a multiphase flow model and a calculation model of retrograde condensate damage are first constructed through a dynamic simulation of the phase behavior characteristics in condensate gas reservoirs using the skin coefficient, and these models are then creatively coupled to quantitatively evaluate retrograde condensation pollution. The coupled model is solved using a numerical method, which is followed by an analysis of the effects of the selected formation and engineering parameters on the condensate saturation distribution and pollution skin coefficient. The model is verified using actual test data. The results of the curves show that gas–liquid two-phase permeability has an obvious effect on well production. When the phase permeability curve changes from the first to the third type, the skin coefficient increases from 3.36 to 26.6, and the condensate precipitation range also increases significantly. The distribution of the pollution skin coefficient also changes significantly as a result of variations in the formation and dew point pressures, well production, and formation permeability. The average error between the calculated skin of the model and the actual test skin is 3.87%, which meets the requirements for engineering calculations. These results have certain significance for guiding well test designs and the evaluation of condensate gas well productivity.