Next Article in Journal
Quantum-Enhanced Representation Learning: A Quanvolutional Autoencoder Approach against DDoS Threats
Previous Article in Journal
Concept Paper for a Digital Expert: Systematic Derivation of (Causal) Bayesian Networks Based on Ontologies for Knowledge-Based Production Steps
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Review

A Comprehensive Summary of the Application of Machine Learning Techniques for CO2-Enhanced Oil Recovery Projects

by
Xuejia Du
,
Sameer Salasakar
and
Ganesh Thakur
*
Department of Petroleum Engineering, Cullen College of Engineering, University of Houston, Houston, TX 77204, USA
*
Author to whom correspondence should be addressed.
Mach. Learn. Knowl. Extr. 2024, 6(2), 917-943; https://doi.org/10.3390/make6020043
Submission received: 15 February 2024 / Revised: 22 April 2024 / Accepted: 26 April 2024 / Published: 29 April 2024

Abstract

:
This paper focuses on the current application of machine learning (ML) in enhanced oil recovery (EOR) through CO2 injection, which exhibits promising economic and environmental benefits for climate-change mitigation strategies. Our comprehensive review explores the diverse use cases of ML techniques in CO2-EOR, including aspects such as minimum miscible pressure (MMP) prediction, well location optimization, oil production and recovery factor prediction, multi-objective optimization, Pressure–Volume–Temperature (PVT) property estimation, Water Alternating Gas (WAG) analysis, and CO2-foam EOR, from 101 reviewed papers. We catalog relative information, including the input parameters, objectives, data sources, train/test/validate information, results, evaluation, and rating score for each area based on criteria such as data quality, ML-building process, and the analysis of results. We also briefly summarized the benefits and limitations of ML methods in petroleum industry applications. Our detailed and extensive study could serve as an invaluable reference for employing ML techniques in the petroleum industry. Based on the review, we found that ML techniques offer great potential in solving problems in the majority of CO2-EOR areas involving prediction and regression. With the generation of massive amounts of data in the everyday oil and gas industry, machine learning techniques can provide efficient and reliable preliminary results for the industry.

1. Introduction

There is a strong correlation between energy consumption and economic growth. Liquid fossil fuels are a key component of the energy mix, contributing up to about 35% of worldwide energy usage. While energy sources are diversifying, liquid fossil fuels are still a key energy source in developing countries such as India and China. The rapid development of these economies will most likely intensify energy generation from fossil fuels. This will unsurprisingly lead to CO2 emissions. CO2 emissions have been rising worldwide. The IPCC report on “Global Warming of 1.5 °C” declared a major concern that unless CO2 emissions are reduced by 50% by the year 2030, major changes will occur in the ocean and on the land, and unfortunately, they may be permanent in nature.
The time is of essence to globally transition to new energy systems. Bloomberg news mentions “Climate change is not a problem with a single solution. And it is not a challenge that any one group—governments, companies, scientists or individual citizens—can solve alone”. Working together, one can build a healthier and more sustainable future for the generations to come. Utilizing a variety of technologies, e.g., solar, wind, geo-thermal, nuclear, extended batteries, and hydrogen, and strong government support, dedicated companies, universities and research centers, regulatory agencies and others, we have a great opportunity to solve the problem.
We can distinguish two main strategies for reducing atmospheric concentrations of CO2. The first strategy includes reducing the emissions of CO2 to the atmosphere by increasing energy efficiency and switching to low-carbon fuel sources, utilizing proven and existing technologies, e.g., solar, wind and nuclear at a large scale and fast pace. The second strategy includes the deployment of negative emission technologies to remove carbon from the atmosphere and sequester it reliably. Some examples of this strategy may include DAC (direct air capture), CCS and CCUS (e.g., CO2 EOR). The potential impact of these technologies on reducing CO2 emissions is immense and should not be underestimated.
Our knowledge of the reservoir management of an oil and gas field from primary to tertiary recovery phases yields an understanding of its key properties. Hence, the use of mature or declining oil and gas reservoirs to store CO2 significantly reduces subsurface uncertainties. CO2 injection is a well-documented method for improving hydrocarbon production rates and increasing recovery. Thus, in light of climate concerns, using CO2 injection for the dual objectives of enhancing oil recovery and carbon storage is a powerful choice.
Petroleum resources have been deemed as the principal source of fossil-fuel-based energy to meet the world’s energy demands since the early 20th century. The importance of enhancing oil reservoir extraction efficiency has grown due to the restricted supply of reserves. Over two-thirds of the original oil in place (OOIP) remains trapped after primary and secondary recovery processes. Furthermore, extracting the remaining oil from mature reservoirs in complicated geological formations is more challenging. EOR methods are initiated to recover the remaining oil from reservoirs after both primary and secondary recovery methods have been exhausted. Surfactant flooding, chemical flooding, polymer flooding, steam stimulation, microbial flooding, gas injection, and so forth [1,2] are the common EOR approaches. Carbon dioxide (CO2) is very successful since it increases oil production by increasing mobility and reducing oil viscosity and saturation, which works well with both conventional and some unconventional formations. CO2-EOR is one of the popular techniques, occupying around 20% of 1120 worldwide EOR projects (Figure 1). It may recover 15% to 25% of the OOIP of the light or medium oil fields that are close to depletion due to flooding [3].
The utilization of CO2 in EOR can significantly improve oil recovery; at the same time, it plays an essential role in environmental preservation. The importance of CO2-EOR as part of carbon capture, use, and storage (CCUS) schemes becomes more vital as the petroleum industry works toward decarbonization to mitigate greenhouse gas emissions. If reinjection is not considered, approximately 60% of injected CO2 can be trapped in the reservoir at the CO2 breakthrough [5]. This approach, efficiently utilizing CO2 in oil recovery, aligns with an environmentally friendly protocol while simultaneously enhancing resource efficiency and contributing substantially to sustainability goals [6].
Machine learning (ML) approaches have drawn considerable interest as emerging technologies in the oil and gas industry over the past 20 years. Applying the ML approaches to examine issues in the oilfield development process has acquired new life with the advent of intelligent oilfields and big data technology. Indeed, ML shows the feasibility of offering a more straightforward and quicker method than rigorous and numerous simulations or experiments. Many ML correlations have emerged with the development of computer tools, particularly in reservoir characterization, CO2 storage, production, and drilling operations [7,8,9,10].
Many literature reviews have been conducted in the past to summarize the application of ML in the oil and gas industry [11]. However, no study on global research trends analyzed the dominant input parameters and evaluated the research work on CO2-EOR projects. The evaluations could help researchers get a preliminary idea about the current research trend on CO2-EOR and whether their recent research impacts a particular field. Furthermore, few studies have systematically summarized and examined all the literature on ML for CO2-EOR. Few reviews find the most critical topics, objectives, input parameters, evaluations, and research gaps in ML for CO2-EOR. This study aims to offer insight into current trends and technological development indicators, which will help identify the viewpoint for the following research areas and prospects. Thus, data extraction analysis was carried out to ascertain the research advancement and trends in ML for CO2-EOR, whereby a systematic review accomplishes the closure of research gaps on this subject.
This paper aims to summarize and evaluate the various ML models in CO2-EOR and provide insightful analysis with 101 papers reviewed. The rest of the paper is organized as follows: Section 2 describes the mechanisms and processes of CO2-EOR; Section 3 provides the most popular ML and optimization methods employed in the literature; Section 4 summarizes the work that has applied ML in the CO2-EOR process, including MMP prediction, WAG, well placement optimization, oil production or recovery factor prediction, multiple objectives optimization, PVT properties estimation, and CO2-foam; and Section 5 outlines the benefits and limitations of the application of ML in the CO2-EOR process, before ending this survey paper with concluding remarks.

2. Mechanisms and Processes of CO2-EOR

CO2 is generally injected into the reservoir under the following conditions: (a) miscible injection; (b) immiscible front displacement after water flooding; (c) water alternating gas (WAG) displacement; and (d) CO2 dissolved in brine flooding, also referred to as carbonated water injection (CWI) [12]. Miscible displacement has been successful over the years. It occurs at pressures above a minimum miscible pressure (MMP) of the oil, where the injected gas and the hydrocarbons are entirely miscible and form a single-phase fluid. The main advantages of miscible displacement are that it can promote oil swelling, reduce fluid viscosity, increase mobility, reduce remaining oil saturation, and improve oil production.
CO2 has been historically favored over other gases due to its low MMP. Furthermore, CO2 gas injection can potentially mitigate greenhouse gas emissions while improving oil recovery. CO2-miscible flooding, whether initiated upon first contact or multiple contacts, results in the remaining oil and CO2 becoming miscible, which leads to near-zero interfacial tension (IFT), no capillary pressure, and improved volumetric sweep (Ev) and displacement efficiency (Ed) [13]. Conversely, in the case of CO2-immiscible flooding, the IFT is not near zero, maintaining the capillary pressure and causing some residual oil saturation. The oil recovery efficacy is contingent upon the efficiency of fluid displacement, volumetric sweep, and CO2 solubility in the oleic phase, consequently increasing oil mobility. These characteristics are influenced by various factors, including gravity, rock wettability, reservoir heterogeneity, crude oil phase behavior, and phenomena such as viscous fingering, etc. [12,14].

3. Summary of Machine Learning Approaches

Machine learning (ML) involves the development of computational models and algorithms capable of learning patterns and making data-driven predictions or decisions without being explicitly programmed. ML algorithms employ data to automatically identify and generalize patterns, which may be applied for classification, regression, clustering, and more tasks. ML can be categorized into four main types: supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning. Figure 2 provides some examples of different ML algorithms. Among these various algorithms, supervised learning is most applied in the oil and gas industry [11].
For instance, ANNs have demonstrated remarkable efficacy in providing user-friendly, cost-effective, reliable, and expedited solutions to a variety of complex challenges encountered in the oil and gas industry. This is primarily attributed to the inherent complexity and non-linear nature of oil and gas datasets, which often have intricate relationships between input variables and output parameters. ANNs excel in capturing these complex relationships by effectively modeling non-linear functions. Moreover, oil and gas data are frequently characterized by noise, incompleteness, and heterogeneity. ANNs exhibit superior capability in handling such diverse data types and can adeptly adapt to varying data distributions, thereby making them highly versatile for addressing various tasks across different domains within the industry.
Furthermore, the enhancement of the ML process involves optimization techniques to determine optimal values for control parameters, including the spreading coefficient, number of neurons, biases, and weights. Several optimization methods, such as the Levenberg–Marquardt (LM) algorithm, genetic algorithm (GA), and smart nature-inspired swarm algorithms like particle swarm optimization (PSO), grey wolf optimization (GWO), and ant colony optimization (ACO), have demonstrated their efficacy in achieving significant improvements in these tasks. There are two categories in intelligent optimization algorithms: single-objective optimization and multi-objective optimization (Figure 3).

4. Application of ML in CO2-EOR

4.1. Minimum Miscibility Pressure (MMP)

In miscible gas injection, MMP is one of the most important parameters to determine the accuracy of miscible CO2 flooding into the reservoir. Traditionally, MMP is defined as the pressure at which 80% of the OOIP is extracted from the reservoir upon the breakthrough of CO2 [16]. Because CO2 flooding is more expensive than waterflooding, an accurate estimation of MMP can help better design miscible CO2 flooding, ultimately leading to cost savings. In the literature, researchers have proposed various MMP estimation approaches, including the following:
(a)
experimental methods such as slim-tube tests [17]; rising-bubble apparatus [18]; vanishing interfacial tension [19];
(b)
empirical correlations [17,20,21,22] and computational techniques such as single mixing-cell and multiple mixing-cell approaches [23].
However, though accurate and reliable, experimental methods are time-consuming and expensive. Most empirical correlations and computation techniques do not consider different thermodynamic and reservoir properties. Moreover, they exhibit limitations in accurately estimating the trend of MMP concerning their input parameters [24]. In contrast, the advent of ML has provided various robust algorithms in problems involving regression/classification. Consequently, considerable research studies dedicated to the precise modeling of MMP and the successful application of ML in this domain have been well documented.
The earliest application of ML on CO2-EOR MMP can be traced back to 2003, when Huang et al. [25] first introduced ANN into this field. Subsequently, Emera and Sarma [26] employed the GA to optimize the MMP prediction processes. Following the year 2010, there has been a gradual increase in the adoption of ML algorithms and optimization techniques, accompanied by a significant expansion of the available dataset. Nowadays, the application of ML in predicting MMP has evolved into a more mature state. A comprehensive survey of the literature review in the field of CO2-oil MMP estimation applying ML, spanning the period from 2003 to the present, is summarized in Table 1. Each reviewed paper is scrutinized and synthesized with respect to the employed algorithms, dataset size, data splitting methods, input variables, outcomes, our assessment, and a rating score. A paper deserving a high rating ought to exhibit certain characteristics, such as the following: a substantial dataset, typically comprising no fewer than 100 data points; a demonstration of effective model generalization without signs of overfitting, where the training dataset constitutes a maximum of 80% of the total data; and validation through empirical evidence derived from experimental and/or field data. Furthermore, a high-rated paper should demonstrate depth in result analysis, including a thorough examination of the outcomes in comparison to other existing models.
Figure 4 presents a statistical analysis from 56 research papers. It reveals a remarkable surge in the adoption of ML methodologies within this domain. ANN and GA have emerged as the most favored choices among many ML and optimization algorithms. ANNs, particularly RBFNN and MLP, are prominently employed. We have provided a separate categorization for RBFNN and MLP to afford a more detailed perspective on their individual utilization patterns.
Furthermore, an essential factor impacting the efficacy of ML models in MMP predictions is the size of the dataset. It is widely recognized that an inadequately sized dataset can lead to overfitting, potentially compromising the model’s generalizability. A substantial proportion of the examined papers (64%) have datasets with fewer than 200 data points, with a noteworthy subset (21%) relying on datasets with fewer than 100 data points. This stark discrepancy in dataset size necessitates critically examining the quality and robustness of models trained on such limited data. Therefore, it becomes paramount to consider the trade-offs between the advantages of ML applications and the constraints posed by data scarcity in the context of MMP prediction.
As summarized in Table 1, the most dominant parameters affecting pure CO2 MMP are reservoir temperature, the molecular weight of C5+ or C7+, the mole fraction of volatile oil elements, and the mole fraction of intermediate oil elements. Meanwhile, for impure CO2 MMP, additional parameters such as the mole fraction of gas, including C1 to C4, CO2, N2, and H2S are also considered. Some studies included volatile oil components (C1 and N2) as well.
A more rigorous way to investigate the impact of each input variable involves conducting sensitivity analysis, a widely employed way to analyze the effect of each input parameter on model predictions. It plays a crucial role in model interpretation, validation, and feature selection, ultimately improving the trustworthiness and transparency of machine learning models. Methods like SHAP (Shapley Additive exPlanations) and relevancy factors are commonly used for sensitivity analysis. Nevertheless, few existing studies [27,28] have performed a sensitivity analysis, while the majority of research only compares their models with experimental and/or empirical results. Future research endeavors should allocate attention toward sensitivity analysis, thereby enhancing the completeness and credibility of machine learning studies.
Table 1. Summary of ML application on CO2-EOR MMP.
Table 1. Summary of ML application on CO2-EOR MMP.
AuthorsMethodsDatasetSplittingInputsResultsEvaluationLimitationsRating *
Huang et al. [25]ANNN/AN/APure CO2 (TR, xvol, MWC5+, xint), impure CO2 (yH2S, yN2, yCH4, ySO2, Fimp)ANN can predict MMP.First applied ANN. ANN is better than other statistical models.Need to separate pure CO2 and impure CO2. 7
Emera and Sarma [26]GAN/AN/ATR, MWC5+, xvol/(yC1 + yH2S + yCO2 + yN2 + yC2-C4).GA is best for predicting MMP and impurity factors.First used GA. Limited input parameters (only 3 variables).Pure CO2. MWC7+ only up to 268.7
Dehghani et al. [29]GA5580% train + 20% testTR, TC, MWC5+, xvol/xint.GA is better than conventional methods.Can predict pure and impure CO2. But limited input parameters and data points. Limited input parameters and data points.6
Shokir [22]ACE4550% train + 50% testTR, MWC5+, yCO2, yH2S, yN2, yC1, yC2-C4, xC1+N2, xintCan predict relatively accurate MMP for pure and impure CO2. Can predict pure and impure CO2. But very limited data points. It may have overfitting.valid only for C1, N2, H2S, and C2–C4 contents in the injected CO2 stream.6
Dehghani et al. [30]ANN-GA46N/ATR, MWC5+, yCO2, yH2S, yN2, yC1, yC2-C4, xC1+N2, xintGA-ANN is better than Shokir [22], Emera and Sarma [26].It can be applied to both CO2 and natural gas streams.Limited data points and only ANN architecture is tested.6
Nezhad et al. [31]ANN179N/ATR, xvol, MWC5+, yCO2, yvolatile, yintermediateANN is acceptable.Acceptable data points but not detailed explanations.Local minima or overfitting8
Shokrollahi et al. [32]LSSVM14780% train + 10% test + 10% validateTR, xvol, MWC5+, yCO2, yC1, yH2S, yN2, yC2-C5First applied LSSVM.It can be used for both pure and impure CO2. Also applied outlier analysis.Valid only for the impurity contents of C1, N2, H2S, and C2–C5.8
Tatar et al. [33]RBFN14780% train + 20% testTR, MWC5+, yCO2, yH2S, yN2, yC1, yC2-C5, (xC1 + xN2)/(xC2-C4+ xH2S + xCO2)Better than Emera and Sarma’s model.Compared with almost all available empirical correlations.Limited data points8
Zendehboudi et al. [34]ANN-PSO35071% train + 29% testTR, xvol, MWC5+, yCO2, yC1, yH2S, yN2, yC2-C4ANN-PSO is best.Though it has large datasets, but only suitable for fixed input parameters.Only valid for specific conditions8
Chen et al. [35]ANN8370% train + 30% testTR, MWC5+, xvol, xint, yCO2, yH2S, yC1, and yN2ANN provides the least errors.May have overfitting.Small datasets7
Asoodeh et al. [36]CM (NN-SVR)55N/ATR, MWC5+, xvol/xint, yC2-C4, yCO2, yH2S, yC1, and yN2CM is better than NN and SVR.Limited data points and may have overfitting.Small datasets6
Rezaei et al. [37]GP43N/ATR, MWC5+, xvol/xint GP provides the best estimation.Limited data points and may have overfitting.Small datasets and only consider pure CO2.6
Chen at al. [38]GA-BPNN8575% train + 25% testTR, MWC7+, xvol, xC5-C6, yCO2, yH2S, yN2, yC1, yC2-C4, xintBoth pure and impure CO2, better than other correlations.It can be applied to both pure and impure CO2 but may have overfitting.Limited data points.
GA is time-consuming.
7
Ahmadi and Ebadi [39]FL5993% train + 7% testTR, MWC5+, xvol/xint, TCThe curve shape membership function has the lowest error.Limited data points and a high possibility of overfitting.Only four experimental results for testing.6
Sayyad et al. [40]ANN-PSO38N/ATR, xvol, MWC5+, yCO2, yH2S, yC1, yN2, yC2-C5Better than Emera and Sarma, Shokir.Only valid for fixed inputs.Limited data points6
Zargar et al. [41]GRNNN/AN/ATR, MWC5+, xvol/xint, yC2-C4, yCO2, yH2S, yC1, and yN2.GRNN is an efficient computational structure. GA reduces the runs of GRNNs.Though compared with most known correlations, but unknown about the data source.Need more information about the treatment of data.6
Bian et al. [42]SVR-GA15067% train + 23% test and 83% train + 17% testTR, MWC5+, xvol, yCO2, yH2S, yC1, yN2.Better than other empirical correlations.Can be used for pure and impure CO2 and low AARD.Separate pure and impure CO2.9
Hemmati-Sarapardeh et al. [43]MLP14770% train + 15% test + 15% validateTR, TC, MWC5+, xvol/xint Can predict both pure and impure CO2.Simple and reliable.Treatment of inputs may be too simple.8
Zhong and Carr [44]MKF-SVM14790% train + 10% testTR, TC, MWC5+, xvol/xint The mixed kernel provides better performance.Treatment of inputs may be too simple. Did not consider the effect of N2, H2S.8
Fathinasab and Ayatollahi [45]GP27080% train + 20% testTR, Tcm, MWC5+, xvol/xintGP provides the best prediction.Relatively large datasets but may simplify the inputs.AARE is a little high (11.76%).7
Alomair and Garrouch [46]GRNN11380% train + 20% testTR, MWC5+, MWC7+, xC1, xC2, xC3, xC4, xC5, xC6, xC7+, xCO2, xH2S, xN2.GRNN is better than five empirical correlations.Too many inputs and no further comparison between GRNN and other ML methods.Does not consider the purity of CO2.7
Karkevandi-Talkhooncheh et al. [47]ANFIS27080% train + 20% testTR, TC, MWC5+, xvol, xint ANFIS-PSO is the best among the five optimization methods.Very comprehensive comparison with available models and different optimizations.Further applicability may be needed.9
Ahamdi et al. [48]GEPN/AN/ATR, Tcm, MWC5+, xvol/xintGEP is better than traditional correlations.Unknown about datasets. Further validation may be needed.6
Karkevandi-Talkhooncheh et al. [49]RBF-GA/PSO/ICA/ACO/DE270 80% train + 20% testTR, MWC5+, xvol, xC2-C4, yCO2, yH2S, yC1, yN2.ICA-RBF is best.Comparable large datasets. Five algorithms were applied.Further applicability may be needed.9
Tarybakhsh et al. [50]SVR-GA, MLP, RBF, GRNN13592.5% train + 7.5% testTR, MWC2-C6 (OIL), MWC7+, SGC7+, MWC2-C6 (GAS), yCO2, yH2S, yC1, yN2.SVT-GA is best.Too many input parameters may cause a high possibility of overfitting.The R2 is as high as 0.999. Too perfect to be reliable.6
Dong et al. [51]ANN12282% train + 18% testH2S, CO2, N2, C1, C2… C36+ANN can be used to predict MMP.Too many inputs. No dominant input selection.Input variables were assumed based on the
availability of data.
7
Hamdi and Chenxi [52]ANFIS4873% train + 27% testTR, MWC5+, xvol, xint Gaussian MF is the best among the five MFs. ANFIS is better than ANN.Though applied five MF but limited data points.Limited data points and does not consider the existence of CO2.6
Khan et al. [53]ANN, FN, SVM5170% train + 30% testTR, MWC7+, xC1, xC2-C6, MWC2+, xC2ANN is best.Compared three methods but input parameters are overlapping.Limited data points and does not consider the existence of CO2.6
Choubineh et al. [54]ANN25175% train + 10% test + 15% validateTR, MWC5+, xvol/xint, SGANN is best compared with empirical correlations.Relatively large dataset. Use gas SG instead.Further applicability may be needed.8
Li et al. [55]NNA, GFA, MLR, PLS136N/ATR, TC, MWC5+, xvol/xint, yC2-C5, yCO2, yH2S, yC1, yN2.ANN is best among both empirical and other algorithms.Unclear about how to split the data. Further applicability may be needed.8
Hassan et al. [56]ANN, RBF, GRNN, FL10070% train + 30% testTR, MWC7+, xC2-C6RBF provides the highest accuracy.Only three input parameters may simplify the model.Does not consider the purity of CO2 and the limited dataset.7
Sinha et al. [57]Linear SVM/KNN/RF/ANNN/A67% train + 33% testTR, MWC7+, MWOil, xC1, xC2, xC3, xC4, xC5, xC6, xC7+, xCO2, xH2S, and xN2.Modified correlation with linear SVR and hybrid method with RF is best.Only need oil composition and TR. Does not consider the purity of CO2.MMP range 1000–4900 psi.7
Nait Amar and Zerabi [9]SVR-ABC20187% train + 13% testTR, TC, MWC5+, xvol/xint, xC2-C4SVR-ABC is better SVR-TE.The choice of inputs is limitedLimited comparison.8
Dargahi-Zarandi et al. [58]AdaBoost SVR, GDMH, MLP27067% train + 33% testTR, TC, MWC5+, xvol, xC2-C4, yCO2, yH2S, yC1, yN2.AdaBoost SVR is best.Create a 3-D plot for better visualization.Further applicability was limited9
Tian et al. [59]BP-NN (GA, MEA, PSO, ABC, DA)15280% train + 20% testTR, MWC5+, xC1, xC2, xC3, xC4, xC5, xC6, xC7+, yCO2, yH2S, yN2.DA-BP has the highest accuracy.Compared with empirical correlations and GA-SVR. Too many input parameters may have overfitting.8
Ekechukwu et al. [60]GPR13790% train + 10% testTR, TC, MWC5+, xvol/xint GPR has higher accuracy than other models.Very comprehensive comparison. A larger dataset may be better.Further validation with experiments may be needed.8
Saeedi Dehaghani and Soleimani [61]SGB, ANN, ANN-PSO, ANN-TLBO14475% train + 25% testTR, MWC5+, xvol, xint, yCO2, yC1, yint, yN2.PSO and TLBO can help improve the accuracy of the ANN model. SGB is better than ANN.First applied SGB. Maybe compared with other optimization methods will be better.Further validation with experiments may be needed.8
Dong et al. [62]FCNN12282% train + 18% testxCO2, xH2S, xN2, xC1, xC2, xC3, xC4, xC5, xC6, …, xC36+.L2 regularization and Dropout can help reduce overfitting.Alleviate overfitting but small datasets.Small datasets.7
Chen et al. [63]SVM14780% train + 20% testTR, MWC7+, xvol, xC2-C4, xC5-C6, yCO2, yHC, yC1, and yN2.POLY kernel is more accurate. MWC7+ and xC5-C6 should not be considered. Very complete and comprehensive. Includes optimization and evaluation.More persuasive with a large dataset.9
Ghiasi et al. [64]ANFIS, AdaBoost-CARTN/A90% train + 10% testTR, TC, MWC5+, xvol/xint, yCO2, yH2S, yC1-C5, and yN2The novel AdaBoost-
The CART model is the most reliable.
The size of the dataset is unknown. First one to use AdaBoost. May have overfitting and validation is not strong.7
Chemmakh et al. [65]ANN, SVR-GA147 (pure CO2), 200 (impure CO2)NATR, TC, MWC5+, xvol/xint ANN and SVR-GA are reliable to use. The novelty of work is not clear.Only compared with empirical correlations.7
Pham et al. [66]FCNN25080% train + 20% testTR, xvol/xint, MW, yC1, yC2+, yCO2, yH2S, yN2Multiple FCN together with Early Stopping and K-fold cross validation has high prediction of MMP.Applied deep learning—multiple FCN to predict MMP. Limited comparisons and validations.Only compared with decision tree and random forest.7
Haider et al. [67]ANN20170% train + 30% testTR, MWC7+, xCO2, xC1, xC2, xC3, xC4, xC5, xC6, xC7, yCO2, yH2S, yC1, yN2.An empirical correlation is developed based on ANN.Too many inputs and a high possibility of overfitting.Need further validation with other reservoir fluid and injected gas.7
Huang et al. [68]CGAN-BOA18060% train + 20% test + 20% validateTR, MWC7+, xCO2, xC1, xC2, xC3, xC4, xC5, xC6, xC7+, xN2, yCO2, yH2S, yN2, yC1, yC2, yC3, yC4, yC5, yC6, yC7+.CGAN-BOA and ANN are better than SVR-RBF and SVR-POLY.Proved deep learning has the potential for predicting MMP.May have overfitting problems given 21 input parameters.8
He et al. [69]GBDT-PSO19585% train + 15% testTR, xCO2, xC1, xC2, xC3, xC4, xC5, xC6, xC7+, xN2,GBDT is better than LR, RR, RF, MLP.Improved GBDT by using PSO. But not a comprehensive comparison.Only GBDT was optimized. Other algorithms could also be tuned and compared.7
Hou et al. [70]GPR-PSO36580% train + 20% testTR, TC, MWC5+, xvol/xint, yCO2, yH2S, yC1, yC2-C5, yN2.GPR-PSO provides the highest accuracy.Comprehensive comparison and large datasets. The model was only validated with literature data.9
Rayhani et al. [71]SFS, SBS, SFFS, SBFS, LR, RFFI81280% train + 20% testTR, TC, MWC7+, MWgas, xC5, xC6, xC2-C6SBFS provides the highest accuracy.Large datasets. Comprehensive data selection and model comparison.Further applicability with field data or commercial simulation was limited. 9
Shakeel et al. [72]ANN, ANFIS10570% train + 30% testTR, MWC7+, xvol, xC2-C4, xC5-C6, yCO2, yH2S, yC1, yHC, yN2.ANN is better than ANFIS; the trainlm performs best.Demonstrated good accuracy but lack of uncertainty analysis.Limited dataset and only two ML algorithms were tested.7
Shen et al. [73]XGBoost, TabNet, KXGB, KTabNet42180% train + 20% testTR, MWC5+, xvol/xint, yCO2, yH2S, yC1, yC2-C5, yHC, and yN2KXGB is best. KTabNet can be used as an alternative. Large datasets. Comprehensive model comparison. New insights into deep learning.Need improvement of feature comprehensiveness.9
Lv et al. [24]XGBoost, CatBoost, LGBM, RF, deep MLN, DBN, CNN31080% train + 20% testTR, TC, MWC5+, xvol/xint CatBoost outperforms than other AI techniques.Comprehensive model comparison and evaluation. New insights into deep learning.The accuracy depends on the databank. A larger dataset will be more robust.9
Hamadi et al. [74]MLP-Adam, SVR-RBF, XGBoost19384% train + 16% testTR, TC, MWC5+, xvol/xint XGBoost provides the best prediction for both pure and impure CO2.Not comprehensive comparison and a limited dataset.Limited dataset and only two ML algorithms were tested7
Huang et al. [27]1D-CNN, SHAP193NATR, MWC7+, xCO2, xC1, xC2, xC3, xC4, xC5, xC6, xC7+, xN2, yCO2, yH2S, yN2, yC1, yC2, yC3, yC4, yC5, yC6, yC7+.MMPs from the slim tube and rising bubble are different. 1D-CNN performs best.It is novel in the SHAP application, but the comparison with other ML models is limited.Further applicability with field data or commercial simulation was limited. 8
Al-Khafaji et al. [28]MLR, SVR, DT, RF, KNN147 (type 1), 197 (type 2), 28 (type 3)80% train + 20% testType 1: TR, MWC5+, xvol/xint; Type 2: MWC7+, xvol, xint, xC5-C6, xC7+, yCO2, yH2S, yN2, yC1, yC2-C6, yC7+.; Type 3: TR, MWC6+, xvol, xint, xC6+, API, sp.gr, Pb.KNN has the highest efficient accuracy and lowest complexity. Have a broad range of data including both experimental and field data. Performed thorough comparisons.Only pure CO2.9
Sinha et al. [75]Light GBM20580% train + 20% testTR, MWC7+, MWOil, xC1, xC2, xC3, xC4, xC5, xC6, xC7+, xCO2, xN2, xH2SAn expanded range is developed with Light GBM.Compared with empirical and EOS correlations. First used Light GBM in MMP prediction.Further applicability with field data or commercial simulation was limited. 8
*: On a scale of 1 to 10, a higher score indicates higher quality of the article.

4.2. Water-Alternating-Gas (WAG)

WAG injection, a widely adopted method in EOR techniques, cyclically injects water and gas, typically CO2 or CO2-hydrocarbon blends, to increase sweep efficiency and maximize oil recovery. Optimizing parameters such as the WAG ratio, duration of each cycle, and reservoir properties is pivotal for achieving favorable economic outcomes. The application of ML methods on WAG has been developed more recently. The earliest application of ML in WAG started in 2016; Hosseinzadeh Helaleh and Alizadeh [76] employed SVM together with three optimization methods, ACO, PSO, and GA, to predict fractional oil recovery. In 2018, Nait Amar et al. [77] used time-dependent multi-ANN to predict the total field oil production. Later on, Nait Amar and Zeraibi [78] successfully applied SVR to construct a dynamic proxy of a field in Algeria, complemented by genetic algorithms (GAs) for optimizing water-alternating CO2 gas parameters. A more detailed summary is listed in Table 2. Figure 5 provides statistical analysis based on 26 papers. Similar to MMP, the most popular ML algorithm is ANN, and the most preferred optimization is GA.

4.3. Well Placement Optimization (WPO)

WPO plays an essential role in reservoir management and development for many reasons. It can help maximize oil recovery and economic considerations (because drilling and maintaining wells is expensive). However, it has been considered one of the most challenging tasks due to the necessity of evaluating numerous computation scenarios to identify the optimal location for wells and achieve maximum production. The complexity of geological heterogeneities, such as variations in permeability and porosity, the existence of multiple facies, and stratigraphic and structural boundary conditions, requires extensive computational efforts. Furthermore, small changes in well locations can lead to significant changes in oil recovery prediction, making the optimization more challenging. Numerous simulations for hundreds or thousands of scenarios need to be run to make the best decision.
In recent years, studies suggesting the integration of ML approaches have been proposed in the literature as a potential solution. They hold the potential to accelerate computation processes, enabling the quicker attainment of accurate scenarios within numerical simulations. Despite the recognized importance of optimizing well placement, the investigations of CO2 injector locations for optimal oil recovery and storage are relatively infrequent (Table 3). Most research is focused on waterflood injector selection [102].

4.4. Oil Production/Recovery Factor

The recovery factor, defined as the ratio of produced oil to OOIP, is one of the most crucial success metrics for evaluating all EOR projects, as it determines how much incremental oil or ultimate oil is produced. Accurately predicting the recovery factor is challenging because it depends on diverse factors, including reservoir characteristics and heterogeneity, fluid properties, well design, injection condition, and the composition of the injected fluid. Reservoir simulations, together with laboratory experiments at reservoir conditions, can help predict the recovery factor. After that, a small-scale pilot test is conducted before undertaking larger-scale operations [105]. Although this approach may provide solutions to numerous problems, it is costly and time consuming. Therefore, ML methods emerge as more practical, affordable, rapid, and accurate alternatives.
Alternatively, ML methods have obtained popularity in predicting oil recovery. For example, Ahmadi et al. [106] applied LSSVM to predict the ultimate oil recovery factor of the miscible CO2-EOR injection operations at different rock, fluid, and process conditions. Karacan [107] employed fuzzy logic to predict the recovery factors of the major past and existing U.S. field applications of miscible CO2-EOR. Table 4 provides further information on ML applications on the CO2-EOR recovery factor.

4.5. Multi-Objective Optimization

As the name indicates, multi-objective optimization optimizes multiple objections simultaneously, such as the oil recovery factor or cumulative oil production, CO2 storage, and net present value (NPV). For each objective, running high-fidelity numerical models provides possible solutions to figure out the optimum. However, finding optimal solutions to all the objectives simultaneously is not always guaranteed since objectives can compete with each other. For example, to maximize oil recovery, more CO2 may be needed, leading to higher oil production. However, this might also mean that more CO2 is used, potentially increasing the project’s cost, which will also adversely affect the project NPV [110]. This requires sophisticated optimization techniques to identify solutions that balance these objectives, considering all the constraints involved in the problem. Therefore, ML techniques outperform other methods as an effective, reliable, and stable workflow to co-optimize crude oil recovery, CO2 sequestration, NPV, and related factors.
Given the complexity of multi-objective optimization, the application of ML on CO2-EOR is very limited (Table 5) and is strongly restricted by the geological model. Once the reservoir characteristics have changed, the model must be rebuilt and retrained. The development of the ML and optimization workflow is challenging and requires more effort in different oil and gas fields.

4.6. PVT Properties

For any CO2-flooding project, it is imperative to comprehend the intricate physical and chemical interactions between CO2 and the reservoir oil, even when primarily exploring recovery potential. Laboratory investigations and the utilization of available modeling or correlation packages serve as viable methods for analyzing the influence of CO2 on the physical properties of oil. Nonetheless, conducting a comprehensive laboratory study to obtain an extensive dataset is costly and time consuming. Furthermore, the available correlation packages are limited in their applicability, rendering them unsuitable for many scenarios.
ML is being increasingly harnessed for tasks such as predicting CO2 solubility and interfacial tension (IFT), as briefly presented in Table 6. Intriguingly, a majority of the studies incorporated the same dataset sourced from Emera and Sarma [115]. Given the relatively small dataset size comprising only 106 data points, the risk of overfitting looms large, casting doubt on the accuracy and generalizability of their ML models. It is evident that a larger and more diverse dataset is required to facilitate a deeper comprehension of the performance of ML techniques in this context.

4.7. CO2-Foam Flooding

The implementation of CO2 injection in Enhanced Oil Recovery (EOR) demonstrates significant potential, but it is accompanied by inherent limitations, including suboptimal sweep efficiency, asphaltene precipitation, and the corrosion of well infrastructure. In response to these challenges, the utilization of CO2 foam has emerged as a promising strategy to enhance the effectiveness of CO2-EOR flooding. Foams offer distinct advantages, primarily due to their elevated viscosities compared to pure gases, a property that equips foams with the capability to displace oil from reservoir formations more efficiently [119]. Furthermore, by obstructing highly permeable pore pathways, foams redirect displaced fluids toward unswept reservoir regions, thereby improving both the sweep efficiency and the storage capacity of CO2 within the reservoir matrix. While ML models have found extensive applications in EOR research, their application in the context of CO2 foam is still in its nascent stages, and the existing body of literature on this subject remains limited, as evidenced in Table 7.

5. Benefits and Limitations of ML

ML exhibits high efficiency when compared with conventional reservoir simulators. Typically, these simulators are performed on 3D grids comprising one million to several billion cells. Computations tend to be time-consuming, imposing constraints on the feasibility of conducting multiple iterations. Consequently, this limitation reduces the optimization potential for meticulous field development planning. A pivotal role of ML techniques is their capacity to speed up reservoir modeling computations. These models can predict time-dependent variables at 100 to 1000 times faster speeds than traditional simulators. This acceleration in computation velocity via ML methods maintains an equivalent level of functionality [11].
Furthermore, extensive research findings have proved the impressive performance of ML methods, consistently yielding accuracy levels exceeding 90% based on statistical quality assessments. This high degree of accuracy demonstrates the confidence in ML’s reliability and portends a promising future within the oil and gas industry.
While the advantages of employing ML are widely acknowledged, it is imperative to recognize the associated limitations inherent in ML-based methodologies. A central challenge confronting researchers is obtaining authentic data from experimental and/or field sources. The limited availability of large datasets is also a concern, impacting both the training accuracy and the overall efficacy of the ML models. When faced with restricted data, researchers often use single-shot learning strategies, wherein models are pre-trained on similar datasets and subsequently refined through experience.
Overfitting is a prevalent issue in ML applications, primarily driven by insufficient training data and the absence of well-defined stopping criteria during training. In total, 12% of the reviewed research papers contain datasets with fewer than 100 data points, heightening the risk of overfitting. Addressing this problem may involve adjusting the model’s structure, including weight modifications. However, it is important to recognize that such alterations can increase model complexity, potentially limiting its generalization beyond the specific dataset.
More efforts are needed to advance ML applications within the oil and gas industry. For instance, integrating knowledge from multiple disciplines, such as geology, reservoir engineering, and petrophysics, into ML models could enhance model accuracy and interpretability. Future endeavors may involve the development of hybrid models implementing ML techniques with physics-based methodologies. Another improvement is reducing data scarcity and heterogeneity, which requires concerted efforts to address bias and model generalization. Researchers could focus on deploying data augmentation techniques, employing transfer learning methodologies, and refining ML algorithms to handle sparse and noisy data effectively.

6. Conclusions

In this work, we have investigated and summarized the employment of ML methods in the application of CO2-EOR from several areas: MMP, WAG, well location placement, oil production/recovery factor, multi-objective optimization, PVT properties, and CO2 foam. We have listed the input parameters, objectives, data sources, results, evaluation, and rating for each area based on the data quality, ML process, and results analysis. The important highlights of this work are summarized by seven key points as follows:
  • Most reports on model performance indicators are limited to the size of the data bank, with 12% of the investigated papers having a database of less than 100 data points, making it difficult to accurately assess the quality of the model over time or track its drift with new data;
  • Regarding validation and verification, the CO2-EOR has many reliable, dependable, and well-established techniques for verification and validation procedures for ML models; the research highlights several issues with current ML models, including scalability, validation and verification deficiencies, and an absence of published data regarding the establishment costs of ML models;
  • Most CO2-EOR research focused on MMP predictions and WAG design, with 56 out of 101 papers devoted to MMP prediction and 26 of 101 papers to WAG design; the applications in the recovery factor, well placement optimization, and PVT properties are limited;
  • ANN is the most employed ML algorithm, and GA is the most popular optimization algorithm based on 101 reviewed papers. ANN has proven to be flexible enough to be implemented to build intelligent proxies; while oil and gas data are frequently characterized by noise, incompleteness, heterogeneity, and nonlinearity, ANNs exhibit superior capability in handling such diverse data types and can adeptly adapt to varying data distributions;
  • ML algorithms have the potential to greatly reduce the computational cost and time to perform compositional simulation runs; however, ML applications for well placement and multi-objective optimizations in CO2-EOR are very limited given the complexity of the problem. Furthermore, the reliability of coupled ML-metaheuristic paradigms based on reservoir simulation results needs further investigation;
  • The application of ML in the oil and gas industry still requires further exploration and development. Future work can focus on integrating knowledge from multiple disciplines, such as geology, reservoir engineering, and petrophysics with ML models to enhance accuracy and interpretability; another focus area could be the development of hybrid models that implement ML techniques alongside physics-based methodologies, providing robust and reliable support;
  • In summary, this study provides a comprehensive overview of the application of ML and optimization techniques in CO2-EOR projects; our work significantly contributes to the advancement of knowledge in the field by providing a synthesis of the latest research; these methods have demonstrated their ability to improve the efficiency, production forecast, and economic viability of CO2-EOR operations; the insights gained from this study provide valuable guidance for the future direction of ML applications in CO2-EOR R&D (research and development) and deployment.

Author Contributions

Conceptualization, G.T. and X.D.; methodology, X.D.; validation, X.D. and G.T.; investigation, S.S.; resources, X.D. and S.S.; data curation, X.D.; writing—original draft preparation, X.D.; writing—review and editing, X.D. and G.T.; visualization, X.D.; supervision, G.T.; All authors have read and agreed to the published version of the manuscript.

Funding

This research received no external funding.

Data Availability Statement

Not applicable.

Conflicts of Interest

The authors declare no conflicts of interest.

Nomenclature

AARDAverage absolute relative deviation
AAREAverage absolute relative error
ABCArtificial bee colony
ACOAnt colony optimization
ACEAlternating conditional expectation
ARAuto-regressive
ANNArtificial Neural Network
ANFISAdaptive neuro-fuzzy inference system
BABee algorithm
BOABayesian optimization algorithm
BPNNBackpropagation algorithm neural network
BRBayesian regularization
CatBoostCategorical boosting
CCDCentral composite design
CFNNCascade forward neural network
CGANConditional generative adversarial network
CMCommittee machine
CNNConvolutional neural network
COACuckoo optimization algorithm
CSOCuckoo search optimization
DADragonfly algorithm
DBNDeep belief network
DEDifferential evolution
DNNDense neural network
ERTExtremely randomized trees
FCNNFully connected neural network
FGIRField gas injection rate
FLFuzzy logic
FNFunctional network
GAGenetic algorithm
GBGradient boosting
GBDTGradient boosting decision tree
GBMGradient boost method
GEPGene expression programming
GFAGenetic function approximation
GIRGas injection rate
GMDHGroup method of data handling
GPGenetic programming
GPRGaussian process regression
GRNNGeneralized regression neural network
GSAGravitational search algorithm
GWOGrey wolf optimization
HeHurst exponent
HPSOHybrid particle swarm optimization
ICAImperialist competitive algorithm
KXGBKnowledge-based XGB
LGBMLight gradient boosting machine
LMLevenberg—Marquardt
LRLasso regression
LSSVMLeast-squares support vector machine
LSTMLong short-term memory
MADSMesh adaptive direct search
MARSMultivariate Adaptive Regression Splines
MASRDMean absolute symmetric relative deviation
MEAMind evolutionary algorithm
MFMembership function
MKFMixed kernels function
MLPMulti-layer perceptron
MLRMultiple linear regression
MLNNMulti-layer neural networks
MOPSOMulti-objective particle swarm optimization
MSEMean squared error
NNANeural network analysis
NPVNet present value
NSGA-IINon-dominated sorting genetic algorithm version II
PLSPartial least squares
POLYPolynomial function
PSOParticle swarm optimization
RBFNRadial-based function networks
RFFIRandom forest feature importance
RRRidge regression
RSMResponse surface models
SBFSSequential backward floating selection
SBSSequential backward selection
SCGScaled conjugate gradient
SFSSequential forward selection
SFFSSequential forward floating selection
SGBStochastic gradient boosting
SGRSolution gas ratio
SHAPShapley Additive explanations
SVRSupport vector regression
SVMSupport vector machine
TLBOTeaching learning-based optimization
TPVTTotal pore volume tested
WIRWater injection rate
WHFPWell head flow pressure
XGBoostExtreme gradient boosting
λ*DxEffective correlation length

References

  1. Green, D.W.; Willhite, P.G. Enhanced Oil Recovery; Henry, L., Ed.; Doherty Memorial Fund of AIME, Society of Petroleum Engineers: Richardson, TX, USA, 1998; Volume 6. [Google Scholar]
  2. Yang, G.; Jiang, R.; Li, X.; Jiang, Y. Evaluation of Polymer Flooding Performance Using Water-Polymer Interference Factor for an Offshore Oil Field in Bohai Gulf: A Case Study. In Proceedings of the SPE Improved Oil Recovery Conference, Tulsa, OK, USA, 14–18 April 2018; SPE: Tulsa, OK, USA, 2018. [Google Scholar]
  3. Yongmao, H.; Zenggui, W.; Binshan, J.; Yueming, C.; Xiangjie, L.; Petro, X. Laboratory Investigation of CO2 Flooding. In Proceedings of the Nigeria Annual International Conference and Exhibition, Abuja, Nigeria, 2 August 2004; SPE: Abuja, Nigeria, 2004. [Google Scholar]
  4. Cheraghi, Y.; Kord, S.; Mashayekhizadeh, V. Application of Machine Learning Techniques for Selecting the Most Suitable Enhanced Oil Recovery Method; Challenges and Opportunities. J. Pet. Sci. Eng. 2021, 205, 108761. [Google Scholar] [CrossRef]
  5. Gozalpour, F.; Ren, S.R.; Tohidi, B. CO2 EOR and Storage in Oil Reservoir. Oil Gas Sci. Technol. 2005, 60, 537–546. [Google Scholar] [CrossRef]
  6. Hasan, M.M.F.; First, E.L.; Boukouvala, F.; Floudas, C.A. A Multi-Scale Framework for CO2 Capture, Utilization, and Sequestration: CCUS and CCU. Comput. Chem. Eng. 2015, 81, 2–21. [Google Scholar] [CrossRef]
  7. Ghoraishy, S.M.; Liang, J.T.; Green, D.W.; Liang, H.C. Application of Bayesian Networks for Predicting the Performance of Gel-Treated Wells in the Arbuckle Formation, Kansas. In Proceedings of the SPE Symposium on Improved Oil Recovery, Tulsa, OK, USA, 19–23 April 2008; SPE: Tulsa, OK, USA, 2008. [Google Scholar]
  8. Liu, M.; Fu, X.; Meng, L.; Du, X.; Zhang, X.; Zhang, Y. Prediction of CO2 Storage Performance in Reservoirs Based on Optimized Neural Networks. Geoenergy Sci. Eng. 2023, 222, 211428. [Google Scholar] [CrossRef]
  9. Nait Amar, M.; Zeraibi, N. Application of Hybrid Support Vector Regression Artificial Bee Colony for Prediction of MMP in CO2-EOR Process. Petroleum 2020, 6, 415–422. [Google Scholar] [CrossRef]
  10. You, J.; Lee, K.J. Pore-Scale Numerical Investigations of the Impact of Mineral Dissolution and Transport on the Heterogeneity of Fracture Systems During CO2-Enriched Brine Injection. SPE J. 2022, 27, 1379–1395. [Google Scholar] [CrossRef]
  11. Ng, C.S.W.; Nait Amar, M.; Jahanbani Ghahfarokhi, A.; Imsland, L.S. A Survey on the Application of Machine Learning and Metaheuristic Algorithms for Intelligent Proxy Modeling in Reservoir Simulation. Comput. Chem. Eng. 2023, 170, 108107. [Google Scholar] [CrossRef]
  12. Kumar, N.; Augusto Sampaio, M.; Ojha, K.; Hoteit, H.; Mandal, A. Fundamental Aspects, Mechanisms and Emerging Possibilities of CO2 Miscible Flooding in Enhanced Oil Recovery: A Review. Fuel 2022, 330, 125633. [Google Scholar] [CrossRef]
  13. Satter, A.; Thakur, G.C. Integrated Petroleum Reservoir Management: A Team Approach; PennWell Books: Tulsa, OK, USA, 1994. [Google Scholar]
  14. Yang, G.; Li, X. Modified Peng-Robinson Equation of State for CO2/Hydrocarbon Systems within Nanopores. J. Nat. Gas Sci. Eng. 2020, 84, 103700. [Google Scholar] [CrossRef]
  15. Wang, L.; Yao, Y.; Luo, X.; Daniel Adenutsi, C.; Zhao, G.; Lai, F. A Critical Review on Intelligent Optimization Algorithms and Surrogate Models for Conventional and Unconventional Reservoir Production Optimization. Fuel 2023, 350, 128826. [Google Scholar] [CrossRef]
  16. Holm, L.W.; Josendal, V.A. Mechanisms of Oil Displacement By Carbon Dioxide. J. Pet. Technol. 1974, 26, 1427–1438. [Google Scholar] [CrossRef]
  17. Yellig, W.F.; Metcalfe, R.S. Determination and Prediction of CO2 Minimum Miscibility Pressures (Includes Associated Paper 8876). J. Pet. Technol. 1980, 32, 160–168. [Google Scholar] [CrossRef]
  18. Christiansen, R.L.; Haines, H.K. Rapid Measurement of Minimum Miscibility Pressure with the Rising-Bubble Apparatus. SPE Reserv. Eng. 1987, 2, 523–527. [Google Scholar] [CrossRef]
  19. Rao, D.N.; Lee, J.I. Application of the New Vanishing Interfacial Tension Technique to Evaluate Miscibility Conditions for the Terra Nova Offshore Project. J. Pet. Sci. Eng. 2002, 35, 247–262. [Google Scholar] [CrossRef]
  20. Alston, R.B.; Kokolis, G.P.; James, C.F. CO2 Minimum Miscibility Pressure: A Correlation for Impure CO2 Streams and Live Oil Systems. Soc. Pet. Eng. J. 1985, 25, 268–274. [Google Scholar] [CrossRef]
  21. Orr, F.M.; Jensen, C.M. Interpretation of Pressure-Composition Phase Diagrams for CO2/Crude-Oil Systems. Soc. Pet. Eng. J. 1984, 24, 485–497. [Google Scholar] [CrossRef]
  22. Shokir, E.M.E.-M. CO2–Oil Minimum Miscibility Pressure Model for Impure and Pure CO2 Streams. J. Pet. Sci. Eng. 2007, 58, 173–185. [Google Scholar] [CrossRef]
  23. Ahmadi, K.; Johns, R.T. Multiple-Mixing-Cell Method for MMP Calculations. SPE J. 2011, 16, 733–742. [Google Scholar] [CrossRef]
  24. Lv, Q.; Zheng, R.; Guo, X.; Larestani, A.; Hadavimoghaddam, F.; Riazi, M.; Hemmati-Sarapardeh, A.; Wang, K.; Li, J. Modelling Minimum Miscibility Pressure of CO2-Crude Oil Systems Using Deep Learning, Tree-Based, and Thermodynamic Models: Application to CO2 Sequestration and Enhanced Oil Recovery. Sep. Purif. Technol. 2023, 310, 123086. [Google Scholar] [CrossRef]
  25. Huang, Y.F.; Huang, G.H.; Dong, M.Z.; Feng, G.M. Development of an Artificial Neural Network Model for Predicting Minimum Miscibility Pressure in CO2 Flooding. J. Pet. Sci. Eng. 2003, 37, 83–95. [Google Scholar] [CrossRef]
  26. Emera, M.K.; Sarma, H.K. Use of Genetic Algorithm to Estimate CO2–Oil Minimum Miscibility Pressure—A Key Parameter in Design of CO2 Miscible Flood. J. Pet. Sci. Eng. 2005, 46, 37–52. [Google Scholar] [CrossRef]
  27. Huang, C.; Tian, L.; Wu, J.; Li, M.; Li, Z.; Li, J.; Wang, J.; Jiang, L.; Yang, D. Prediction of Minimum Miscibility Pressure (MMP) of the Crude Oil-CO2 Systems within a Unified and Consistent Machine Learning Framework. Fuel 2023, 337, 127194. [Google Scholar] [CrossRef]
  28. Al-Khafaji, H.F.; Meng, Q.; Hussain, W.; Khudhair Mohammed, R.; Harash, F.; Alshareef AlFakey, S. Predicting Minimum Miscible Pressure in Pure CO2 Flooding Using Machine Learning: Method Comparison and Sensitivity Analysis. Fuel 2023, 354, 129263. [Google Scholar] [CrossRef]
  29. Dehghani, S.A.M.; Vafaie Sefti, M.; Ameri, A.; Kaveh, N.S. A Hybrid Neural-Genetic Algorithm for Predicting Pure and Impure CO2 Minimum Miscibility Pressure. Iran. J. Chem. Eng. 2006, 3, 44–59. [Google Scholar]
  30. Dehghani, S.A.M.; Sefti, M.V.; Ameri, A.; Kaveh, N.S. Minimum Miscibility Pressure Prediction Based on a Hybrid Neural Genetic Algorithm. Chem. Eng. Res. Des. 2008, 86, 173–185. [Google Scholar] [CrossRef]
  31. Nezhad, A.B.; Mousavi, S.M.; Aghahoseini, S. Development of an Artificial Neural Network Model to Predict CO2 Minimum Miscibility Pressure. Nafta 2011, 62, 105–108. [Google Scholar]
  32. Shokrollahi, A.; Arabloo, M.; Gharagheizi, F.; Mohammadi, A.H. Intelligent Model for Prediction of CO2—Reservoir Oil Minimum Miscibility Pressure. Fuel 2013, 112, 375–384. [Google Scholar] [CrossRef]
  33. Tatar, A.; Shokrollahi, A.; Mesbah, M.; Rashid, S.; Arabloo, M.; Bahadori, A. Implementing Radial Basis Function Networks for Modeling CO2-Reservoir Oil Minimum Miscibility Pressure. J. Nat. Gas Sci. Eng. 2013, 15, 82–92. [Google Scholar] [CrossRef]
  34. Zendehboudi, S.; Ahmadi, M.A.; Bahadori, A.; Shafiei, A.; Babadagli, T. A Developed Smart Technique to Predict Minimum Miscible Pressure-Eor Implications. Can. J. Chem. Eng. 2013, 91, 1325–1337. [Google Scholar] [CrossRef]
  35. Chen, G.; Wang, X.; Liang, Z.; Gao, R.; Sema, T.; Luo, P.; Zeng, F.; Tontiwachwuthikul, P. Simulation of CO2-Oil Minimum Miscibility Pressure (MMP) for CO2 Enhanced Oil Recovery (EOR) Using Neural Networks. Energy Procedia 2013, 37, 6877–6884. [Google Scholar] [CrossRef]
  36. Asoodeh, M.; Gholami, A.; Bagheripour, P. Oil-CO2 MMP Determination in Competition of Neural Network, Support Vector Regression, and Committee Machine. J. Dispers. Sci. Technol. 2014, 35, 564–571. [Google Scholar] [CrossRef]
  37. Rezaei, M.; Eftekhari, M.; Schaffie, M.; Ranjbar, M. A CO2-Oil Minimum Miscibility Pressure Model Based on Multi-Gene Genetic Programming. Energy Explor. Exploit. 2013, 31, 607–622. [Google Scholar] [CrossRef]
  38. Chen, G.; Fu, K.; Liang, Z.; Sema, T.; Li, C.; Tontiwachwuthikul, P.; Idem, R. The Genetic Algorithm Based Back Propagation Neural Network for MMP Prediction in CO2-EOR Process. Fuel 2014, 126, 202–212. [Google Scholar] [CrossRef]
  39. Ahmadi, M.-A.; Ebadi, M. Fuzzy Modeling and Experimental Investigation of Minimum Miscible Pressure in Gas Injection Process. Fluid Phase Equilib. 2014, 378, 1–12. [Google Scholar] [CrossRef]
  40. Sayyad, H.; Manshad, A.K.; Rostami, H. Application of Hybrid Neural Particle Swarm Optimization Algorithm for Prediction of MMP. Fuel 2014, 116, 625–633. [Google Scholar] [CrossRef]
  41. Zargar, G.; Bagheripour, P.; Asoodeh, M.; Gholami, A. Oil-CO2 Minimum Miscible Pressure (MMP) Determination Using a Stimulated Smart Approach. Can. J. Chem. Eng. 2015, 93, 1730–1735. [Google Scholar] [CrossRef]
  42. Bian, X.-Q.; Han, B.; Du, Z.-M.; Jaubert, J.-N.; Li, M.-J. Integrating Support Vector Regression with Genetic Algorithm for CO2-Oil Minimum Miscibility Pressure (MMP) in Pure and Impure CO2 Streams. Fuel 2016, 182, 550–557. [Google Scholar] [CrossRef]
  43. Hemmati-Sarapardeh, A.; Ghazanfari, M.-H.; Ayatollahi, S.; Masihi, M. Accurate Determination of the CO2-Crude Oil Minimum Miscibility Pressure of Pure and Impure CO2 Streams: A Robust Modelling Approach. Can. J. Chem. Eng. 2016, 94, 253–261. [Google Scholar] [CrossRef]
  44. Zhong, Z.; Carr, T.R. Application of Mixed Kernels Function (MKF) Based Support Vector Regression Model (SVR) for CO2—Reservoir Oil Minimum Miscibility Pressure Prediction. Fuel 2016, 184, 590–603. [Google Scholar] [CrossRef]
  45. Fathinasab, M.; Ayatollahi, S. On the Determination of CO2–Crude Oil Minimum Miscibility Pressure Using Genetic Programming Combined with Constrained Multivariable Search Methods. Fuel 2016, 173, 180–188. [Google Scholar] [CrossRef]
  46. Alomair, O.A.; Garrouch, A.A. A General Regression Neural Network Model Offers Reliable Prediction of CO2 Minimum Miscibility Pressure. J. Pet. Explor. Prod. Technol. 2016, 6, 351–365. [Google Scholar] [CrossRef]
  47. Karkevandi-Talkhooncheh, A.; Hajirezaie, S.; Hemmati-Sarapardeh, A.; Husein, M.M.; Karan, K.; Sharifi, M. Application of Adaptive Neuro Fuzzy Interface System Optimized with Evolutionary Algorithms for Modeling CO2-Crude Oil Minimum Miscibility Pressure. Fuel 2017, 205, 34–45. [Google Scholar] [CrossRef]
  48. Ahmadi, M.A.; Zendehboudi, S.; James, L.A. A Reliable Strategy to Calculate Minimum Miscibility Pressure of CO2-Oil System in Miscible Gas Flooding Processes. Fuel 2017, 208, 117–126. [Google Scholar] [CrossRef]
  49. Karkevandi-Talkhooncheh, A.; Rostami, A.; Hemmati-Sarapardeh, A.; Ahmadi, M.; Husein, M.M.; Dabir, B. Modeling Minimum Miscibility Pressure during Pure and Impure CO2 Flooding Using Hybrid of Radial Basis Function Neural Network and Evolutionary Techniques. Fuel 2018, 220, 270–282. [Google Scholar] [CrossRef]
  50. Tarybakhsh, M.R.; Assareh, M.; Sadeghi, M.T.; Ahmadi, A. Improved Minimum Miscibility Pressure Prediction for Gas Injection Process in Petroleum Reservoir. Nat. Resour. Res. 2018, 27, 517–529. [Google Scholar] [CrossRef]
  51. Dong, P.; Liao, X.; Chen, Z.; Chu, H. An Improved Method for Predicting CO2 Minimum Miscibility Pressure Based on Artificial Neural Network. Adv. Geo-Energy Res. 2019, 3, 355–364. [Google Scholar] [CrossRef]
  52. Hamdi, Z.; Chenxi, D. Accurate Prediction of CO2 Minimum Miscibility Pressure Using Adaptive Neuro-Fuzzy Inference Systems. In Proceedings of the SPE Gas & Oil Technology Showcase and Conference, Dubai, United Arab Emirates, 21–23 October 2019. [Google Scholar]
  53. Khan, M.R.; Kalam, S.; Khan, R.A.; Tariq, Z.; Abdulraheem, A. Comparative Analysis of Intelligent Algorithms to Predict the Minimum Miscibility Pressure for Hydrocarbon Gas Flooding. In Proceedings of the Abu Dhabi International Petroleum Exhibition & Conference, Abu Dhabi, United Arab Emirates, 11 November 2019; SPE: Abu Dhabi, United Arab Emirates, 2019. [Google Scholar]
  54. Choubineh, A.; Helalizadeh, A.; Wood, D.A. 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. Adv. Geo-Energy Res. 2019, 3, 52–66. [Google Scholar] [CrossRef]
  55. Li, D.; Li, X.; Zhang, Y.; Sun, L.; Yuan, S. Four Methods to Estimate Minimum Miscibility Pressure of CO2-Oil Based on Machine Learning. Chin. J. Chem. 2019, 37, 1271–1278. [Google Scholar] [CrossRef]
  56. Hassan, A.; Elkatatny, S.; Abdulraheem, A. Intelligent Prediction of Minimum Miscibility Pressure (MMP) During CO2 Flooding Using Artificial Intelligence Techniques. Sustainability 2019, 11, 7020. [Google Scholar] [CrossRef]
  57. Sinha, U.; Dindoruk, B.; Soliman, M. Prediction of CO2 Minimum Miscibility Pressure MMP Using Machine Learning Techniques. In Proceedings of the SPE Improved Oil Recovery Conference, Tulsa, OK, USA, 31 August–4 September 2020; SPE: Tulsa, OK, USA, 2020. [Google Scholar]
  58. Dargahi-Zarandi, A.; Hemmati-Sarapardeh, A.; Shateri, M.; Menad, N.A.; Ahmadi, M. Modeling Minimum Miscibility Pressure of Pure/Impure CO2-Crude Oil Systems Using Adaptive Boosting Support Vector Regression: Application to Gas Injection Processes. J. Pet. Sci. Eng. 2020, 184, 106499. [Google Scholar] [CrossRef]
  59. Tian, Y.; Ju, B.; Yang, Y.; Wang, H.; Dong, Y.; Liu, N.; Ma, S.; Yu, J. Estimation of Minimum Miscibility Pressure during CO2 Flooding in Hydrocarbon Reservoirs Using an Optimized Neural Network. Energy Explor. Exploit. 2020, 38, 2485–2506. [Google Scholar] [CrossRef]
  60. Ekechukwu, G.K.; Falode, O.; Orodu, O.D. Improved Method for the Estimation of Minimum Miscibility Pressure for Pure and Impure CO2–Crude Oil Systems Using Gaussian Process Machine Learning Approach. J. Energy Resour. Technol. 2020, 142, 123003. [Google Scholar] [CrossRef]
  61. Saeedi Dehaghani, A.H.; Soleimani, R. Prediction of CO2-Oil Minimum Miscibility Pressure Using Soft Computing Methods. Chem. Eng. Technol. 2020, 43, 1361–1371. [Google Scholar] [CrossRef]
  62. Dong, P.; Liao, X.; Wu, J.; Zou, J.; Li, R.; Chu, H. A New Method for Predicting CO2 Minimum Miscibility Pressure MMP Based on Deep Learning. In Proceedings of the SPE/IATMI Asia Pacific Oil & Gas Conference and Exhibition, Bali, Indonesia, 25 October 2020; SPE: Bali, Indonesia, 2020. [Google Scholar]
  63. Chen, H.; Zhang, C.; Jia, N.; Duncan, I.; Yang, S.; Yang, Y. A Machine Learning Model for Predicting the Minimum Miscibility Pressure of CO2 and Crude Oil System Based on a Support Vector Machine Algorithm Approach. Fuel 2021, 290, 120048. [Google Scholar] [CrossRef]
  64. Ghiasi, M.M.; Mohammadi, A.H.; Zendehboudi, S. Use of Hybrid-ANFIS and Ensemble Methods to Calculate Minimum Miscibility Pressure of CO2—Reservoir Oil System in Miscible Flooding Process. J. Mol. Liq 2021, 331, 115369. [Google Scholar] [CrossRef]
  65. Chemmakh, A.; Merzoug, A.; Ouadi, H.; Ladmia, A.; Rasouli, V. Machine Learning Predictive Models to Estimate the Minimum Miscibility Pressure of CO2-Oil System. In Proceedings of the Abu Dhabi International Petroleum Exhibition & Conference, Abu Dhabi, United Arab Emirates, 15–18 December 2021; SPE: Abu Dhabi, United Arab Emirates, 2021. [Google Scholar]
  66. Pham, Q.C.; Trinh, T.Q.; James, L.A. Data Driven Prediction of the Minimum Miscibility Pressure (MMP) Between Mixtures of Oil and Gas Using Deep Learning. In Proceedings of the Volume 1: Offshore Technology; American Society of Mechanical Engineers: Cincinnati, OH, USA, 2021. [Google Scholar]
  67. Haider, G.; Khan, M.A.; Ali, F.; Nadeem, A.; Abbasi, F.A. An Intelligent Approach to Predict Minimum Miscibility Pressure of Injected CO2-Oil System in Miscible Gas Flooding. In Proceedings of the ADIPEC, Abu Dhabi, United Arab Emirates, 31 October–3 November 2022; SPE: Abu Dhabi, United Arab Emirates, 2022. [Google Scholar]
  68. Huang, C.; Tian, L.; Zhang, T.; Chen, J.; Wu, J.; Wang, H.; Wang, J.; Jiang, L.; Zhang, K. Globally Optimized Machine-Learning Framework for CO2-Hydrocarbon Minimum Miscibility Pressure Calculations. Fuel 2022, 329, 125312. [Google Scholar] [CrossRef]
  69. He, Y.; Li, W.; Qian, S. Minimum Miscibility Pressure Prediction Method Based On PSO-GBDT Model. Improv. Oil Gas Recovery 2023, 6. [Google Scholar] [CrossRef]
  70. Hou, Z.; Su, H.; Wang, G. Study on Minimum Miscibility Pressure of CO2–Oil System Based on Gaussian Process Regression and Particle Swarm Optimization Model. J. Energy Resour. Technol. 2022, 144, 103002. [Google Scholar] [CrossRef]
  71. Rayhani, M.; Tatar, A.; Shokrollahi, A.; Zeinijahromi, A. Exploring the Power of Machine Learning in Analyzing the Gas Minimum Miscibility Pressure in Hydrocarbons. Geoenergy Sci. Eng. 2023, 226, 211778. [Google Scholar] [CrossRef]
  72. Shakeel, M.; Khan, M.R.; Kalam, S.; Khan, R.A.; Patil, S.; Dar, U.A. Machine Learning for Prediction of CO2 Minimum Miscibility Pressure. In Proceedings of the SPE Middle East Oil and Gas Show and Conference, MEOS, Proceedings, Abu Dhabi, United Arab Emirates, 23–25 May 2023; Society of Petroleum Engineers (SPE): Abu Dhabi, United Arab Emirates, 2023. [Google Scholar]
  73. Shen, B.; Yang, S.; Gao, X.; Li, S.; Yang, K.; Hu, J.; Chen, H. Interpretable Knowledge-Guided Framework for Modeling Minimum Miscible Pressure of CO2-Oil System in CO2-EOR Projects. Eng. Appl. Artif. Intell. 2023, 118, 105687. [Google Scholar] [CrossRef]
  74. Hamadi, M.; El Mehadji, T.; Laalam, A.; Zeraibi, N.; Tomomewo, O.S.; Ouadi, H.; Dehdouh, A. Prediction of Key Parameters in the Design of CO2 Miscible Injection via the Application of Machine Learning Algorithms. Eng 2023, 4, 1905–1932. [Google Scholar] [CrossRef]
  75. Sinha, U.; Dindoruk, B.; Soliman, M. Physics Guided Data-Driven Model to Estimate Minimum Miscibility Pressure (MMP) for Hydrocarbon Gases. Geoenergy Sci. Eng. 2023, 224, 211389. [Google Scholar] [CrossRef]
  76. Hosseinzadeh Helaleh, A.; Alizadeh, M. Performance Prediction Model of Miscible Surfactant-CO2 Displacement in Porous Media Using Support Vector Machine Regression with Parameters Selected by Ant Colony Optimization. J. Nat. Gas Sci. Eng. 2016, 30, 388–404. [Google Scholar] [CrossRef]
  77. Nait Amar, M.; Zeraibi, N.; Redouane, K. Optimization of WAG Process Using Dynamic Proxy, Genetic Algorithm and Ant Colony Optimization. Arab. J. Sci. Eng. 2018, 43, 6399–6412. [Google Scholar] [CrossRef]
  78. Amar, M.N.; Zeraibi, N.; Jahanbani Ghahfarokhi, A. Applying Hybrid Support Vector Regression and Genetic Algorithm to Water Alternating CO2 Gas EOR. Greenh. Gases Sci. Technol. 2020, 10, 613–630. [Google Scholar] [CrossRef]
  79. Le Van, S.; Chon, B.H. Evaluating the Critical Performances of a CO2–Enhanced Oil Recovery Process Using Artificial Neural Network Models. J. Pet. Sci. Eng. 2017, 157, 207–222. [Google Scholar] [CrossRef]
  80. Van, S.L.; Chon, B.H. Effective Prediction and Management of a CO2 Flooding Process for Enhancing Oil Recovery Using Artificial Neural Networks. J. Energy Resour. Technol. 2018, 140, 032906. [Google Scholar] [CrossRef]
  81. Mohagheghian, E.; James, L.A.; Haynes, R.D. Optimization of Hydrocarbon Water Alternating Gas in the Norne Field: Application of Evolutionary Algorithms. Fuel 2018, 223, 86–98. [Google Scholar] [CrossRef]
  82. Nwachukwu, A.; Jeong, H.; Sun, A.; Pyrcz, M.; Lake, L.W. Machine Learning-Based Optimization of Well Locations and WAG Parameters under Geologic Uncertainty. In Proceedings of the SPE Improved Oil Recovery Conference, Tulsa, OK, USA, 14–18 April 2018; SPE: Tulsa, OK, USA, 2018. [Google Scholar]
  83. Belazreg, L.; Mahmood, S.M.; Aulia, A. Novel Approach for Predicting Water Alternating Gas Injection Recovery Factor. J. Pet. Explor. Prod. Technol. 2019, 9, 2893–2910. [Google Scholar] [CrossRef]
  84. Jaber, A.K.; Alhuraishawy, A.K.; AL-Bazzaz, W.H. A Data-Driven Model for Rapid Evaluation of Miscible CO2-WAG Flooding in Heterogeneous Clastic Reservoirs. In Proceedings of the SPE Kuwait Oil & Gas Show and Conference, Mishref, Kuwait, 13–16 October 2019; SPE: Mishref, Kuwait, 2019. [Google Scholar]
  85. Menad, N.A.; Noureddine, Z. An Efficient Methodology for Multi-Objective Optimization of Water Alternating CO2 EOR Process. J. Taiwan Inst. Chem. Eng. 2019, 99, 154–165. [Google Scholar] [CrossRef]
  86. Yousef, A.M.; Kavousi, G.P.; Alnuaimi, M.; Alatrach, Y. Predictive Data Analytics Application for Enhanced Oil Recovery in a Mature Field in the Middle East. Pet. Explor. Dev. 2020, 47, 393–399. [Google Scholar] [CrossRef]
  87. Belazreg, L.; Mahmood, S.M. Water Alternating Gas Incremental Recovery Factor Prediction and WAG Pilot Lessons Learned. J. Pet. Explor. Prod. Technol. 2020, 10, 249–269. [Google Scholar] [CrossRef]
  88. You, J.; Ampomah, W.; Sun, Q. Development and Application of a Machine Learning Based Multi-Objective Optimization Workflow for CO2-EOR Projects. Fuel 2020, 264, 116758. [Google Scholar] [CrossRef]
  89. You, J.; Ampomah, W.; Morgan, A.; Sun, Q.; Huang, X. A Comprehensive Techno-Eco-Assessment of CO2 Enhanced Oil Recovery Projects Using a Machine-Learning Assisted Workflow. Int. J. Greenh. Gas Control. 2021, 111, 103480. [Google Scholar] [CrossRef]
  90. Enab, K.; Ertekin, T. Screening and Optimization of CO2-WAG Injection and Fish-Bone Well Structures in Low Permeability Reservoirs Using Artificial Neural Network. J. Pet. Sci. Eng. 2021, 200, 108268. [Google Scholar] [CrossRef]
  91. Afzali, S.; Mohamadi-Baghmolaei, M.; Zendehboudi, S. Application of Gene Expression Programming (GEP) in Modeling Hydrocarbon Recovery in WAG Injection Process. Energies 2021, 14, 7131. [Google Scholar] [CrossRef]
  92. Lv, W.; Tian, W.; Yang, Y.; Yang, J.; Dong, Z.; Zhou, Y.; Li, W. Method for Potential Evaluation and Parameter Optimization for CO2-WAG in Low Permeability Reservoirs Based on Machine Learning. IOP Conf. Ser. Earth Environ. Sci. 2021, 651, 032038. [Google Scholar] [CrossRef]
  93. Nait Amar, M.; Jahanbani Ghahfarokhi, A.; Ng, C.S.W.; Zeraibi, N. Optimization of WAG in Real Geological Field Using Rigorous Soft Computing Techniques and Nature-Inspired Algorithms. J. Pet. Sci. Eng. 2021, 206, 109038. [Google Scholar] [CrossRef]
  94. Junyu, Y.; William, A.; Qian, S. Optimization of Water-Alternating-CO2 Injection Field Operations Using a Machine-Learning-Assisted Workflow. In Proceedings of the SPE Reservoir Simulation Conference, Online, 26 October–1 November 2021; SPE: Abu Dhabi, United Arab Emirates, 2021. [Google Scholar]
  95. Sun, Q.; Ampomah, W.; You, J.; Cather, M.; Balch, R. Practical CO2—WAG Field Operational Designs Using Hybrid Numerical-Machine-Learning Approaches. Energies 2021, 14, 1055. [Google Scholar] [CrossRef]
  96. Huang, R.; Wei, C.; Li, B.; Yang, J.; Wu, S.; Xu, X.; Ou, Y.; Xiong, L.; Lou, Y.; Li, Z.; et al. Prediction and Optimization of WAG Flooding by Using LSTM Neural Network Model in Middle East Carbonate Reservoir. In Proceedings of the Abu Dhabi International Petroleum Exhibition & Conference, Abu Dhabi, United Arab Emirates, 15–18 November 2021; SPE: Abu Dhabi, United Arab Emirates, 2021. [Google Scholar]
  97. Li, H.; Gong, C.; Liu, S.; Xu, J.; Imani, G. Machine Learning-Assisted Prediction of Oil Production and CO2 Storage Effect in CO2-Water-Alternating-Gas Injection (CO2-WAG). Appl. Sci. 2022, 12, 10958. [Google Scholar] [CrossRef]
  98. Andersen, P.Ø.; Nygård, J.I.; Kengessova, A. Prediction of Oil Recovery Factor in Stratified Reservoirs after Immiscible Water-Alternating Gas Injection Based on PSO-, GSA-, GWO-, and GA-LSSVM. Energies 2022, 15, 656. [Google Scholar] [CrossRef]
  99. Singh, G.; Davudov, D.; Al-Shalabi, E.W.; Malkov, A.; Venkatraman, A.; Mansour, A.; Abdul-Rahman, R.; Das, B. A Hybrid Neural Workflow for Optimal Water-Alternating-Gas Flooding. In Proceedings of the SPE Reservoir Characterization and Simulation Conference and Exhibition, Abu Dhabi, United Arab Emirates, 24–26 January 2023; SPE: Abu Dhabi, United Arab Emirates, 2023. [Google Scholar]
  100. Asante, J.; Ampomah, W.; Carther, M. Forecasting Oil Recovery Using Long Short Term Memory Neural Machine Learning Technique. In Proceedings of the SPE Western Regional Meeting, Anchorage, AK, USA, 22–25 May 2023; SPE: Anchorage, AK, USA, 2023. [Google Scholar]
  101. Matthew, D.A.M.; Jahanbani Ghahfarokhi, A.; Ng, C.S.W.; Nait Amar, M. Proxy Model Development for the Optimization of Water Alternating CO2 Gas for Enhanced Oil Recovery. Energies 2023, 16, 3337. [Google Scholar] [CrossRef]
  102. Xiong, X.; Lee, K.J. Data-Driven Modeling to Optimize the Injection Well Placement for Waterflooding in Heterogeneous Reservoirs Applying Artificial Neural Networks and Reducing Observation Cost. Energy Explor. Exploit. 2020, 38, 2413–2435. [Google Scholar] [CrossRef]
  103. Nwachukwu, A.; Jeong, H.; Pyrcz, M.; Lake, L.W. Fast Evaluation of Well Placements in Heterogeneous Reservoir Models Using Machine Learning. J. Pet. Sci. Eng. 2018, 163, 463–475. [Google Scholar] [CrossRef]
  104. Selveindran, A.; Zargar, Z.; Razavi, S.M.; Thakur, G. Fast Optimization of Injector Selection for Waterflood, CO2-EOR and Storage Using an Innovative Machine Learning Framework. Energies 2021, 14, 7628. [Google Scholar] [CrossRef]
  105. Ding, M.; Yuan, F.; Wang, Y.; Xia, X.; Chen, W.; Liu, D. Oil Recovery from a CO2 Injection in Heterogeneous Reservoirs: The Influence of Permeability Heterogeneity, CO2-Oil Miscibility and Injection Pattern. J. Nat. Gas Sci. Eng. 2017, 44, 140–149. [Google Scholar] [CrossRef]
  106. Ahmadi, M.A.; Zendehboudi, S.; James, L.A. Developing a Robust Proxy Model of CO2 Injection: Coupling Box–Behnken Design and a Connectionist Method. Fuel 2018, 215, 904–914. [Google Scholar] [CrossRef]
  107. Karacan, C.Ö. A Fuzzy Logic Approach for Estimating Recovery Factors of Miscible CO2-EOR Projects in the United States. J. Pet. Sci. Eng. 2020, 184, 106533. [Google Scholar] [CrossRef]
  108. Chen, B.; Pawar, R.J. Characterization of CO2 Storage and Enhanced Oil Recovery in Residual Oil Zones. Energy 2019, 183, 291–304. [Google Scholar] [CrossRef]
  109. Iskandar, U.P.; Kurihara, M. Time-Series Forecasting of a CO2-EOR and CO2 Storage Project Using a Data-Driven Approach. Energies 2022, 15, 4768. [Google Scholar] [CrossRef]
  110. You, J.; Ampomah, W.; Sun, Q.; Kutsienyo, E.J.; Balch, R.S.; Dai, Z.; Cather, M.; Zhang, X. Machine Learning Based Co-Optimization of Carbon Dioxide Sequestration and Oil Recovery in CO2-EOR Project. J. Clean. Prod. 2020, 260, 120866. [Google Scholar] [CrossRef]
  111. Ampomah, W.; Balch, R.S.; Grigg, R.B.; McPherson, B.; Will, R.A.; Lee, S.; Dai, Z.; Pan, F. Co-optimization of CO2-EOR and Storage Processes in Mature Oil Reservoirs. Greenh. Gases Sci. Technol. 2017, 7, 128–142. [Google Scholar] [CrossRef]
  112. You, J.; Ampomah, W.; Sun, Q.; Kutsienyo, E.J.; Balch, R.S.; Cather, M. Multi-Objective Optimization of CO2 Enhanced Oil Recovery Projects Using a Hybrid Artificial Intelligence Approach. In Proceedings of the SPE Annual Technical Conference and Exhibition, Calgary, AB, Canada, 30 September–2 October 2019; SPE: Calgary, AB, Canada, 2019. [Google Scholar]
  113. You, J.; Ampomah, W.; Kutsienyo, E.J.; Sun, Q.; Balch, R.S.; Aggrey, W.N.; Cather, M. Assessment of Enhanced Oil Recovery and CO2 Storage Capacity Using Machine Learning and Optimization Framework. In Proceedings of the SPE Europec featured at 81st EAGE Conference and Exhibition, London, UK, 3–6 June 2019; SPE: London, UK, 2019. [Google Scholar]
  114. Vo Thanh, H.; Sugai, Y.; Sasaki, K. Application of Artificial Neural Network for Predicting the Performance of CO2 Enhanced Oil Recovery and Storage in Residual Oil Zones. Sci. Rep. 2020, 10, 18204. [Google Scholar] [CrossRef] [PubMed]
  115. Emera, M.K.; Sarma, H.K. A Genetic Algorithm-Based Model to Predict CO-Oil Physical Properties for Dead and Live Oil. J. Can. Pet. Technol. 2008, 47, 52–61. [Google Scholar] [CrossRef]
  116. Rostami, A.; Arabloo, M.; Kamari, A.; Mohammadi, A.H. Modeling of CO2 Solubility in Crude Oil during Carbon Dioxide Enhanced Oil Recovery Using Gene Expression Programming. Fuel 2017, 210, 768–782. [Google Scholar] [CrossRef]
  117. Rostami, A.; Arabloo, M.; Lee, M.; Bahadori, A. Applying SVM Framework for Modeling of CO2 Solubility in Oil during CO2 Flooding. Fuel 2018, 214, 73–87. [Google Scholar] [CrossRef]
  118. Mahdaviara, M.; Nait Amar, M.; Hemmati-Sarapardeh, A.; Dai, Z.; Zhang, C.; Xiao, T.; Zhang, X. Toward Smart Schemes for Modeling CO2 Solubility in Crude Oil: Application to Carbon Dioxide Enhanced Oil Recovery. Fuel 2021, 285, 119147. [Google Scholar] [CrossRef]
  119. Iskandarov, J.; Fanourgakis, G.S.; Ahmed, S.; Alameri, W.; Froudakis, G.E.; Karanikolos, G.N. Data-Driven Prediction of in Situ CO2 Foam Strength for Enhanced Oil Recovery and Carbon Sequestration. RSC Adv. 2022, 12, 35703–35711. [Google Scholar] [CrossRef]
  120. Moosavi, S.R.; Wood, D.A.; Ahmadi, M.A.; Choubineh, A. ANN-Based Prediction of Laboratory-Scale Performance of CO2-Foam Flooding for Improving Oil Recovery. Nat. Resour. Res. 2019, 28, 1619–1637. [Google Scholar] [CrossRef]
  121. Raha Moosavi, S.; Wood, D.A.; Samadani, A. Modeling Performance of Foam-CO2 Reservoir Flooding with Hybrid Machine-Learning Models Combining a Radial Basis Function and Evolutionary Algorithms. Comput. Res. Prog. Appl. Sci. Eng. CRPASE 2020, 6, 1–8. [Google Scholar]
  122. Khan, M.R.; Kalam, S.; Abu-khamsin, S.A.; Asad, A. Machine Learning for Prediction of CO2 Foam Flooding Performance. In Proceedings of the ADIPEC, Abu Dhabi, United Arab Emirates, 31 October–3 November 2022; SPE: Abu Dhabi, United Arab Emirates, 2022. [Google Scholar]
  123. Vo Thanh, H.; Sheini Dashtgoli, D.; Zhang, H.; Min, B. Machine-Learning-Based Prediction of Oil Recovery Factor for Experimental CO2-Foam Chemical EOR: Implications for Carbon Utilization Projects. Energy 2023, 278, 127860. [Google Scholar] [CrossRef]
Figure 1. Distribution of different EOR projects worldwide [4].
Figure 1. Distribution of different EOR projects worldwide [4].
Make 06 00043 g001
Figure 2. Examples of different machine learning algorithms.
Figure 2. Examples of different machine learning algorithms.
Make 06 00043 g002
Figure 3. Representative intelligent optimization algorithms [15].
Figure 3. Representative intelligent optimization algorithms [15].
Make 06 00043 g003
Figure 4. (a). Rise of ML application papers in MMP prediction; (b) occurrence of different ML algorithms; (c) distribution of dataset size.
Figure 4. (a). Rise of ML application papers in MMP prediction; (b) occurrence of different ML algorithms; (c) distribution of dataset size.
Make 06 00043 g004
Figure 5. Occurrence of ML algorithms in WAG.
Figure 5. Occurrence of ML algorithms in WAG.
Make 06 00043 g005
Table 2. Summary for ML applications on WAG.
Table 2. Summary for ML applications on WAG.
AuthorsMethodsDatasetSplittingObjectivesInputsResultsEvaluationsLimitationsRating *
Hosseinzadeh Helaleh and Alizadeh [76]SVM (ACO, GA, PSO)20080% train + 20% testFractional oil recoveryRLC, RLD, NgAO, NgGO, MSWAG, NC, SGR, NPe, NSCon, NB, Nα, Nσ, λ*Dx, Nn, HeACO has high accuracy and low computational time compared to ANN, GA, and PSO.Evaluate with both experiments and simulations. Limited to a similar geological model.Only has SVM model.8
Le Van and Chon [79]ANN223 (simulation)45% train + 20% test + 35% validationOil recovery factor, oil rate, GOR, accumulative CO2 production, net CO2 storageSwi, kv/kh, WAG ratio, duration of each cycleANN models can support numerical simulation of CO2-EOR projects. WAG ratio less than 1.5 is best. Evaluated multiple objectives but only limited to ANN.Only have simulation results as trained data. 8
Van and Chon [80]ANN263 (simulation)50% train + 20% test + 30% validationOil recovery + net CO2 storage + cumulative gaseous CO2 productionKv/Kh, WAG ratio, Sw, well distance between each injector, TANN can help estimate oil recovery and CO2 storage. Injection cycle 25 is best.Evaluate different WAG ratios but limited to ANN models only.Only have simulation results as trained data.7
Mohagheghia [81]GA, PSO2000 (simulation)NANPV + incremental recovery factorWater and gas injection rates, BHP of producers, cycle ratio, cycle time, injected gas composition, total WAG periodPSO is capable of optimizing WAG variables and projects at field scale.First used GA in WAG at field scale. Evaluated with three case studies. Limited to specific geological models. Only GA and PSO are evaluated. Specific to E-segment.9
Nwachukwu, Jeong, Sun et al. [82]XGBoost, MADS1000 (simulation)50% train + 50% testOil/water/gas production rates, well locations, NPVWell x-coordinates, well y-coordinates, water/gas injection rates, well block ϕ/k, well block SwiThe new model combined XGBoost and MADS provided high accuracy.Demonstrated with a case study in which underlying geology is uncertain. Limited to one model.Only XGBoost is employed.8
Nait Amar et al. [77]ANN/GA, ACO8588% train + 12% testField oil production totalGas/water injection rates, gas/water injection half-cycle, WAG ratio, and slug sizeBoth GA and ACO are highly effective in the optimization of the WAG process.Demonstrated the application of a time-dependent proxy model for the WAG process. Without further application of the case study.Restricted to specific geological models. Limited simulation runs8
Belzareg et al. [83]Regression, GDMH429070% train + 30% testIncremental recovery factorkh, kv, API, gas gravity, water viscosity, solution GOR, WAG ratio, WAG cycle, land coefficient, reservoir pressure, PV of injected water, PV of injected gasGMDH performed better in selecting effective input parameters and optimizing the model structure.Novel approach but did not apply real field WAG pilot data to validate.Limited to two ML methods.8
Jaber et al. [84]CCD81NAOil recoveryk, ϕ, kv/kh, cyclic length, BHP, WAG ratio, CO2 slug sizeThe new proxy model can predict oil recovery. The optimum WAG ratio is 1.5. Developed a new proxy model based on CCD, but limited to one model.Limited data points and only from simulation runs.7
Menad and Noureddine [85]MLP (LMA, BR, SCG) + NSGA-IIFrom 2010 to 2018NAFOPR, FWPRTime, FWIR, FGIR, the value of the needed parameter at the previous time stepMLP-LMA has the highest accuracy and lowest computation time.Developed a dynamic proxy model for multiple objectives. But limited to one geological model.The database was generated based on multiple runs of the simulation.8
Nait Amar and Zeraibi [9]SVR, GA75NAField oil production totalInjection rates of water and gas, half-cycle injection time, WAG ratio, slug size, initialization time of the processSVR-GA provides high accuracy and reasonable CPU time.Established a dynamic proxy model based on SVR-GA, but no comparison with other algorithms.Limited data points and only one model evaluated.7
Yousef et al. [86]ANN8 years × 37 wells85% train + 15% testOil/gas/water production rate, GOR, infill well locationWell trajectory data, well logs, seismic data, production and injection history, reservoir pressure, choke opening, and WHP historyImplementing ANN
for top-down
modeling can predict
reservoir performance
under WAG.
Can predict the reservoir performance 3 months ahead. But simplify the data gathering, modeling, and validation process.Unknown about specific input data. No comparison with other models or field case studies.6
Belazreg and Mahmood [87]GDMH17770% train + 30% testIncremental oil recovery factorRock type, WAG process type, reservoir horizontal permeability, API, oil viscosity, reservoir pressure and temperature, and hydrocarbon pore volume of injected gasGDMH models can predict three WAG incremental recovery factors: sandstone immiscible gas injection, sandstone miscible gas injection, and carbonate miscible gas injectionProved GDMH can model the WAG process and has good potential. More data and validation are needed to improve model robustness and applicability.Limited published WAG pilot data.8
You et al. [88]ANN82080% train + 10% test + 10% validationOil recovery, CO2 storage, and project NPVWater injection time, CO2 injection time, producer BHP, water injection rateThe ANN proxy model can help improve the prediction performance.Could handle two or three objectives very well when a limited number of control parametersOnly suitable for limited input parameters.8
You et al. [89]Gaussian SVR-PSO217NAHydrocarbon recovery + CO2 sequestration volume + NPVFOPR × 2, gas cycle × 5, water cycle × 5 The proposed method can optimize the WAG process with high accuracy.Nice sensitivity studies of CO2 price and oil price on NPV. Limited comparison with other ML models.Restricted to specific geological models.8
Enab and Ertekin [90]ANN200080% train + 10% test + 10% validationProduction prediction, production schemes design, history matching25 inputs including reservoir rock characteristics, initial conditions, oil composition, well design parameters, and injection strategy parametersANN provides a faster prediction for fish-bone structure in low permeability reservoirs.Nice project design and economic analysis, but limited to ANN model only.Limitations were
Afzali et al. [91]GEP9667% train + 33% testRecovery factorOil viscosity, gas/water injection rates, k, PVI, number of cyclesThe developed model is successful when compared with experimental results.Novelty in using GEP. The dataset is from mathematical correlation.imposed by defining the range of each variable.8
Lv et al. [92]ANN-PSO210070% train + 15% test + 15% validationOil productionSo, Pi, k, ϕ, h, Pwf, water injection rate, water cut before gas flooding, gas injection rate, water injection volume, cycle time, water injection time, production rate, grid sizeANN-PSO provides a good model for parameter optimization of CO2 WAG-EOR.Routine procedures, not too much novelty in applying ANN-PSO.Limited and less supportive dataset. 8
Nait Amar et al. [93]MLP-LM, RBFNN-ACO/GWO8288% train + 12% testField oil production totalWater/gas injection rates, injection half-cycle, downtime, WAG ratio, gas slug sizeMLP-LMA is best. The proxy model can significantly reduce simulation time and conserve high accuracy. The application of GWO is novel. Limited runs and may have overfitting problems.No comparison with other ML models.7
Junyu et al. [94]Gaussian-SVR1400NACumulative oil production and cumulative CO2 storage.Water/gas cycle, producer BHP, water injection rate, etc. (91 variables in total)Gaussian-SVR performs best.Showed the possibility to design a CO2-WAG
project using as many inputs as possible.
Water cut is limited to 50%. Reservoir pressure must be higher than MMP.8
Sun et al. [95]SVR, MLNN, RSM60083% train + 17% testOil production, CO2 storage, NPV.Duration of CO2 and water injection cycles, water injection rate, production well specifications, oil price, CO2 price, etc. (62 parameters)The MLNN model can handle problems with large input and output dimensions.Compared three different methods. But only suitable for specific geological models.Given the large number of input parameters, the dataset may not be large enough.7
Huang et al. [96]LSTM540490% train + 10% testOil production, GOR, water cutDaily liquid rate, daily oil/gas/water rate, GIR, WIR, reservoir pressure, WHFP, choke size of producersThe calculation time of LSTM is 864% less than the simulation, while the prediction error of the LSTM method is 261% less than the simulation.The model is based on real reservoir data over 15 years. But limited to one ML model.The average reservoir pressure must be between 3700–5400 psi.8
Li et al. [97]RF21670% train + 30% testCumulative oil production, CO2 storage amount, CO2 storage efficiencyCO2-WAG period, CO2 injection rate, water-gas ratio, reservoir properties, oil properties, depth, layer thickness, Soi, well operationCO2-WAG cycle time has a slight influence on oil production. Random forest can predict oil production and CO2 storage.Proved RF has high computation efficiency and accuracy in CO2-WAG projects. But no comparison of different ML models.Only one ML model is considered. No comparison with other models.7
Andersen et al. [98]LSSVM—PSO/GA/GWO/GSA250070% train + 15% test + 15% validationOil recovery factorWater-oil and gas-oil mobility ratios, water-oil and gas-oil gravity numbers, reservoir heterogeneity factor, two hysteresis parameters, and water fractionLSSVM with GWO or PSO performed better than GA or GSA.Very detailed and thorough study. The dataset is relatively large. Some limitations of input parameters.Small dataset and only one ML model is studied. 7
Singh et al. [99]DNN-GA220070/80% train + 30/20% testMaximize oil recoveryWater injection rates, gas-to-water ratio, slug sizeDNN-GA workflow can identify improved WAG parameters over the baseline recovery, with incremental increases of 0.5–2%.Presents a novel workflow for WAG optimization using ML. Requires a large number of simulation runs (2200 here) to initially train DNN.Several important parameters were not varied much.9
Asante et al. [100]LSTM2345 × 380% train + 20% testOil production rate, oil recovery factorBottom-hole pressure at injector and producer, water and gas injection volumes, WAG cycleLSTM can model complex time-series data without the use of the geological model.Shows the ability of LSTM to perform time series analysis. But the input parameters are restricted.Limited to optimizing WAG parameters. 7
Matthew et al. [101]ANN-NSGA-II68 + 97NAMaximize oil produced and CO2 storageWater and gas injection rate, half-cycle length, time stepThe developed proxy model can predict both simple and complex models.Developed a dynamic proxy model for multiple objectives. But the dataset size is limited.Requires large amounts of quality field data.7
*: On a scale of 1 to 10, a higher score indicates higher quality of the article.
Table 3. Summary of ML applications in well location optimization.
Table 3. Summary of ML applications in well location optimization.
AuthorsMethodsDatasetSplittingObjectivesInputsResultsEvaluationsLimitationsRating *
Nwachukwu et al. [103]XGBoost200, 500, 1000NATotal profit, cumulative oil/gas produced, net CO2 storedWell-to-well pairwise connectivity, injector block k and ϕ, initial injector block saturationsQuick evaluation of well placement using well-to-well connectivity was successful with 1000 simulation runs and R2 = 0.92.No co-optimization of oil recovery and CO2 storage, only ML proxy usage.The dataset is from simulation runs. Only suitable for one geological model.8
Selveindran et al. [104]AdaBoost, RF, ANN3000, 2000, 100070% train + 30% testIncremental oil production K, ϕ, PV, initial fluid saturation, pressure, time of flight, well-to-well distances, distance to the injector, injection rate, and injection depthStacked learner is better than an individual learner. ML helps rapidly identify the areas that are optimal for injection.Detailed and comprehensive analysis, including posterior sampling.Heavily rely on the geological model.8
*: On a scale of 1 to 10, a higher score indicates higher quality of the article.
Table 4. Summary of ML applications on oil production/recovery factor.
Table 4. Summary of ML applications on oil production/recovery factor.
AuthorsMethodsDatasetSplittingObjectivesInputsResultsEvaluationsLimitationsRating *
Ahmadi et al. [106]LSSVM4680% train + 20% testOil recovery factorBHP of injection well, CO2 injection rate, CO2 injection concentration, BHP of production well, oil production rateThe hybridization of LSSVM and BBD is statistically correct for predicting RF.Provided the possibility of using ML and comparing it with commercial software. But limited dataset. Small dataset and only suitable for similar oil reservoirs. Only valid for the same input parameters range.7
Chen and Pawar [108]MARS, SVR, RF500, 250, 100NARecovery factorThickness, depth, k, Sor, CO2 injection rate, BHP of production wellMARS has the best performance.Applied to 5 fields in Permian Basin and had good matches. Heavily relies on a base model and may not fully represent diverse ROZs.Significant assumptions are made regarding uncertain parameters like residual oil saturation.8
Karacan [107]FL2483% train + 17% testRecovery factorLithology, API, ϕ, k, HCPV, depth, net pay, Pi, well spacing, SorwFL provided a reasonably accurate prediction.Though a small dataset, it provides the possibility of using ML in recovery factor prediction.Too difficult to draw statistical conclusions from such a small dataset.7
Iskandar and Kurihara [109]AR, MLP, LSVM3653 × 8 wells40% train + 20% test + 40% validationOil, gas, and water productionϕ, k, formation thickness, BHP, flow capacity, storage capacityThe AR model is best, with long and consistent forecast horizons across wells. LSTM performs well but has shorter forecast horizons. MLP has high variability and short forecast horizons.First time series forecasting study. No model updating/retraining over time. Overall, it is a solid study.Limited hyperparameter tuning is performed. Only three models were tested.9
*: On a scale of 1 to 10, a higher score indicates higher quality of the article.
Table 5. Summary of ML applications on multi-objective optimizations.
Table 5. Summary of ML applications on multi-objective optimizations.
AuthorsMethodsDatasetSplittingObjectivesInputsResultsEvaluationsLimitationsRating *
Ampomah et al. [111]GANANAOil recover + CO2 storageNAThe proxy models to determine the optimal operational parameters, including injection/production rates, pressure, and WAG cycles.First used proxy models and GA to optimize oil recovery and CO2 storage simultaneously. But relies heavily on having an accurate reservoir mode.Optimal parameters are specific to this reservoir—and not necessarily generalizable.7
You et al. [112]RBFNN160N/ACumulative oil production + CO2 storage + NPVwater cycle, gas cycle, BHP of producer, water injection rateThe proxy model is built based on RBFNN for optimization.The overall prediction is acceptable, but the CO2 storage prediction is much higher. The CO2 storage optimization is 18% higher than the baseline.7
You et al. [113]ANN-PSO820 (numerical model)80% train + 10% test + 10% validationCumulative oil production + CO2 storage + NPVwater cycle, gas cycle, BHP of producer, water injection rateThe optimization study showed promising results for multiple objectives.Developed a novel hybrid optimization for multiple objective functions. But only validated with field case.Only four input parameters are considered.7
Vo Thanh et al. [114]ANN-PSO351 (numerical model)80% train + 10% test + 10% validationCumulative oil production + cumulative CO2 storage +cumulative CO2 retainedϕ, k, Sorg, Sorw, BHP of producer, CO2 injection rateANN can forecast the performance of CO2 EOR and storage in a residual oil zone.The ANN provides R2 of 0.99 and MSE of less than 2%, but the application in other types of reservoirs is questionable. Case specific. 7
*: On a scale of 1 to 10, a higher score indicates the higher quality of the article.
Table 6. Summary of ML application on PVT properties.
Table 6. Summary of ML application on PVT properties.
AuthorsMethodsDatasetSplittingObjectivesInputsResultsEvaluationsLimitationsRating *
Emera and Sarma [115]GA106 (dead oil), 74 (live oil)NACO2 solubility, oil swelling factor, CO2-oil density, and viscosity API, Ps, T, MWThe GA-base correlations provided the highest accuracy.First applied GA in CO2-oil properties prediction. Will be more helpful if a full dataset is provided.Validated over a certain data range. May not be reliable if it is out of data range.8
Rostami et al. [116]ANN, GEP106 (dead oil), 74 (live oil)80% train + 20% testCO2 solubilityPs, T, MW, γ, PbGEP is more accurate than ANN for dead oil. Compared with several empirical methods. More comparisons between ML models will be more persuasive. Limited dataset on live oil. 8
Rostami et al. [117]LSSVM106 (dead oil), 74 (live oil)70% train + 15% test + 15% validationCO2 solubilityPs, T, MW, γLSSVM showed higher accuracy compared to previous empirical correlations. More rigorous validation against experimental data equations of state models would be useful.Only a few literature models were compared. 7
Mahdaviara et al. [118]MLP, RBF (GA, DE, FA), GMDHNANACO2 solubilityPs, T, MW, γ, PbMLP-LM and MLP-SCG are better at predicting solubility. GMDH is better than LSSVM.Compared with various models and optimization methods. But unknown for the dataset.Not known for the dataset.8
Hamadi et al. [74]MLP-Adam, SVR-RBF, XGBoost105 (dead oil), 74 (live oil)80% train + 20% testCO2 solubility, IFTPs, T, MW, γ, PbSVR-RBF provided the best accuracy.Limited comparisons between different models.Given the year that this paper was published, the dataset is small.7
*: On a scale of 1 to 10, a higher score indicates higher quality of the article.
Table 7. Summary of ML application on CO2-foam EOR.
Table 7. Summary of ML application on CO2-foam EOR.
AuthorsMethodsDatasetSplittingObjectivesInputsResultsEvaluationsLimitationsRating *
Moosavi et al. [120]MLP, RBF (GA, COA)21480% train + 20% test;
75% train + 25% test;
90% train + 10% test
Oil flow rate and recovery factorSurfactant kind, ϕ, K, PV of core, Soi, injected foam PVBoth MLP and RBF provide high accuracy with R2 up to 0.99.The earliest research on CO2-foam EOR. Only focus on laboratory data.Only studied two methods, and there was no comparison among other ML algorithms.8
Raha Moosavi et al. [121]RBF (TLBO, PSO, GA, ICA)21480% train + 20% testOil flow rate and recovery factorSurfactant kind, ϕ, K, PV of core, Soi, injected foam PVRBF-TLBO provides the highest accuracy.Proved ML can provide high accuracy (R2 can reach 0.999), but is only limited to coreflood.Limited to laboratory experiments.8
Iskandarov et al. [119]DT, RF, ERT, GB, XGBoost, ANN14570% train + 30% testSurfactant stabilized CO2 apparent foam viscosity Shear rate, Darcy velocity, surfactant concentration, salinity, foam quality, T, and pressureML can provide reliable prediction, and ANN provides the highest accuracy.Proved ML can predict for both bulk and sandstone formation under various conditions.The dataset size is relatively small and may have overfitting.8
Khan et al. [122]XGBoost20070% train + 30% testOil recovery factorFoam type, Soi, total PV tested, ϕ, K, injected foam PVXGBoost can provide high accuracy.Proved XGBoost can be used for CO2-foam. Limited to laboratory data.Only one ML is applied. No other comparisons.7
Vo Thanh et al. [123]GRNN, CFNN-LM, CFNN-BR, XGBoost26070% train + 30% testOil recovery factorIOIP, TPVT, ϕ, K, injected foam PVPorosity is the most significant parameter. GRNN has the highest accuracy.Comprehensive and detailed description. Limited to laboratory experiments.9
*: On a scale of 1 to 10, a higher score indicates the higher quality of the article.
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Du, X.; Salasakar, S.; Thakur, G. A Comprehensive Summary of the Application of Machine Learning Techniques for CO2-Enhanced Oil Recovery Projects. Mach. Learn. Knowl. Extr. 2024, 6, 917-943. https://doi.org/10.3390/make6020043

AMA Style

Du X, Salasakar S, Thakur G. A Comprehensive Summary of the Application of Machine Learning Techniques for CO2-Enhanced Oil Recovery Projects. Machine Learning and Knowledge Extraction. 2024; 6(2):917-943. https://doi.org/10.3390/make6020043

Chicago/Turabian Style

Du, Xuejia, Sameer Salasakar, and Ganesh Thakur. 2024. "A Comprehensive Summary of the Application of Machine Learning Techniques for CO2-Enhanced Oil Recovery Projects" Machine Learning and Knowledge Extraction 6, no. 2: 917-943. https://doi.org/10.3390/make6020043

Article Metrics

Back to TopTop