Minimum Miscibility Pressure Prediction Research Articles

Optimizing Minimum Miscibility Pressure Prediction Using Machine Learning: A Comprehensive Evaluation and Validation

Optimizing Minimum Miscibility Pressure Prediction Using Machine Learning: A Comprehensive Evaluation and Validation

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.

A One-Dimensional Convolutional Neural Network for Fast Predictions of the Oil-CO2 Minimum Miscibility Pressure in Unconventional Reservoirs

Summary Miscible carbon dioxide (CO2) injection has proven to be an effective method of recovering oil from unconventional reservoirs. An accurate and efficient procedure to calculate the oil-CO2 minimum miscibility pressure (MMP) is a crucial subroutine in the successful design of a miscible CO2 injection. However, current numerical methods for the unconventional MMP prediction are very demanding in terms of time and computational costs which result in long runtime with a reservoir simulator. This work proposes to employ a one-dimensional convolutional neural network (1D CNN) to accelerate the unconventional MMP determination process. Over 1,200 unconventional MMP data points are generated using the multiple-mixing-cell (MMC) method coupled with capillarity and confinement effects for training purposes. The data set is first standardized and then processed with principal component analysis (PCA) to avoid overfitting. The performance of the proposed model is evaluated with testing data. By applying the trained model, the unconventional MMP results are almost instantly produced and a coefficient of determination of 0.9862 is achieved with the testing data. Notably, 98.58% of predicting data points lie within 5% absolute relative error. This work demonstrates that the prediction of unconventional MMP can be significantly accelerated, compared with the numerical simulations, by the proposed well-trained deep learning model with a slight impact on the accuracy.

RNN-based CO2 minimum miscibility pressure (MMP) estimation for EOR and CCUS applications

Accurate estimation of minimum miscibility pressure (MMP) is crucial for assessing the efficiency of most miscible and immiscible processes, specifically CO2-based enhanced oil recovery (EOR) methods and Carbon capture utilization and sequestration (CCUS). The experimental procedure for MMP prediction is often time-consuming and costly. On the other hand, the empirical models that have been historically used could work based on limited input parameters, ignore the importance of others and are not necessarily accurate. The novelty of the current study is using an explainable deep-learning approach, Recurrent neural network (RNN), to train a model using a multi-dimensional (22 features) dataset with 544 rows of data. The Dataset comprises mole fractions of injected gas (pure and impure CO2). Out of those features, eight subsets of parameters (labelled X_1 to X_8) were used to develop models. The multi-dimensionality of the dataset makes it suitable to study the effects of various parameters on MMP, specifically in conditions of interest to CCUS-EOR applications. Among the multiple inputs tested, the model trained with X_1 and X_8 input parameters (including mole fraction of different hydrocarbon and nonhydrocarbon components and reservoir temperature) resulted in the most accurate estimations of MMP (R2 = 0.99). To further enhance the explainability of the model, feature importance and shapely values analysis were conducted on the developed models, and the impact of each input feature on MMP was elaborated. Temperature, volatile/intermediate, and nonhydrocarbon components are the most influential parameters depending on the subset of parameters chosen. Moreover, the developed model using X_8 inputs performed significantly better (37 % more accurately) than three well-known empirical models from the literature.

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.

Minimum Miscibility Pressure Prediction Method Based On PSO-GBDT Model

With the development of EOR technology, CO2 flooding was a very promising method to improve the recovery of conventional and unconventional oil reservoirs. MMP (minimum miscibility pressure ) was one of the important parameters of the CO2 flooding, and the use of an artificial intelligence algorithm can accurately predict the MMP, which was important to evaluate the effect of CO2 flooding development in the reservoir.   This work presents methods to automatically find optimal parameter settings for machine learning model by using an evolutionary algorithm. In this paper, 195 sets of experimental data of MMP were collected and screened from a large amount of literature for model establish, and sensitivity analysis was performed with the Pearson's method for feature selection. Then, five machine learning algorithms were used for regression and comparison. Finally, a particle swarm optimization algorithm was used to optimize the parameters of the machine learning model with best performance. The accuracy of the training set obtained by the hybrid model was 99.9% and the accuracy of the test set was 97.6%. It indicated that the hybrid model are valid and accurate, and it can be used for MMP prediction in both laboratory and actual field.

Prediction of minimum miscibility pressure (MMP) of the crude oil-CO2 systems within a unified and consistent machine learning framework

In this study, considering the differences of minimum miscibility pressure (MMP) measured with the slim-tube and rising bubble apparatus (RBA) methods and taking each individual compound and the parameter representing the source of MMP measurement as the input, a new machine learning model has been proposed and validated to determine MMPs of the crude oil-CO2 systems by use of the one-dimensional convolutional neural network (1D-CNN). Then, the differences of the aforementioned two MMP measurement methods and each individual factor on the predicted MMP are analyzed by using the SHapley Additive exPlanations (SHAP). Compared to the existing models that ignore the differences of MMPs obtained from different experiments and taking the pseudocomponents as the input, the newly proposed model not only has the lowest mean absolute percentage error (MAPE) of 7.29%, lowest mean square error (MSE) of 3.7916, and highest R2 of 0.9458 on the slim-tube test dataset, but also can be used to accurately reflect the relationship between the MMP and each of its influential factor. Furthermore, it is observed that there is a very good correlation between the MMP measured with the slim-tube and the RBA methods to capture the corresponding physics in such two experiments within a unified, consistent, and efficient framework.

Prediction of Minimum Miscibility Pressure for CO2 Flooding Based on Microscopic Pore-Throat Structure

CO2 flooding can effectively enhance the recovery of low-permeability reservoirs and realize CO2 geological storage. During the displacement process, the minimum miscible pressure (MMP) of CO2 and oil is an important parameter that affects the displacement effect and storage efficiency. However, the microscopic pore-throat structure of low-permeability reservoirs has significant influences on the fluids and phase behaviors. This paper presented a method to determine the miscible state of CO2 flooding based on the microscopic pore-throat structure. Firstly, a physic model was established to quantitatively characterize the microscopic pore-throat structure. Secondly, taking into consideration the P-R equation of state, the gas-liquid equilibrium in the narrow pore-throat was calculated. On this basis, a MMP prediction model was established correspongdingly by considering the multi-stage contact and mass transfer of CO2-oil. Finally, the results obtained by the proposed model were compared with the experimental results of CO2 flooding, and then the model was applied to the actual reservoir to predict plane distribution of MMP. The curves of MMP distribution and pressure drawdown between wells were combined to determine the position of miscible front and non-miscible area at different production stages. The results have shown that the MMP of core sample calculated by the model was 20.3 MPa, which was comparable to that of CO2 flooding experiment, e.g., 20 MPa, and thus indicatesd a high accuracy of the model. The MMP in the well control area of the Y29-101 well group was 19.8 MPa. During the unsteady flow stage, the miscible-phase front was 430 m from the injection well, while it was 310 m from the injection well during the stable flow stage. This method can accurately determine the specific phase distribution of CO2-oil in the formation, which is of great significance to promote the development of CO2 flooding and storage technology, improve the recovery of low permeability reservoirs, ensure energy supply and reduce carbon emission.

Reliable estimate of minimum miscibility pressure from multiple possible EOS models for a reservoir oil under data constraint

Multiple Equation of State (EOS) models are possible for a reservoir oil if limited laboratory data is used in the EOS model development; each EOS model has its own predicted minimum miscibility pressure (MMP) value with unknown reliability. This article presents a novel approach to estimate a reliable MMP value using the multiple MMP values calculated from multiple EOS models developed with limited laboratory data such as bubble point and density at bubble point. MMP predicted using the proposed approach has better accuracy than the estimated MMP from an EOS model developed using a large set of data at the regression stage. Each possible EOS model for a reservoir oil has a specific set of values of total Gibbs free energy of mixing (g) at bubble point and predicted MMP for a given injection gas. The MMP estimate is developed using the trend of g versus MMP (predicted) from multiple EOS models in the proposed approach. The AARD in MMP prediction for 22 oils is 5.21% using SRK EOS and 6.65% using PR EOS, which is lower than the earlier approach (7.6%) that uses all PVT, swelling test, and multi-contact test data in EOS model development.

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.

Multiple-Mixing-Cell Model for Calculation of Minimum Miscibility Pressure Controlled by Tie-Line Length

A simple and robust algorithm has been developed to calculate the minimum miscibility pressure (MMP), which is considered one of the crucial and essential design parameters of miscible gas injection projects for enhanced oil recovery (EOR). This algorithm is to track all tie-line lengths through the cell-cell calculation by the minimum distance function for the prediction of MMP. The MMP is the pressure at which any one of all key tie-line lengths becomes zero. To verify the accuracy of the revised MMC algorithm for determining MMP, several examples taken from the published literature have been examined. The calculation results of our revised MMC algorithm show excellent agreement with those estimated by MOC, MMC, and slim-tube experiments, which are found to be reliable within acceptable accuracy (4.53%-0.50%).

Intelligent Prediction of Minimum Miscibility Pressure (MMP) During CO2 Flooding Using Artificial Intelligence Techniques

Carbon dioxide (CO2) injection is one of the most effective methods for improving hydrocarbon recovery. The minimum miscibility pressure (MMP) has a great effect on the performance of CO2 flooding. Several methods are used to determine the MMP, including slim tube tests, analytical models and empirical correlations. However, the experimental measurements are costly and time-consuming, and the mathematical models might lead to significant estimation errors. This paper presents a new approach for determining the MMP during CO2 flooding using artificial intelligent (AI) methods. In this work, reliable models are developed for calculating the minimum miscibility pressure of carbon dioxide (CO2-MMP). Actual field data were collected; 105 case studies of CO2 flooding in anisotropic and heterogeneous reservoirs were used to build and evaluate the developed models. The CO2-MMP is determined based on the hydrocarbon compositions, reservoir conditions and the volume of injected CO2. An artificial neural network, radial basis function, generalized neural network and fuzzy logic system were used to predict the CO2-MMP. The models’ reliability was compared with common determination methods; the developed models outperform the current CO2-MMP methods. The presented models showed a very acceptable performance: the absolute error was 6.6% and the correlation coefficient was 0.98. The developed models can minimize the time and cost of determining the CO2-MMP. Ultimately, this work will improve the design of CO2 flooding operations by providing a reliable value for the CO2-MMP.

Four Methods to Estimate Minimum Miscibility Pressure of CO2‐Oil Based on Machine Learning

Summary of main observation and conclusionCO2 flooding accounts for a considerable proportion in gas flooding. Using CO2 as a gas displacement agent is benefit for enhanced oil recovery (EOR), and the alleviation of the greenhouse effect by the permanent storage of CO2 in the crust. Minimum miscibility pressure (MMP) of CO2‐oil is a key factor affecting EOR, which determines the yield and economic benefit of crude oil recovery. Therefore, it is of great importance to use fast, accurate and cheap prediction methods for MMP estimation. In the present study, to evaluate the reliability of four recently developed prediction models based on machine learning (i.e., neural network analysis (NNA), genetic function approximation (GFA), multiple linear regression (MLR), partial least squares (PLS)), 136 sets of data are selected for calculation via outlier analysis from 147 sets of data. Afterwards, we compared the four models with existing prediction models from the literature. The analysis of correlation coefficients and multiple error functions shows that the four models can solve the MMP prediction problem well, and the model using intelligent algorithm has a higher prediction accuracy than the simple linear model. Besides, intelligent methods based on similarity algorithm have little difference from each other. Finally, a sensitivity analysis was conducted.

An improved method for predicting CO2 minimum miscibility pressure based on artificial neural network

The CO 2 enhanced oil recovery (EOR) method is widely used in actual oilfields. It is extremely important to accurately predict the CO 2 minimum miscibility pressure (MMP) for CO 2 -EOR. At present, many studies about MMP prediction are based on empirical, experimental, or numerical simulation methods, but these methods have limitations in accuracy or computation efficiency. Therefore, more work needs to be done. In this work, with the results of the slim-tube experiment and the data expansion of the multiple mixing cell methods, an improved artificial neural network (ANN) model that predicts CO 2 MMP by the full composition of the crude oil and temperature is trained. To stabilize the neural network training process, L2 regularization and Dropout are used to address the issue of over-fitting in neural networks. Predicting results show that the ANN model with Dropout possesses higher prediction accuracy and stronger generalization ability. Then, based on the validation sample evaluation, the mean absolute percentage error and R-square of the ANN model are 6.99 and 0.948, respectively. Finally, the improved ANN model is tested by six samples obtained from slim-tube experiment results. The results indicate that the improved ANN model has extremely low time cost and high accuracy to predict CO 2 MMP, which is of great significance for CO 2 -EOR. Cited as : Dong, P., Liao, X., Chen, Z., Chu, H. An improved method for predicting CO 2 minimum miscibility pressure based on artificial neural network. Advances in Geo-Energy Research, 2019, 3(4): 355-364, doi: 10.26804/ager.2019.04.02

Modeling minimum miscibility pressure of pure/impure CO2-crude oil systems using adaptive boosting support vector regression: Application to gas injection processes

Carbon dioxide based enhanced oil recovery (CO2-EOR) techniques have been of great interest due to CO2 effectiveness as an oil solvent under supercritical condition and potential application to the sequestration purposes of CO2. Appropriate design of these techniques such as CO2 gas injection process needs accurate knowledge of the minimum miscibility pressure (MMP) allowing to the injected gas to be miscible with the oil. In this paper, three intelligent models named group method of data handling (GMDH), adaptive boosting support vector regression (AdaBoost SVR) and multi-layer perceptron (MLP) were implemented for MMP prediction in systems oil - CO2 streams. To this end, a widespread databank covering extended range of reservoirs and thermodynamic conditions was considered. The data bank covers dead and live oils under reservoir temperatures up to 388.73 K, while the gathered real MMP values were ranged between 6.54 MPa and 31.30 MPa. Graphical and statistical assessment criteria were performed to examine the reliability of the implemented paradigms and to compare them with the most well-known models. The results of this study indicated that the established models outperform the existing ones. In addition, among the proposed models, AdaBoost SVR has the highest accuracy with an Average Absolute Percent Relative Error (AAPRE) of 3.09% and Root Mean Square Error (RMSE) of 0.9 MPa. All of the proposed models can be applied in gas injection processes to prevent overestimation and underestimation of MMP, leading to appropriate performance of gas injection.

A Modified Multiple-Mixing-Cell Algorithm for Minimum Miscibility Pressure Prediction with the Consideration of the Asphaltene-Precipitation Effect

Minimum miscibility pressure (MMP) is one of the most important design parameters in CO2 flooding. Recent experimental studies show that asphaltene precipitation in light oils increases the MMP bet...

Minimum Miscibility Pressure Using the Multiple Mixing-cell Combined with the PC-SAFT Equation of State

The minimum miscibility pressure (MMP) is one of the crucial and substantial parameters in the gas injection projects for enhanced oil recovery (EOR). This parameter indicates the minimum pressure at constant temperature and composition conditions for reaching 100 percent of the oil production recovery which leads to a huge economic income. Therefore, an inaccurate prediction of the MMP may lead to increase the costs of oil production. Among the various methods for prediction of the MMP: slim-tube experiment, slim-tube simulation techniques and their simplified cell-to-cell could be considered as the most accurate methods. Although the experimental methods for calculation the MMP take into account the real crude oil, but they are always expensive; therefore, thermodynamic simulation is a better way for the estimation of this parameter. Indeed, the analytical methods are fast and some of them like multiple mixing-cell method used in this study lead to the reliable results and often show good agreements with the experimental methods. A combination of multiple mixing-cell model proposed by Ahmadi and Johns and pressure-temperature (P-T) flash calculations including the PC-SAFT equation of state (EoS), and the cubic equations of state of Peng-Robinson (PR) and Esmaeilzadeh-Roshanfekr (ER) were used in this work for the prediction of MMP. The results overally prove that the PC-SAFT EoS leads to more accurate results in comparison with the ER and PR equations of state.

Prediction of minimum miscibility pressure of pure CO2, carbon dioxide gas mixtures and polymer-supercritical CO2 in oil using modified quadrupole Cubic Plus Association Equation of State (mqCPA EoS)

In this work, the modified quadrupole Cubic Plus Association Equation of State (mqCPA EoS) is used to predict the minimum miscibility pressure (MMP) of pure carbon dioxide, carbon dioxide gas mixtures and polymer-supercritical carbon dioxide (scCO2) systems with the different oils. Carbon dioxide is accounted as a quadruple molecule and by applying Ahmadi and Johns's algorithm, which is a multiple mixing cell (MMC) method, minimum miscibility pressures (MMP) for some scCO2-oil systems are predicted. Moreover, a specific parameterization work was performed so that the new binary interaction parameters, kij, were optimized for the hydrocarbon-CO2 pairs using mqCPA with the quadropolar term. For comparison of the present equation of state (EoS) with the common EoSs, the predictive Peng-Robinson 78 (PPR78) and Soave-Redlich-Kwong (SRK) are applied along with the binary interaction parameter correlations of the Pedesen and Xu et al. kij (Industrial & Engineering Chemistry Research, 54 (2015) 2816–2824). The obtained MMP values by mqCPA EoS are compared to the experiments and those obtained using the PPR78 and SRK EoSs. It is shown that the calculated results by mqCPA EoS demonstrate a good agreement with the experimental values, especially for injected of pure CO2 and leads to the better results in comparison with PPR78 and SRK EoSs. To predict MMP of the polymer-scCO2 systems, three types of poly(lactic acid) (PLA), three types of poly(1-O-(vinyloxy) ethyl-2,3,4,6-tetra-O-acetyl-β-d-glucopyranoside) (P(AcGlcVE)) and seven types of poly(vinyl acetate-alt-dibutyl maleate) (PVAc-alt-PDBM) are used. To our best knowledge, this is the first effort to predict the MMP of these polymer-scCO2-oil systems.

Estimation of minimum miscibility pressure (MMP) in enhanced oil recovery (EOR) process by N2 flooding using different computational schemes

Nitrogen is an effective agent to be considered in gas injection processes as a part of enhanced oil recovery (EOR) process. Successful design and implementation of nitrogen flooding scenarios greatly depend on accurate prediction of minimum miscibility pressure (MMP). This work highlights the application of three models namely GA-RBF, PSO-ANFIS and MLP for estimation of pure and impure MMP value in nitrogen-crude oil systems based on reliable and valid experimental data covering a wide range of operational parameters gathered from literature. Various statistical and graphical methods were utilized to evaluate the performance of the developed models. The results of the developed models are also compared with reported literature methods for estimation of nitrogen MMP. Results show that the proposed GA-RBF, CHPSO-ANFIS and MLP models are accurate for estimation of experimental data with overall average absolute relative errors of 1.9%, 2.92% and 3.59% and overall R2 values of 0.9847, 0.9686 and 0.9485, respectively. Moreover, the proposed models successfully outperform other literature methods and present more accurate and reliable results.

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.