Solubility Of CO2 In Ionic Liquids Research Articles

Insight to the prediction of CO2 solubility in ionic liquids based on the interpretable machine learning model

In this work, we investigated three different ML-based models, i.e., GPR, LightGBM, and CatBoost, for predicting the solubility of CO2 in various ionic liquids (ILs). Three molecular descriptors, i.e., group contribution (GC), molecular structure descriptors (MSD), and hybrid GC-MSD are used in our three models. The performance of our developed models were rigorously evaluated using mean absolute error (MAE), coefficient of determination (R2), and mean relative error (MRE) (i.e., relative deviation in percentage), with each model subjected to multiple tests employing different random state parameters. The dataset underwent partitioning into training and testing sets at an 80:20 ratio, with additional splits at various ratios to assess prediction performance sensitivity. Overall, all models exhibited proficient CO2 solubility prediction in ILs, with performance varying based on descriptor type. Notably, the hybrid GC-MSD consistently outperformed others, attributed to GC-MSD incorporates a broader array of molecular feature information. Particularly, the CatBoost-GC-MSD model excelled, achieving an impressive R2 of 0.9925, MAE of 0.0122, and MRE of 11.1550%. Comparing our models to previous studies revealed the superior performance of CatBoost-GC-MSD across all descriptor types. Furthermore, our model interpretation, employing SHAP analysis, identified pressure, temperature, Chi0, Kappa2, and EState_VSA10 as the top five influential input features. These findings provide valuable insights into the underlying molecular features affecting CO2 solubility in ILs and lay the foundation for future research in this field.

Estimating CO2 solubility in ionic liquids by using machine learning methods

Ionic liquids (ILs) can be used to absorb a greater quantity of carbon dioxide (CO2) by adjusting the ratio of anions and cations.The methods to obtain CO2 solubility in ILs are as follows: Experiment, Equation of State (EOS) and Molecular dynamics simulation (MD). The experiment is time-consuming and labor-intensive, EOS requires critical parameters, and MD calculation is complicated. However, Machine Learning (ML) methods are embraced with high prediction accuracy and convenience by the chemical and petroleum industry. In this work, 1517 solubility data were collected based on 20 different ILs. Three different machine learning methods (Optimization (PSO), Grey Wolf Optimization (GWO) and Sparrow Search Algorithm (SSA) based on Support Vector Machine (SVR)), using acentric factor (ω), critical temperature (Tc), critical pressure (pc) of ILs accompanied by pressure (p), and temperature (T), as input parameters, were employed to predict CO2 solubility in ILs. Meanwhile, three error indexes (namely root mean square error (RMSE), correlation coefficient (R2) and average absolute relative deviation (AARD)), and the duration of time each specified model (PSO-SVR, GWO-SVR and SSA-SVR) takes in order to evaluate the effectiveness of each prediction model.Although the results show that the three different optimization models (PSO-SVR, GWO-SVR and SSA-SVR) have viable prediction effects, the performance of PSO-SVR model has high accuracy and is the lowest time-consuming among them with RMSE and R2 of 0.01881 and 0.9824, respectively. For the SSA-SVR, the estimated RMSE and R2 are respectively 0.01944 and 0.9824 while they are 0.01889 and 0.9822 for the GWO-SVR, respectively. The results imply that all of the models can give reliable predictions on the CO2 solubilities in ILs and the PSO-SVR model performs slightly better than the SSA-SVR and GWO-SVR models.

Prediction of CO2 solubility in ionic liquids via convolutional autoencoder based on molecular structure encoding

AbstractIn this study, novel molecular structure encoding descriptors composed of feature encoding and one‐hot encoding was developed and then convolutional autoencoder was used to denoise based on the structure of ionic liquids (ILs). It could be used to predict the CO2 solubility in ILs at different temperatures and pressures, when combined with three different machine learning algorithms (multilayer perceptron [MLP], random forest [RF], and support vector machine [SVM]). Statistics of the prediction results show that the newly proposed molecular structure‐based coding has better regression prediction performance than the conventional molecular cheminformatics descriptors. SE‐MLP model with R2 of 0.9873 and mean square error of 0.0007 has the best performance in predicting the CO2 solubility in ILs. In addition, the relationship between features and dissolved CO2 capacity was analyzed through model interpretation to retrieve physical insights for the underlying system. This work provided a new predictive tool for enriching and refining data on CO2 solubility in ILs and for solving phase equilibrium problems.

SCREENING OF IONIC LIQUIDS FOR CO2 CAPTURE USING DATA ANALYTICS TECHNIQUES

Carbon dioxide (CO2) is the most prominent greenhouse gas (GHG) present in the atmosphere, making it the most accountable for global warming. CO2 capture is capable of greatly reducing carbon emissions. The current method of CO2 capture by amine-based solvent has drawbacks, such as high demand for energy and intense corrosion, making it a less reliable method. More attention is given to ionic liquids (ILs) for their negligible vapour pressure, low melting point, and high chemical and thermal stability advantage. This study uses data analytics techniques to develop a predictive model for screening ILs for CO2 capture, moving away from the experimental approach, which is burdensome, costly, and less environmental-friendly. Data on the properties and parameters of ILs are collected from COSMO-RS software. CO2 solubility is the function of collected data and developed into 15 models of three different methods: Support Vector Machine (SVM), Neural Networks (NN), and Gaussian Process Regression (GPR). The use of data analytics in this field is new and can provide valuable insight towards CO2 solubility in ILs. The dataset is distributed randomly at 80/20% for training and testing. Each model is evaluated using R-squared and root mean square error (RMSE). The rational Quadratic GPR model shows the lowest RMSE of 0.0002 for training and testing, with R-squared the closest to 1. Rational Quadratic GPR is the best model to be used for screening IL for CO2 capture.

Solubility‐Boosted Molecular Sieving‐Based Separation for Purification of Acetylene in Core–Shell IL@MOF Composites

AbstractConsidering the small amount of CO2 as a contaminant in industrial gas mixtures, developing CO2‐selective adsorbents exhibit advantages in directly obtaining pure C2H2 in one‐step to reduce the energy consumption. However, it is still a great challenge due to the essential molecular feature of C2H2, including the triple bond and high polarizability. Herein, a simple but effective CO2‐facilitated transport strategy is presented to realize the overwhelming adsorption of CO2 over C2H2 by constructing core–shell composite structures using ionic liquid (IL) and metal‐organic framework (MOF). With the aid of excellent solubility of CO2 in IL and almost total exclusion of C2H2, the obtained materials boost molecular sieving‐based separation of CO2/C2H2. Density functional theory calculations combining molecular dynamic simulations revealed the solution‐diffusion mechanism for CO2, which is rarely reported in solid adsorbents. Ideal adsorbed solution theory selectivity for CO2/C2H2 with 1/1 and 1/3 volume ratios can reach over 104 and 4000 at 100 kPa with a high CO2 uptake of 40.3 cm3 g−1, superior to those of the reported materials so far. More importantly, this solution‐based separation strategy can avoid the difficulty for precise control of the regulation of adsorbent structure, which may be beneficial to practical production.

Prediction of carbon-dioxide activity coefficient for solubility in ionic liquids using multi-non-linear regression analysis.

Activity coefficient values offer insight into the intermolecular interactions between the solute and the solvent and the deviation from the ideal behavior. CO2 capture from different industrial processes is a globally pertinent issue and the search for suitable chemicals is required. To address the issue, knowledge of activity coefficient values is crucial for CO2 separation-based process. In this regard, a correlation is developed that predicts the coefficient of CO2 activity in ionic liquids by multi-nonlinear regression analysis. The correlation is developed between the pressure range of 1–50 bar and the temperature range of 298.15–33.15 K for mole fractions of 0.3, 0.5, and 0.7. Outliers’ analysis is performed using the boxplot method to determine the suitability of ranges of the selected input parameters. The preceding literature does not predict the activity coefficient in relatively lower to higher temperature and pressure ranges for CO2 solubility in ionic liquids. Initially, the activity coefficient values from COSMO-RS were obtained and compared with the correlation results. The COSMO-RS and the correlation predicted results were subsequently validated with the experimental data. The average absolute error (AAE%) of the predicted correlation values is 19.53% while the root mean square error (RMSE) value is 0.465. The correlation can be used in the future to predict the CO2 activity coefficient values in ionic liquids to facilitate qualitative analyses of their CO2 capture efficiency.

Solubility of CO2 in Ionic Liquids with Additional Water and Methanol: Modeling with PC-SAFT Equation of State

The superior properties of specific ionic liquids (ILs), such as negligible volatility, high thermal stability, flexible designability, and their affinity to capture CO2, make them an attractive alternative to chemical and physical solvents that are currently used in CO2 capture processes. However, a limitation to use ILs for industrial CO2 capture is their high viscosity compared to conventional solvents, which leads to a lower CO2 capture rate and higher pumping cost. The viscosity of ILs can be reduced by adding a co-solvent, such as water or methanol. In this work, solubility, vapor–liquid equilibria (VLE), and liquid–liquid equilibria (LLE) for binary and ternary mixtures involving CO2, ILs, water, and methanol have been systematically investigated by employing perturbed-chain statistical associating fluid theory (PC-SAFT) equation of state with two different strategies. ILs were considered as self-associating chain molecules with two association sites in the first strategy. As a comparison, they were regarded as strong electrolytes that dissociate into anions and cations in the second strategy. It was found that both strategies provide accurate correlations in modeling CO2 solubilities in ILs and LLE of binary ILs/water systems. Four ternary systems were selected to verify the predictive capability of the two strategies. For water-containing systems, both strategies performed excellently when binary interaction parameters (BIPs) can be obtained by fitting to experimental data, while they performed poorly for system with few experimental data. For cases where methanol acted as a co-solvent, accurate predictions were obtained with both strategies, even without any BIPs. PC-SAFT was found to be a potential practical tool to develop CO2 capture processes with new alternative solvents when there are sufficient experimental data for binary mixtures.

Application of a Single Multilayer Perceptron Model to Predict the Solubility of CO2 in Different Ionic Liquids for Gas Removal Processes

In this work, 2099 experimental data of binary systems composed of CO2 and ionic liquids are studied to predict solubility using a multilayer perceptron. The dataset includes 33 different types of ionic liquids over a wide range of temperatures, pressures, and solubilities. The main objective of this work is to propose a procedure for the prediction of CO2 solubility in ionic liquids by establishing four stages to determine the model parameters: (1) selection of the learning algorithm, (2) optimization of the first hidden layer, (3) optimization of the second hidden layer, and (4) selection of the input combination. In this study, a bound is set on the number of model parameters: the number of model parameters must be less than the amount of predicted data. Eight different learning algorithms with (4,m,n,1)-type hidden two-layer architectures (m = 2, 4, …, 10 and n = 2, 3, …, 10) are studied, and the artificial neural network is trained with three input combinations with three combinations of thermodynamic variables such as temperature (T), pressure (P), critical temperature (Tc), critical pressure, the critical compressibility factor (Zc), and the acentric factor (ω). The results show that the 4-6-8-1 architecture with the input combination T-P-Tc-Pc and the Levenberg–Marquard learning algorithm is a very acceptable and simple model (95 parameters) with the best prediction and a maximum absolute deviation close to 10%.

Predicting the Thermodynamics of Ionic Liquids: What to Expect from PC-SAFT and COSMO-RS?

Two popular thermodynamic modeling frameworks, namely, the PC-SAFT equation of state and the COSMO-RS model, are benchmarked for their performance in predicting the thermodynamic properties of pure ionic liquids (ILs) and the solubility of CO2 in ILs. The ultimate goal is to provide an illustration of what to expect from these frameworks when applied to ILs in a purely predictive way with established parametrization approaches, since the literature generally lacks their mutual comparisons. Two different modeling approaches with respect to the description of the molecular structure of ILs are tested within both models: a cation-anion pair as (i) a single electroneutral supermolecule and (ii) a pair of separately modeled counterions (ion-based approach). In general, we illustrate that special attention should be paid when estimating unknown thermodynamic data of ILs even with these two progressive thermodynamic frameworks. For both PC-SAFT and COSMO-RS, the supermolecule approach generally yields better results for the vapor pressure and the vaporization enthalpy of pure ILs, while the ion-based approach is found to be more suitable for the solubility of CO2. In spite of some shortcomings, COSMO-RS with the supermolecule approach shows the best overall predictive capabilities for the studied properties. The ion-based strategy within both models has significant limitations in the case of the vaporization properties of ILs. In COSMO-RS, these limitations can, to a certain extent, be surpassed by additional quantum mechanical calculations of the ion pairing in the gas phase, while the ion-based PC-SAFT approach still needs a sophisticated improvement to be developed. As an initiating point, we explore one possible and simple route considering a high degree of cross associations between the counterions in the gas phase.

Electroreduction of low concentration CO2 at atomically dispersed Ni-N-C catalysts with nanoconfined ionic liquids

Most studies on electrochemical CO2 reduction reaction use pure CO2, which requires extra energy for CO2 capture and enrichment from atmosphere. Herein, nanoconfined ionic liquids are introduced into porous atomically dispersed nickel-nitrogen-carbon (Ni-N-C) catalysts to enrich local CO2 concentration and increase the CO2RR kinetics. A series of high-CO2-solubility ionic liquids (ILs) were impregnated into the pores of the columnar Ni-N-C catalyst to alter the CO2-Ni sites interactions and create a solid/liquid interface with high CO2 concentration. The optimal Ni-N-C/[Bmim][PF6] composite outperforms the Ni-N-C catalyst for pure CO2 electroreduction with a maximum FECO of 99.6% and 2.7-fold larger jCO. The high solubility of CO2 in ILs compared to aqueous electrolyte enables direct electrolysis of CO2 at low concentrations. When fed with 5–10% (v/v) CO2, the Ni-N-C/[Bmim][PF6] composite exhibited up to 1.5-fold higher FECO and a 68% increase of jCO, in comparison to Ni-N-C, and robust stability over 30 h.

Estimation of CO2 solubility in ionic liquids using connectionist tools based on thermodynamic and structural characteristics

Ionic Liquids (ILs) are a promising alternative to conventional amine-based solvents in CO2 absorption processes. Relatively high cost and viscous nature of ILs tempt researchers to find appropriate combination of cations and anions for targeting a competitive absorbent close to amines in terms of CO2 absorption capacity. Conducting extensive experimental studies appears to be time-consuming and expensive for a large number of common CO2/IL systems. One of the fast and reliable approaches to predict the solubility of CO2 in ILs is Machine Learning (ML)-based models or smart tools where the thermodynamic-based and structure-based property relationships can be explored. Four ML methods including Least Squares Support Vector Machine (LSSVM), Decision Tree (DT), Random Forest (RF), and Multilinear Regression (MLR) are employed in this study to obtain CO2 solubility in a structurally diverse set of ILs based on thermodynamic properties and Quantitative Structure–Activity Relationship (QSPR) model. In this paper, two datasets of CO2 solubility (taken from the literature) at various operating conditions are used; one model (or dataset) considers critical properties, molecular weight, and acentric factor of pure ILs as the input information, and the second one includes structural descriptors of cations and anions as the input parameters. Among different types of descriptors, the most important input variables (e.g., Homo-Lumo fraction and Disps (cation)) are selected using Genetic Algorithm (GA)-MLR method. The predictive ability of the introduced models is also analyzed using a four-fold external cross-validation procedure. A great match between the predicted values and experimental measurements is attained while using RF and DT techniques developed based on descriptors and thermodynamics properties. The structural descriptors-based models are more accurate and robust than those built on the critical properties. The feature selection approach is also applied to identify the most effective cation and anion descriptors. For both thermodynamic and QSPR modeling approaches, pressure has the maximum relative importance in the estimation of CO2 solubility in ILs. In the absence of temperature and pressure impacts, the critical pressure and Homo-Lumo fraction have the highest contribution to the thermodynamic – based and structural-based tools, respectively.

Prediction of CO2 solubility in ionic liquids using machine learning methods

A comprehensive database containing 10,116 CO2 solubility data measured in various ionic liquids (ILs) at different temperatures and pressures is established. Based on this database, the relationship between CO2 solubility and IL structure, temperature and pressure is correlated using group contribution (GC) methods. Two different machine learning algorithms, namely artificial neural network (ANN) and support vector machine (SVM), are employed to develop the GC models. For the 2023 test-set data, the estimated MAE and R2 are 0.0202 and 0.9836, respectively for the ANN-GC model and for the SVM-GC model they are 0.0240 and 0.9783, respectively. The distributions of prediction errors are plotted for both models to provide more comprehensive knowledge on the model performance. The results indicate that both of the models can give reliable predictions on the CO2 solubilities in ILs and the ANN-GC model performs slightly better than the SVM-based model.

Searching for Solvents with an Increased Carbon Dioxide Solubility Using Multivariate Statistics.

Ionic liquids (ILs) are used in various fields of chemistry. One of them is CO2 capture, a process that is quite well described. The solubility of CO2 in ILs can be used as a model to investigate gas absorption processes. The aim is to find the relationships between the solubility of CO2 and other variables—physicochemical properties and parameters related to greenness. In this study, 12 variables are used to describe a dataset consisting of 26 ILs and 16 molecular solvents. We used a cluster analysis, a principal component analysis, and a K-means hierarchical clustering to find the patterns in the dataset and the discriminators between the clusters of compounds. The results showed that ILs and molecular solvents form two well-separated groups, and the variables were well separated into greenness-related and physicochemical properties. Such patterns suggest that the modeling of greenness properties and of the solubility of CO2 on physicochemical properties can be difficult.

Effective modeling methods to accurately predict the miscibility of CO2 in ionic liquids

CO2 solubility in ionic liquids (ILs) over wide temperature and pressure ranges of (283.15–373.35 K) and (99.8–85800.0 kPa), respectively, has been predicted using three models; a group method of data handling correlation (model I), a radial basis function network (model II), and an empirical relation (model III). The Nelder–Mead simplex and Levenberg–Marquardt algorithms were used to find the constants of the suggested functionality relations for models I and III, respectively. Model I with R2, RMSE and AARD% of 0.9650, 4.2727 and 8.46, respectively; model II with R2, RMSE and AARD% of 0.9942, 1.7172, and 4.23, respectively and model III with R2, RMSE and AARD% of 0.9886, 2.4248 and 4.25, respectively, were highly accurate in the prediction of experimental values. All the models proposed are vigorous and possess satisfactory error trends based on a comprehensive statistical assessment. To confirm the validity of the database, the dataset was subjected to a statistical outlier diagnostic test.

Energy Analysis of Physical Absorption and Chemical Absorption of CO2 in Ionic Liquids

CO2 solubility in ionic liquids (ILs) is measured extensively to develop IL‐based technology for CO2 capture. Herein, the choline‐ and acetate‐based ILs are selected as the studied physical and chemical absorbents for CO2 capture, respectively. The CO2 solubilities in choline‐ and acetate‐based ILs are thermodynamically modeled. The ILs consumed for CO2 absorption and the energy demands for the ILs regeneration are calculated and compared with those of the conventional imidazolium‐based ILs. The results show that the three choline‐based ILs are not energy saving in the pressure‐swing process. In the temperature‐swing process, the energy demand for CO2 absorption by using acetate‐based ILs reveals that the chemical absorption‐based ILs are the absorbent with lower energy demands compared with the physical absorption‐based ILs.

Prediction carbon dioxide solubility in ionic liquids based on deep learning

Ionic liquids have a great potential in capture and separation of carbon dioxide (CO2), and the solubility of CO2 in ionic liquids is one of key data for engineering applications. In this paper, the critical properties of ionic liquids are combined with deep learning models (CP-DNN, CP-CNN, CP-RNN) to establish theoretical prediction models of CO2 solubility in ionic liquids. The predictive performance of these framworks is able to meet or exceed the predicted effects of the method based on thermodynamic models (PR,SRK) and machine learning method (XGBoost). For CP-RNN, the coefficient of determination (R 2) between experimental and predicted values is 0.988, CP-CNN is 0.999, and CP-DNN is 0.984. This research can avoid complex computational characterisation, it is to provide a theoretical method to further enrich and improve the data information analysis of the solubility of CO2 in ionic liquids.

Assessment of carbon dioxide solubility in ionic liquid/toluene/water systems by extended PR and PC-SAFT EOSs: Carbon capture implication

Recently, there has been a growing interest in CO2 capture using ionic liquids (ILs). To determine the CO2 absorption potential of ILs and their selectivity in the presence of other gaseous components in the mixture, the solubility of ILs at various operating conditions and the influence of impurities/additives such as water and toluene should be evaluated. Carbon capture capacity of the ILs can be examined using various methods such as experiments, thermodynamic approaches including Equations of State (EOSs), and molecular-based modeling. In this research work, the extended Peng–Robinson (PR) and Perturbed-Chain Statistical Associating Fluid Theory (PC-SAFT) EOSs are utilized to assess the solubility and selectivity of CO2 in ILs through comparing the modeling results with experimental data. PC-SAFT and PR parameters are determined by employing the experimental density data. Modeling results reveal that the solubility values estimated by the PC-SAFT due to considering the association effects have a lower deviation (or a better performance) than PR EOS based on the magnitudes of Absolute Average Deviation (AAD %). The AAD (%) for [bmim][BF4], [bmim][PF6], [bmim][Tf2N], [hmim][Tf2N], [hmim][FAP], and [hmim][FAP] are calculated using PR EOS and PC-SAFT EOS, which are 2–5.7% and 3–7.5%, respectively. Furthermore, ternary systems of CO2 + ILs + water and CO2 + ILs + toluene are modeled to determine the effect of water and toluene on the gas solubility in ILs and viscosity of ILs with PC-SAFT EOS. Based on the results, low concentrations of water (0.1 wt%) have a negligible influence on the CO2 solubility in ILs. However, with increasing the water concentration, the solubility of water reduces significantly. On the other hand, the viscosity of ILs is reduced with increasing the water concentration. Viscosity reduction in the hydrophilic ILs is significant. It seems promising to add water up to 10 wt% to hydrophilic ILs, since a decrease in the viscosity to an amount close to the viscosity of water and a decrease in solubility by 9% are experienced. Finally, the selectivity of [hmim][Tf2N] in separation of CO2 from mixtures containing H2S, SO2, CH4, and H2 are reported. Based on the results, [hmim][Tf2N] is not appropriate for separation of CO2 from streams with a high concentration of H2S and SO2 gases.

CO2 absorption with ionic liquids at elevated temperatures

CO2 capture with ionic liquids (ILs) has attracted many attentions, and most works focused on absorption ability at ambient temperatures, while seldom research was concerned at elevated temperatures. This not only limits the CO2 absorption application at elevated temperature, but also the determination of the operation condition of the CO2 desorption generally occurring at higher temperature. This work mainly reported CO2 solubilities in ILs at elevated temperatures and related properties were also provided. 1-alkyl-3-methylimidazolium bis(trifluoromethylsulfonyl)imide ([CnMIm][Tf2N]) ILs were selected as physical absorbents for CO2 capture in this work due to their relative higher CO2 absorption capacities and good thermal stabilities. The long-term stability tests showed that [CnMIm][Tf2N] is thermally stable at 393.15 K for long time. CO2 solubilities in [CnMIm][Tf2N] were systematically determined at temperatures from 353.15 K to 393.15 K. It demonstrated that CO2 solubility obviously increases with the increase of pressure while slightly decreases with increase of temperature. As the length of alkyl chain on the cation increases, CO2 solubility in ILs increases. Additionally, the thermodynamic properties including the Gibbs free energy, enthalpy, and entropy of CO2 were also calculated.

Modeling H2S and CO2 solubility in ionic liquids using the CPA equation of state through a new approach

In this communication, the solubility of two single gases, hydrogen sulfide and carbon dioxide, in the fourteen ionic liquids ([emim][eFAP], [emim][EtSO4], [emim][OTf], [emim][Tf2N], [bmim][BF4], [bmim][PF6], [hmim][PF6], [hmim][Tf2N], [omim][PF6], [omim][Tf2N], [HOemim][BF4], [HOemim][OTf], [HOemim][PF6] and [HOemim][Tf2N]) are modeled using the CPA EoS through a new approach. First, the critical temperature of ionic liquids was estimated using modified Lydersen-Joback-Reid method. Then, Using the CPA EoS, the pure parameters of ionic liquids were obtained through optimization on both of H2S and CO2 solubility data in ionic liquids as well as experimental liquid density data of ionic liquids. In next step, the interaction parameters between the ionic liquids and H2S as well as the ionic liquids and CO2 were calculated. Using the obtained pure parameters of the ionic liquids and the interaction parameters, the vapor-liquid equilibrium data were tested for thermodynamic consistency. Also, the proposed systems were modeled by the SRK EoS and the obtained results were compared by the obtained ones by the CPA EoS. For all the studied systems, the percent average absolute deviation (AAD %) was lower than 10% that shows good agreement between the experimental and calculated values.

Rigorous modeling of CO2 equilibrium absorption in ionic liquids

Over the past few decades, solution of high amount of carbon dioxide in ionic liquids (ILs) has been the object of extensive studies. It is believed that ILs can be applied to capture CO2 and avoiding greenhouse gas emissions into the atmosphere. In this communication, the predictive capability of the Least Square Support Vector Machine (LSSVM), Adaptive Neuro-Fuzzy Inference System (ANFIS), Multi-Layer Perceptron Artificial Neural Network (MLP-ANN), and Radial Basis Function Artificial Neural Network (RBF-ANN) has been evaluated for estimating carbon dioxide solubility in 67 different ILs as a function of the operational temperature (T), pressure (P) accompanied with the properties of ILs including the critical temperature (Tc), critical pressure (Pc) and, acentric factor (ω). In this regard, an extensive data bank containing 5368 data gathered from the literature was employed. Results obtained from the LSSVM approach indicate its satisfactory predictions than other strategies. Moreover, an outlier analysis was utilized to detect suspected data points. Obtained values of R-squared (R2), Mean Squared Error (MSE) were 0.9942 & 0.00035, 0.9135 & 0.004883, 0.9135 & 0.004883, and 0.9135 & 0.004883 for the LSSVM, ANFIS, MLP-ANN, and RBF-ANN respectively. Accordingly, the LSSVM strategy was introduced as a great tool for estimating CO2 solubility in such ionic liquids, which is easy to apply and can avoid time-consuming experimental measurement and expensive experimental apparatuses as well as complicated interpretation procedures. In addition, it can help chemists and chemical engineers to have a low parameter model with satisfactory results for the estimation of CO2 solubility in ILs.