Oil Minimum Miscibility Pressure Research Articles

Unveiling the Effect of Complex Components on CO2-Oil Minimum Miscibility Pressure: Insights from Deep Convolutional Neural Networks

Unveiling the Effect of Complex Components on CO₂-Oil Minimum Miscibility Pressure: Insights from Deep Convolutional Neural Networks

Improved Least Squares Support Vector Machine Model Based on Grey Wolf Optimizer Algorithm for Predicting CO2–Crude Oil Minimum Miscibility Pressure

The minimum miscibility pressure (MMP) is an important reference parameter in the study of CO2 oil drive systems. In response to the problems of time‐consuming and costly prediction of MMP by conventional experimental methods, an improved least squares support vector machine (LSSVM) model based on grey wolf optimizer (GWO) algorithm is proposed to predict the CO2–crude oil MMP. Based on Pearson correlation analysis, reservoir temperature, C5+ molecular weight, intermediate component mole fraction, and volatile component mole fraction are selected as independent variables of the model, and MMP is the dependent variable. A total of 51 MMP experimental data are collected, of which 35 are used to fine‐tune the model's parameters and 16 are used to verify the model's reliability. The high leverage point method is used to detect anomalies in all experimental data to check the reliability of the model, and the abnormality of only one piece of experimental data is identified. Finally, a comparison of the model with other intelligent models is found. The absolute relative deviation of the GWO‐LSSVM model is 2.24% for the training data and 3.48% for the test data, which provides high adaptability and accuracy.

Nanometer-Scale CO2-Shale Oil Minimum Miscibility Pressure Calculations Based on Modified PR-EOS

CO2 flooding is recognized as an efficient method for enhancing shale oil recovery, while CO2-oil MMP (minimum miscibility pressure) in the micro-nanoscale is a crucial parameter. This paper presents a method for calculating the MMPs of pure hydrocarbons (C4H10, C6H14, C8H18, and C10H22) and CO2 systems in nanopores (3 nm to 10 nm) with temperature ranging from 290.15 K to 373.15 K. Firstly, we modify the Peng-Robinson equation of state (PR-EOS) by considering the influence of confinement effect and capillary pressure in nanopores. Secondly, the flash calculation algorithm is employed to determine whether the oil and gas phases in nanopores have reached an equilibrium state according to the equality of the fugacity of the two phases. Thirdly, we calculate the interfacial tension (IFT) between the two phases using the Macleod-Sugden equation. When the extrapolated IFT is zero, we treat the corresponding pressure as the MMP of the CO2-oil system in nanopores. Simulation results indicate that the calculated MMP using this method has a relative error of about 0.62% compared to the MMP calculated using the multiple mixing cell (MMC) method, indicating high reliability for MMP prediction. Moreover, the measured MMP at the nanoscale is generally smaller than that in the bulk phase due to the influence of the confinement effect. The MMP is positively correlated with the reservoir temperature, the carbon atom number in alkanes, and the nanopore radius.

The Effect of Formation Water Salinity on the Minimum Miscibility Pressure of CO2-Crude Oil for Y Oilfield

CO2 miscible flooding is an important technology for enhancing oil recovery and greenhouse gas storage in the world. As a tertiary recovery technology, it is usually applied after water flooding. Therefore, the actual reservoirs usually contain a lot of injected water in addition to connate water. The salinity of these formation waters varies from place to place. CO2 is an acid gas. After it is injected into the reservoir, it easily reacts with formation water and rock and affects the physical properties of the reservoir. However, no research results have been reported whether this reaction affects the minimum miscibility pressure (MMP) of CO2-crude oil, a key parameter determining miscible flooding in formation water. Based on CO2-formation water–rock interaction experiments, this paper uses the core flooding method to measure the CO2-crude oil MMP under different salinity in formation water. Results show that CO2 causes a formation water pH decrease from 7.4 to 6.5 due to its dissolution in formation water. At the same time, CO2 reacts with formation water, albite, potassium feldspar, and carbonate minerals in the cores to generate silicate and carbonate precipitates, which could migrate to the pore throat together with the released clay particles. Overall, CO2 increased core porosity by 5.63% and reduced core permeability by 7.43%. In addition, when the salinity of formation water in cores was 0, 4,767, and 6,778 mg/L, the MMP of CO2-crude oil was 20.58, 19.85, and 19.32 MPa, respectively. In other words, the MMP of CO2-crude oil decreased with the increase of salinity of formation water.

Use of hybrid-ANFIS and ensemble methods to calculate minimum miscibility pressure of CO2 - reservoir oil system in miscible flooding process

CO2 injection is believed to be a reliable carbon dioxide sequestration and enhanced hydrocarbon recovery technique. Accurate calculation of minimum miscibility pressure (MMP) is of great importance for the design and implementation of CO2 injection processes. This study involves an innovative machine learning-based algorithm called AdaBoost integrated with the classification and regression tree (AdaBoost-CART) to accurately calculate the CO2-reservoir oil MMP for streams with various compositions. Furthermore, another model is presented on the basis of hybrid-adaptive neuro-fuzzy inference system (ANFIS). The reservoir temperature, composition of injection gas, critical temperature of the drive gas (in average), molecular weight of C5+ fraction in crude oil (MW C5+), and ratio of volatile to intermediate components in crude oil (Vol./Int.) are the independent input parameters considered for the modeling. A large number of data available in technical papers related to intelligent models were selected for comparison purpose. The results reveal the accuracy of the presented Hybrid-ANFIS and AdaBoost-CART models over models selected from the literature. It was also found that the most precise results can be obtained using the developed AdaBoost-CART model as the average absolute relative deviation percent is 0.40. The proposed models can be incorporated in various chemical and petroleum engineering simulators for more accurate and reliable MMP calculations.

Direct Measurement of Minimum Miscibility Pressure of Decane and CO2 in Nanoconfined Channels.

Determining gas and oil minimum miscibility pressure (MMP) plays a vital role in the enhanced oil recovery. Injecting gases above the MMP into oil reservoirs leads to a relatively high oil recovery ratio. For conventional reservoirs, the fluid bulk MMP is measured by lab techniques such as the rising bubble approach. However, for the increasingly important tight and shale reservoirs, oil is confined in nanoscale pores. Nanoscopic MMP remains largely unknown from experiments and relies heavily on theoretical predictions. To close this gap, we developed a nanofluidic device to determine the MMP down to 50 nm by measuring the fluorescence intensity change in a nanoconfined channel. CO2 and decane are used as the working fluids, with 1% fluorescent dye for characterization. At the isothermal condition, the fluorescence intensity in decane reduces with the injecting CO2 pressure increasing, and the maximum fluorescence intensity reduction at certain CO2 pressure indicates the MMP being reached. We measured and compared CO2 and decane MMP at the bulk scale (5 μm) and nanoscale (50 nm). The experimental results align well with literature data and theoretical predictions. Importantly, our nanofluidic approach provides a promising strategy to determine the nanoscopic fluid MMP and is readily applicable in assisting the enhanced tight/shale oil recovery.

Chemistry of Reservoir Fluids in the Aspect of CO2 Injection for Selected Oil Reservoirs in Poland

Worldwide experiences related to geological CO2 storage show that the process of the injection of carbon dioxide into depleted oil reservoirs (CCS-EOR, Carbon Capture and Storage—Enhanced Oil Recovery) is highly profitable. The injection of CO2 will allow an increasing recovery factor (thus increasing CCS process profitability) and revitalize mature reservoirs, which may lead to oil spills due to pressure buildups. In Poland, such a solution has not yet been implemented in the industry. This work provides additional data for analysis of the possibility of the CCS-EOR method’s implementation for three potential clusters of Polish oil reservoirs located at a short distance one from another. The aim of the work was to examine the properties of reservoir fluids for these selected oil reservoirs in order to assure a better understanding of the physicochemical phenomena that accompany the gas injection process. The chemical composition of oils was determined by gas chromatography. All tested oils represent a medium black oil type with the density ranging from 795 to 843 g/L and the viscosity at 313 K, varying from 1.95 to 5.04 mm/s. The content of heavier components C25+ is up to 17 wt. %. CO2–oil MMP (Minimum Miscibility Pressure) was calculated in a CHEMCAD simulator using the Soave–Redlich–Kwong equation of state (SRK EoS). The oil composition was defined as a mixture of n-alkanes. Relatively low MMP values (ca. 8.3 MPa for all tested oils at 313 K) indicate a high potential of the EOR method, and make this geological CO2 storage form more attractive to the industry. For reservoir brines, the content of the main ions was experimentally measured and CO2 solubility under reservoir conditions was calculated. The reservoir brines showed a significant variation in properties with total dissolved solids contents varying from 17.5 to 378 g/L. CO2 solubility in brines depends on reservoir conditions and brine chemistry. The highest calculated CO2 solubility is 1.79 mol/kg, which suggest possible CO2 storage in aquifers.

A novel system for reducing CO2-crude oil minimum miscibility pressure with CO2-soluble surfactants

Due to its lower viscosity and thus better injectivity than water, CO2 injection has attracted lots of attention in tight oil recovery. Lowering the minimum miscible pressure (MMP) of CO2 and crude oil for an easier realization of the miscible condition where crude oil is displaced the most efficiently by CO2 is critical in CO2 injection. However, the limited solubilities of most surfactants in CO2 impose difficulties in reducing the MMP as surfactants can hardly in presence at the interface to lower the interfacial tension (IFT). In this work, we overcome this limitation by introducing ethanol as a co-solvent to notably promote the solubilities of four different surfactants (NP-9, 2EH-PO5-EO9, AOT, and TXIB) in CO2. As a consequence of the enhanced solubilities, the surfactants reduce more efficiently the CO2-crude oil IFT and MMP. Systematical measurements of CO2-crude oil IFT are conducted to distinguish the efficiencies of the four surfactants with and without ethanol as co-solvent. Based on the measured IFT, solubilities, and partition coefficients of the surfactants in CO2 and crude oil, a mechanistic understanding of the synergy between ethanol and surfactants are proposed. Under the optimal conditions of 7 wt% ethanol and 0.3 wt% TXIB, the MMP of crude oil and CO2 can be reduced as much as 30.2%. The remarkable reduction of MMP is very intriguing and will be highly beneficial in tight oil recovery.

Estimation of minimum miscibility pressure during CO2 flooding in hydrocarbon reservoirs using an optimized neural network

CO2 flooding recovery strongly depends on the minimum miscibility pressure (MMP). Conventional tests to determine gas–oil MMP such as rising bubble apparatus and slim tube displacement are either costly or time consuming. In order to propose a quick and accurate model to determine MMP, a back-propagation neural network is presented for MMP prediction during pure and impure CO2 injections. Five new variables were screened as input parameters to the network. Next, the network was optimized using five evolutionary algorithms, and this work highlights that three of these evolutionary algorithms (e.g. Mind Evolutionary, Artificial Bee Colony, and Dragonfly) are firstly used to predict MMP. Then, data from the literature were input to the optimized network to train it. Statistical evaluation and graphical analyses were used to evaluate the performance of the proposed models and for comparison with published MMP correlates to obtain the optimal model for predicting MMP. The back-propagation model optimized using the dragonfly algorithm exhibited the highest accuracy among all those considered and MMP correlates; its coefficient of determination, average absolute percent relative error, root mean square error, and standard deviation were 0.965, 5.79%, 206.1, and 0.08, respectively. In addition, reservoir temperature was determined as the strongest MMP predictor (Pearson correlation = 0.63) based on sensitivity analysis.

Experimental Investigation of Asphaltene Content Effect on Crude Oil/CO2 Minimum Miscibility Pressure

Minimum Miscibility Pressure (MMP) is regarded as one of the foremost parameters required to be measured in a CO2 injection process. Therefore, a reasonable approximation of the MMP can be useful for better development of injection conditions as well as planning surface facilities. In this study, the impact of asphaltene content ranging from 3.84 % to 16 % on CO2/heavy oil MMP is evaluated. In this respect, slim tube miscibility and Vanishing Interfacial Tension (VIT) tests are used. Regarding the VIT test, the Interfacial Tension (IFT) is measured by means of two methods including pendant drop and capillary apparatuses, and thereafter the MMP measurement error between slim tube and VIT methods are calculated. Based on the results, by increasing the asphaltene content, the measured MMP by slim tube method increases linearly while that by VIT follows no clear trend. The results also indicate that there is an asphaltene content range within which the MMP error between slim tube and VIT tests is minimized. IFT measurement by pendant drop and Capillary Glass Tube (CGT) methods show that by increasing asphaltene content up to 10.15 %, IFT declines, whereas for further increase in content, IFT increases because of the irregular dispersion of asphaltene in oil droplets.

Prediction of CO2‐Oil Minimum Miscibility Pressure Using Soft Computing Methods

AbstractSearching for computational approaches for determination of the minimum miscibility pressure (MMP) is highly requested during the miscible gas injection process. New models, namely, the stochastic gradient boosting (SGB) algorithm and two distinct hybrid artificial neural network (ANN) models were used to predict CO2 MMP as a function of reservoir temperature, mole percent of volatile oil components, mole percent of intermediate oil components, molecular weight of pentane‐plus fraction in the oil phase, mole percentage of CO2 in injected gas, volatile components, and intermediate components in the injected gas based on 144 published data points. The SGB model was found to provide the better performance. The reservoir temperature turned out to be the most important factor.

Experimental Study on Reducing CO2–Oil Minimum Miscibility Pressure with Hydrocarbon Agents

CO2 flooding is an important method for improving oil recovery for reservoirs with low permeability. Even though CO2 could be miscible with oil in regions nearby injection wells, the miscibility could be lost in deep reservoirs because of low pressure and the dispersion effect. Reducing the CO2–oil miscibility pressure can enlarge the miscible zone, particularly when the reservoir pressure is less than the needed minimum miscible pressure (MMP). Furthermore, adding intermediate hydrocarbons in the CO2–oil system can also lower the interfacial tension (IFT). In this study, we used dead crude oil from the H Block in the X oilfield to study the IFT and the MMP changes with different hydrocarbon agents. The hydrocarbon agents, including alkanes, alcohols, oil-soluble surfactants, and petroleum ethers, were mixed with the crude oil samples from the H Block, and their performances on reducing CO2–oil IFT and CO2–oil MMP were determined. Experimental results show that the CO2–oil MMP could be reduced by 6.19 MPa or 12.17% with petroleum ether in the boiling range of 30–60 °C. The effects of mass concentration of hydrocarbon agents on CO2–oil IFT and crude oil viscosity indicate that the petroleum ether in the boiling range of 30–60 °C with a mass concentration of 0.5% would be the best hydrocarbon agent for implementing CO2 miscible flooding in the H Block.

An improved correlation to determine minimum miscibility pressure of CO2–oil system

An accurate and reliable estimation of minimum miscibility pressure (MMP) of CO2–oil system is a critical task for the design and implementation of CO2 miscible displacement process. In this study, an improved CO2–oil MMP correlation was developed to predict the MMP values for both pure and impure CO2 injection cases based on ten influential factors, i.e. reservoir temperature (TR), molecular weight of C7+ oil components (MWC7+), mole fraction of volatile oil components (xvol), mole fraction of C2C4 oil components (xC2-C4), mole fraction of C5C6 oil components (xC5-C6), and the gas stream mole fractions of CO2 (yCO2), H2S (yH2S), C1 (yC1), hydrocarbons (yHC) and N2 (yN2). The accuracy of the improved correlation was evaluated against experimental data reported in literature concurrently with those estimated by several renowned correlations. It was found that the improved correlation provided higher prediction accuracy and consistency with literature experimental data than other literature correlations. In addition, the predictive capability of the improved correlation was further validated by predicting an experimentally measured CO2–oil MMP data, and it showed an accurate result with the absolute deviation of 4.15%. Besides, the differential analysis of the improved correlation was analyzed to estimate the impact of parameters uncertainty in the original MMP data on the calculated results. Also, sensitivity analysis was performed to analyze the influence of each parameter on MMP qualitatively and quantitatively. The results revealed that the increase of xC2-C4, xC5-C6 and yH2S lead to the decrease of MMP, while the increase of TR, MWC7+, xvol, yCO2, yC1, yHC and yN2 tend to increase the MMP. Overall, the relevance of each parameter with MMP follows the order of TR > xC5-C6 > MWC7+ >xvol > yH2S > yHC > yCO2 >yC1 >yN2 >xC2-C4.

Describing a strategy to estimate the CO2-heavy oil minimum miscibility pressure based on the experimental methods

ABSTRACTTo measure MMP, slim tube method is time consuming, especially for heavy oils. In this study, a strategy is considered to measure the MMP in one of the Iranian heavy oil reservoirs. The strategy steps were done through; partial data of slim tube, coupling numerical model (CNM), full slim tube, and VIT test. The results showed that CNM technique with two experimental data obtains the MMP value faster than running a full slim tube with low error result. However, VIT determined MMP faster and its results illustrated that miscibility pressure for heavy oil occurs at zero IFT, unlike light oils.

Molecular dynamics simulation to estimate minimum miscibility pressure for oil with pure and impure CO2

CO2 enhanced oil recovery (CO2-EOR) has gained great attention worldwide for increasing oil production and reducing greenhouse emissions. In CO2-EOR project, the minimum miscibility pressure (MMP) is the key factor to determine the possibility of CO2 miscible-phase displacement. In this study, we used molecular dynamics (MD) simulation to estimate the MMP of pure and impure CO2 with oil by obtaining interfacial tensions (IFTs) based on the vanishing interfacial tension technique. To get accurate IFTs, modified Lorentz-Berthelot rules were developed for all simulations. Then, we performed MD simulations for CO2 + n-hexane binary system, CO2 + n-hexane + n-decane ternary system and complex CO2 + crude oil system to calculate the MMPs. Firstly, MMPs predicted by MD simulation show good agreement with previous experimental data. Secondly, the effects of injected gas components, oil components and reservoir temperature on the MMP are investigated. The results demonstrate that methane and N2 will increase the MMP of CO2-oil system significantly; the effects of a certain oil component on the MMP depend on the properties of crude oil, generally speaking, heavy oil components will increase the MMP while light oil components decrease it; temperature will increase the MMP of CO2-oil system, while it will decrease the MMP of N2-oil system, which is due to their different solubility in oil. Thirdly, sensitivity analysis is conducted to evaluate the effects of those influence parameters on the MMP of CO2-oil system, finding that N2 concentration in CO2 and reservoir temperature have more significant impacts on the MMP.

Estimation of minimum miscibility pressure of varied gas compositions and reservoir crude oil over a wide range of conditions using an artificial neural network model

Minimum miscibility pressure (MMP) is a key variable for monitoring miscibility between reservoir fluid and injection gas. Experimental and non-experimental methods are used to estimate MMP. Available miscibility correlations attempt to predict the minimum miscibility pressure for a specific type of gas. Here an artificial neural network (ANN) model is applied to a dataset involving 251 data records from around the world in a novel way to estimate the gas-crude oil MMP for a wide range of injected gases and crude oil compositions. This approach is relevant to sequestration projects in which injected gas compositions might vary significantly. The model is correlated with the reservoir temperature, concentrations of volatile (C1 and N2) and intermediate (C2, C3, C4, CO2 and H2S) fractions in the oil (Vol/Inter), C5+ molecular weight fractions in the oil and injected gas specific gravity. A key benefit of the ANN model is that MMP can be determined with reasonable accuracy for a wide range of oil and gas compositions. Statistical comparison of predictions shows that the developed ANN model yields better predictions than empirical-correlation methods. The ANN model predictions achieve a mean absolute percentage error of 13.46%, root mean square error of 3.6 and Pearson's correlation coefficient of 0.95. Sensitivity analysis reveals that injected gas specific gravity and temperature are the most important factors to consider when establishing appropriate miscible injection conditions. Among the available published correlations, the Yellig and Metcalfe correlation demonstrates good prediction performance, but it is not as accurate as the developed ANN model.

The impacts of gas impurities on the minimum miscibility pressure of injected CO2-rich gas\u2013crude oil systems and enhanced oil recovery potential

An effective parameter in the miscible-CO2 enhanced oil recovery procedure is the minimum miscibility pressure (MMP) defined as the lowest pressure that the oil in place and the injected gas into reservoir achieve miscibility at a given temperature. Flue gases released from power plants can provide an available source of CO2, which would otherwise be emitted to the atmosphere, for injection into a reservoir. However, the costs related to gas extraction from flue gases is potentially high. Hence, greater understanding the role of impurities in miscibility characteristics between CO2 and reservoir fluids helps to establish which impurities are tolerable and which are not. In this study, we simulate the effects of the impurities nitrogen (N2), methane (C1), ethane (C2) and propane (C3) on CO2 MMP. The simulation results reveal that, as an impurity, nitrogen increases CO2–oil MMP more so than methane. On the other hand, increasing the propane (C3) content can lead to a significant decrease in CO2 MMP, whereas varying the concentrations of ethane (C2) does not have a significant effect on the minimum miscibility pressure of reservoir crude oil and CO2 gas. The novel relationships established are particularly valuable in circumstances where MMP experimental data are not available.

Application of hybrid support vector regression artificial bee colony for prediction of MMP in CO2-EOR process

Minimum miscibility pressure (MMP) is a key parameter in the successful design of miscible gases injection such as CO2 flooding for enhanced oil recovery process (EOR). MMP is generally determined through experimental tests such as slim tube and rising bubble apparatus (RBA). As these tests are time-consuming and their cost is very expensive, several correlations have been developed. However, and although the simplicity of these correlations, they suffer from inaccuracies and bad generalization due to the limitation of their ranges of application. This paper aims to establish a global model to predict MMP in both pure and impure CO2-crude oil in EOR process by combining support vector regression (SVR) with artificial bee colony (ABC). ABC is used to find best SVR hyper-parameters. 201 data collected from authenticated published literature and covering a wide range of variables are considered to develop SVR-ABC pure/impure CO2-crude oil MMP model with following inputs: reservoir temperature (TR), critical temperature of the injection gas (Tc), molecular weight of pentane plus fraction of crude oil (MWC5+) and the ratio of volatile components to intermediate components in crude oil (xvol/xint). Statistical indicators and graphical error analyses show that SVR-ABC MMP model yields excellent results with a low mean absolute percentage error (3.24%) and root mean square error (0.79) and a high coefficient of determination (0.9868). Furthermore, the results reveal that SVR-ABC outperforms either ordinary SVR with trial and error approach or all existing methods considered in this work in the prediction of pure and impure CO2-crude oil MMP. Finally, the Leverage approach (Williams plot) is done to investigate the realm of prediction capability of the new model and to detect any probable erroneous data points.

Evaluation of recycle gas injection on CO2 enhanced oil recovery and associated storage performance

An enhanced oil recovery (EOR) technique comprising the alternate injection of gas (CO2) and water, commonly referred to as water alternating gas (WAG) flooding, is currently ongoing at an oil field in the northeastern Powder River Basin (PRB), where 4 million barrels (MMbbl) of oil were produced between May 2013 and September 2017. During WAG flooding, a large amount of CO2, which contains some impurities, is produced at the surface with the recovered oil and reinjected into the reservoir to minimize the amount of purchased CO2. The concentration of these impurities in the CO2, which are dominated by CH4, is a key parameter in the design of miscible CO2 flooding of an oil reservoir and in the quantitative assessment of the associated storage of CO2 that occurs in the reservoir. For a given oil and reservoir temperature, the CO2–oil minimum miscibility pressure (MMP) is strongly and adversely affected by the presence of CH4, the concentration of which varies with time and operational conditions, such as injection pressure, flooding pattern, and injection scheme (i.e., continuous CO2 injection or WAG). To capture the full range of potential variation in the MMP caused by the presence of CH4, a series of laboratory experiments were conducted to determine CO2–oil MMP with different mole percentages of CH4 in the CO2. All of the experiments were performed at reservoir temperature (108 °F) using the VIT (vanishing interfacial tension) method. Results showed that MMP increases from 1403 to 4085 psi as the mole percentage of CH4 in the CO2 increases from 0% to 100%. To assess the impact of this variation in MMP on the oil recovery performance in the field, a history-matched, compositional reservoir simulation model was used to predict the oil production performance for a WAG flood using CO2 that contained a range of CH4 concentrations. The reservoir simulations examined the effects of permeability heterogeneity, fluid crossflow, and phase behavior on the oil displacement performance in three-dimensional space over time. Simulation results indicated that CO2 floods using a limited range of CO2–CH4 mixtures could still maintain multiple-contact miscibility and result in effective EOR. In addition, the ability to reinject produced CO2–CH4 mixtures as is, without removal of the CH4, ensured that this approach to EOR would continue to be cost-effective.

Application of adaptive neuro fuzzy interface system optimized with evolutionary algorithms for modeling CO2-crude oil minimum miscibility pressure

CO2 injection is known as one of the most reliable enhanced oil recovery techniques. The success of every gas injection process depends highly on the minimum miscibility pressure (MMP) needed for the injected gas and the oil to reach miscibility. Therefore, determination of the MMP between the two fluids is of great importance. In this study, a novel intelligent model based on adaptive neuro fuzzy interface system (ANFIS) was developed for predicting MMP values between pure/impure CO2 and reservoir oil at different reservoir conditions based on 270 experimental data points for pure and impure CO2, dead and live oils, reservoir temperature ranges from 293.72K to 388.73K, and experimental MMP values range from 6.54MPa to 31.30MPa. The ANFIS model was optimized by five different approaches; including Back Propagation (BP), Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO) and Differential Evolution (DE). A large number of data points from various sources of literature were gathered for model development and verification. In addition, various statistical and graphical error analyses were employed to evaluate the performance of the developed models as well as to compare them with major literature models for MMP prediction. The results showed that the ANFIS model optimized by PSO has the highest accuracy among all the models developed in this study as well as literature models, with an average absolute percent relative error of only 7.53%. In addition, all models developed in this study are more accurate than the existing models and their accuracy are as follows: ANFIS-PSO>ANFIS-GA>ANFIS-ACO>ANFIS-BP>ANFIS-DE. Lastly, the ANFIS models developed here can be inserted in any simulator to increase the accuracy of predicting pure and impure CO2-crude oil MMP.