Modeling of ionic liquids viscosity via advanced white-box machine learning.

Ionic liquids (ILs) are more widely used within the industry than ever before, and accurate models of their physicochemical characteristics are becoming increasingly important during the process optimization. It is especially challenging to simulate the viscosity of ILs since there is no widely agreed explanation of how viscosity is determined in liquids. In this research, genetic programming (GP) and group method of data handling (GMDH) models were used as white-box machine learning approaches to predict the viscosity of pure ILs. These methods were developed based on a large open literature database of 2813 experimental viscosity values from 45 various ILs at different pressures (0.06-298.9 MPa) and temperatures (253.15-573 K). The models were developed based on five, six, and seven inputs, and it was found that all the models with seven inputs provided more accurate results, while the models with five and six inputs had acceptable accuracy and simpler formulas. Based on GMDH and GP proposed approaches, the suggested GMDH model with seven inputs gave the most exact results with an average absolute relative deviation (AARD) of 8.14% and a coefficient of determination (R2) of 0.98. The proposed techniques were compared with theoretical and empirical models available in the literature, and it was displayed that the GMDH model with seven inputs strongly outperforms the existing approaches. The leverage statistical analysis revealed that most of the experimental data were located within the applicability domains of both GMDH and GP models and were of high quality. Trend analysis also illustrated that the GMDH and GP models could follow the expected trends of viscosity with variations in pressure and temperature. In addition, the relevancy factor portrayed that the temperature had the greatest impact on the ILs viscosity. The findings of this study illustrated that the proposed models represented strong alternatives to time-consuming and costly experimental methods of ILs viscosity measurement.

Modeling liquid rate through wellhead chokes using machine learning techniques.

Precise measurement and prediction of the fluid flow rates in production wells are crucial for anticipating the production volume and hydrocarbon recovery and creating a steady and controllable flow regime in such wells. This study suggests two approaches to predict the flow rate through wellhead chokes. The first is a data-driven approach using different methods, namely: Adaptive boosting support vector regression (Adaboost-SVR), multivariate adaptive regression spline (MARS), radial basis function (RBF), and multilayer perceptron (MLP) with three algorithms: Levenberg-Marquardt (LM), bayesian-regularization (BR), and scaled conjugate gradient (SCG). The second is a developed correlation that depends on wellhead pressure (Pwh), gas-to-liquid ratio (GLR), and choke size (Dc). A dataset of 565 data points is available for model development. The performance of the two suggested approaches is compared with earlier correlations. Results revealed that the proposed models outperform the existing ones, with the Adaboost-SVR model showing the best performance with an average absolute percent relative error (AAPRE) of 5.15% and a correlation coefficient of 0.9784. Additionally, the results indicated that the developed correlation resulted in better predictions compared to the earlier ones. Furthermore, a sensitivity analysis of the input variable was also investigated in this study and revealed that the choke size variable had the most significant effect, while the Pwh and GLR showed a slight effect on the liquid rate. Eventually, the leverage approach showed that only 2.1% of the data points were in the suspicious range.

On the evaluating membrane flux of forward osmosis systems: Data assessment and advanced intelligent modeling.

As an emerging desalination technology, forward osmosis (FO) can potentially become a reliable method to help remedy the current water crisis. Introducing uncomplicated and precise models could help FO systems' optimization. This paper presents the prediction and evaluation of FO systems' membrane flux using various artificial intelligence-based models. Detailed data gathering and cleaning were emphasized because appropriate modeling requires precise inputs. Accumulating data from the original sources, followed by duplicate removal, outlier detection, and feature selection, paved the way to begin modeling. Six models were executed for the prediction task, among which two are tree-based models, two are deep learning models, and two are miscellaneous models. The calculated coefficient of determination (R2 ) of our best model (XGBoost) was 0.992. In conclusion, tree-based models (XGBoost and CatBoost) show more accurate performance than neural networks. Furthermore, in the sensitivity analysis, feed solution (FS) and draw solution (DS) concentrations showed a strong correlation with membrane flux. PRACTITIONER POINTS: The FO membrane flux was predicted using a variety of machine-learning models. Thorough data preprocessing was executed. The XGBoost model showed the best performance, with an R2 of 0.992. Tree-based models outperformed neural networks and other models.

Modeling crude oil pyrolysis process using advanced white-box and black-box machine learning techniques.

Accurate prediction of fuel deposition during crude oil pyrolysis is pivotal for sustaining the combustion front and ensuring the effectiveness of in-situ combustion enhanced oil recovery (ISC EOR). Employing 2071 experimental TGA datasets from 13 diverse crude oil samples extracted from the literature, this study sought to precisely model crude oil pyrolysis. A suite of robust machine learning techniques, encompassing three black-box approaches (Categorical Gradient Boosting-CatBoost, Gaussian Process Regression-GPR, Extreme Gradient Boosting-XGBoost), and a white-box approach (Genetic Programming-GP), was employed to estimate crude oil residue at varying temperature intervals during TGA runs. Notably, the XGBoost model emerged as the most accurate, boasting a mean absolute percentage error (MAPE) of 0.7796% and a determination coefficient (R2) of 0.9999. Subsequently, the GPR, CatBoost, and GP models demonstrated commendable performance. The GP model, while displaying slightly higher error in comparison to the black-box models, yielded acceptable results and proved suitable for swift estimation of crude oil residue during pyrolysis. Furthermore, a sensitivity analysis was conducted to reveal the varying influence of input parameters on residual crude oil during pyrolysis. Among the inputs, temperature and asphaltenes were identified as the most influential factors in the crude oil pyrolysis process. Higher temperatures and oil °API gravity were associated with a negative impact, leading to a decrease in fuel deposition. On the other hand, increased values of asphaltenes, resins, and heating rates showed a positive impact, resulting in an increase in fuel deposition. These findings underscore the importance of precise modeling for fuel deposition during crude oil pyrolysis, offering insights that can significantly benefit ISC EOR practices.

Toward empirical correlations for estimating the specific heat capacity of nanofluids utilizing GRG, GP, GEP, and GMDH.

When nanoparticles are dispersed and stabilized in a base-fluid, the resulting nanofluid undergoes considerable changes in its thermophysical properties, which can have a substantial influence on the performance of nanofluid-flow systems. With such necessity and importance, developing a set of mathematical correlations to identify these properties in various conditions can greatly eliminate costly and time-consuming experimental tests. Hence, the current study aims to develop innovative correlations for estimating the specific heat capacity of mono-nanofluids. The accurate estimation of this crucial property can result in the development of more efficient and effective thermal systems, such as heat exchangers, solar collectors, microchannel cooling systems, etc. In this regard, four powerful soft-computing techniques were considered, including Generalized Reduced Gradient (GRG), Genetic Programming (GP), Gene Expression Programming (GEP), and Group Method of Data Handling (GMDH). These techniques were implemented on 2084 experimental data-points, corresponding to ten different kinds of nanoparticles and six different kinds of base-fluids, collected from previous research sources. Eventually, four distinct correlations with high accuracy were provided, and their outputs were compared to three correlations that had previously been published by other researchers. These novel correlations are applicable to various oxide-based mono-nanofluids for a broad range of independent variable values. The superiority of newly developed correlations was proven through various statistical and graphical error analyses. The GMDH-based correlation revealed the best performance with an Average Absolute Percent Relative Error (AAPRE) of 2.4163% and a Coefficient of Determination (R2) of 0.9743. At last, a leverage statistical approach was employed to identify the GMDH technique's application domain and outlier data, and also, a sensitivity analysis was carried out to clarify the degree of dependence between input and output variables.

Estimation of the flow rate of pyrolysis gasoline, ethylene, and propylene in an industrial olefin plant using machine learning approaches.

Light olefins, as the backbone of the chemical and petrochemical industries, are produced mainly via steam cracking route. Prediction the of effects of operating variables on the product yield distribution through the mechanistic approaches is complex and requires long time. While increasing in the industrial automation and the availability of the high throughput data, the machine learning approaches have gained much attention due to the simplicity and less required computational efforts. In this study, the potential capability of four powerful machine learning models, i.e., Multilayer perceptron (MLP) neural network, adaptive boosting-support vector regression (AdaBoost-SVR), recurrent neural network (RNN), and deep belief network (DBN) was investigated to predict the product distribution of an olefin plant in industrial scale. In this regard, an extensive data set including 1184 actual data points were gathered during four successive years under various practical conditions. 24 varying independent parameters, including flow rates of different feedstock, numbers of active furnaces, and coil outlet temperatures, were chosen as the input variables of the models and the outputs were the flow rates of the main products, i.e., pyrolysis gasoline, ethylene, and propylene. The accuracy of the models was assessed by different statistical techniques. Based on the obtained results, the RNN model accurately predicted the main product flow rates with average absolute percent relative error (AAPRE) and determination coefficient (R2) values of 1.94% and 0.97, 1.29% and 0.99, 0.70% and 0.99 for pyrolysis gasoline, propylene, and ethylene, respectively. The influence of the various parameters on the products flow rate (estimated by the RNN model) was studied by the relevancy factor calculation. Accordingly, the number of furnaces in service and the flow rates of some feedstock had more positive impacts on the outputs. In addition, the effects of different operating conditions on the propylene/ethylene (P/E) ratio as a cracking severity factor were also discussed. This research proved that intelligent approaches, despite being simple and straightforward, can predict complex unit performance. Thus, they can be efficiently utilized to control and optimize different industrial-scale units.

Modeling Permeability Using Advanced White-Box Machine Learning Technique: Application to a Heterogeneous Carbonate Reservoir.

From exploration to production, the permeability of reservoir rocks is essential for various stages of all types of hydrocarbon field development. In the absence of costly reservoir rock samples, having a reliable correlation to predict rock permeability in the zone(s) of interest is crucial. To predict permeability conventionally, petrophysical rock typing is done. This method divides the reservoir into zones of similar petrophysical properties, and the permeability correlation for each zone is independently developed. The challenge of this approach is that the success depends upon the reservoir's complexity and heterogeneity and the methods and parameters used for rock typing. As a result, in the case of heterogeneous reservoirs, conventional rock typing methods and indices fail to predict the permeability accurately. The target area is a heterogeneous carbonate reservoir in southwestern Iran with a permeability range of 0.1-127.0 md. In this work, two approaches were used. First, based on permeability, porosity, the radius of pore throats at mercury saturation of 35% (r35), and connate water saturation (Swc) as inputs of K-nearest neighbors, the reservoir was classified into two petrophysical zones, and then, permeability for each zone was estimated. Due to the heterogeneous nature of the formation, the predicted permeability results needed to be more accurate. In the second part, we applied novel machine learning algorithms, modified group modeling data handling (GMDH), and genetic programming (GP) to develop one universal permeability equation for the whole reservoir of interest as a function of porosity, the radius of pore throats at mercury saturation of 35% (r35), and connate water saturation (Swc). The novelty of the current approach is that despite being universal, the models developed using GP and GMDH performed substantially better than zone-specific permeability, index-based empirical, or data-driven models used in the literature, such as FZI and Winland. The predicted permeability using GMDH and GP resulted in accurate prediction with R2 of 0.99 and 0.95, respectively, in the heterogeneous reservoir of interest. Moreover, as this study aimed to develop an explainable model, different parameter importance analyses were also applied to the developed permeability models, and r35 was found to be the most impactful feature.

Modeling of H2S solubility in ionic liquids: comparison of white-box machine learning, deep learning and ensemble learning approaches.

In the context of gas processing and carbon sequestration, an adequate understanding of the solubility of acid gases in ionic liquids (ILs) under various thermodynamic circumstances is crucial. A poisonous, combustible, and acidic gas that can cause environmental damage is hydrogen sulfide (H2S). ILs are good choices for appropriate solvents in gas separation procedures. In this work, a variety of machine learning techniques, such as white-box machine learning, deep learning, and ensemble learning, were established to determine the solubility of H2S in ILs. The white-box models are group method of data handling (GMDH) and genetic programming (GP), the deep learning approach is deep belief network (DBN) and extreme gradient boosting (XGBoost) was selected as an ensemble approach. The models were established utilizing an extensive database with 1516 data points on the H2S solubility in 37 ILs throughout an extensive pressure and temperature range. Seven input variables, including temperature (T), pressure (P), two critical variables such as temperature (Tc) and pressure (Pc), acentric factor (ω), boiling temperature (Tb), and molecular weight (Mw), were used in these models; the output was the solubility of H2S. The findings show that the XGBoost model, with statistical parameters such as an average absolute percent relative error (AAPRE) of 1.14%, root mean square error (RMSE) of 0.002, standard deviation (SD) of 0.01, and a determination coefficient (R2) of 0.99, provides more precise calculations for H2S solubility in ILs. The sensitivity assessment demonstrated that temperature and pressure had the highest negative and highest positive affect on the H2S solubility in ILs, respectively. The Taylor diagram, cumulative frequency plot, cross-plot, and error bar all demonstrated the high effectiveness, accuracy, and reality of the XGBoost approach for predicting the H2S solubility in various ILs. The leverage analysis shows that the majority of the data points are experimentally reliable and just a small number of data points are found beyond the application domain of the XGBoost paradigm. Beyond these statistical results, some chemical structure effects were evaluated. First, it was shown that the lengthening of the cation alkyl chain enhances the H2S solubility in ILs. As another chemical structure effect, it was shown that higher fluorine content in anion leads to higher solubility in ILs. These phenomena were confirmed by experimental data and the model results. Connecting solubility data to the chemical structure of ILs, the results of this study can further assist to find appropriate ILs for specialized processes (based on the process conditions) as solvents for H2S.

Modeling the solubility of light hydrocarbon gases and their mixture in brine with machine learning and equations of state.

Knowledge of the solubilities of hydrocarbon components of natural gas in pure water and aqueous electrolyte solutions is important in terms of engineering designs and environmental aspects. In the current work, six machine-learning algorithms, namely Random Forest, Extra Tree, adaptive boosting support vector regression (AdaBoost-SVR), Decision Tree, group method of data handling (GMDH), and genetic programming (GP) were proposed for estimating the solubility of pure and mixture of methane, ethane, propane, and n-butane gases in pure water and aqueous electrolyte systems. To this end, a huge database of hydrocarbon gases solubility (1836 experimental data points) was prepared over extensive ranges of operating temperature (273-637 K) and pressure (0.051-113.27 MPa). Two different approaches including eight and five inputs were adopted for modeling. Moreover, three famous equations of state (EOSs), namely Peng-Robinson (PR), Valderrama modification of the Patel-Teja (VPT), and Soave-Redlich-Kwong (SRK) were used in comparison with machine-learning models. The AdaBoost-SVR models developed with eight and five inputs outperform the other models proposed in this study, EOSs, and available intelligence models in predicting the solubility of mixtures or/and pure hydrocarbon gases in pure water and aqueous electrolyte systems up to high-pressure and high-temperature conditions having average absolute relative error values of 10.65% and 12.02%, respectively, along with determination coefficient of 0.9999. Among the EOSs, VPT, SRK, and PR were ranked in terms of good predictions, respectively. Also, the two mathematical correlations developed with GP and GMDH had satisfactory results and can provide accurate and quick estimates. According to sensitivity analysis, the temperature and pressure had the greatest effect on hydrocarbon gases' solubility. Additionally, increasing the ionic strength of the solution and the pseudo-critical temperature of the gas mixture decreases the solubilities of hydrocarbon gases in aqueous electrolyte systems. Eventually, the Leverage approach has revealed the validity of the hydrocarbon solubility databank and the high credit of the AdaBoost-SVR models in estimating the solubilities of hydrocarbon gases in aqueous solutions.

Solubility of gaseous hydrocarbons in ionic liquids using equations of state and machine learning approaches.

Ionic liquids (ILs) have emerged as suitable options for gas storage applications over the past decade. Consequently, accurate prediction of gas solubility in ILs is crucial for their application in the industry. In this study, four intelligent techniques including Extreme Learning Machine (ELM), Deep Belief Network (DBN), Multivariate Adaptive Regression Splines (MARS), and Boosting-Support Vector Regression (Boost-SVR) have been proposed to estimate the solubility of some gaseous hydrocarbons in ILs based on two distinct methods. In the first method, the thermodynamic properties of hydrocarbons and ILs were used as input parameters, while in the second method, the chemical structure of ILs and hydrocarbons along with temperature and pressure were used. The results show that in the first method, the DBN model with root mean square error (RMSE) and coefficient of determination (R2) values of 0.0054 and 0.9961, respectively, and in the second method, the DBN model with RMSE and R2 values of 0.0065 and 0.9943, respectively, have the most accurate predictions. To evaluate the performance of intelligent models, the obtained results were compared with previous studies and equations of the state including Peng-Robinson (PR), Soave-Redlich-Kwong (SRK), Redlich-Kwong (RK), and Zudkevitch-Joffe (ZJ). Findings show that intelligent models have high accuracy compared to equations of state. Finally, the investigation of the effect of different factors such as alkyl chain length, type of anion and cation, pressure, temperature, and type of hydrocarbon on the solubility of gaseous hydrocarbons in ILs shows that pressure and temperature have a direct and inverse effect on increasing the solubility of gaseous hydrocarbons in ILs, respectively. Also, the evaluation of the effect of hydrocarbon type shows that increasing the molecular weight of hydrocarbons increases the solubility of gaseous hydrocarbons in ILs.

Estimation of tetracycline antibiotic photodegradation from wastewater by heterogeneous metal-organic frameworks photocatalysts.

In this work, the potential ability of various modern and powerful machine learning methods such as Categorical Boosting (CatBoost), Light Gradient Boosting Machine (LightGBM), Extreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), Gradient-Boosted Decision Trees (GBDT), Extra Tree (ET), Decision Trees (DT), and Random Forest (RF) were investigated to estimate tetracycline (TC) photodegradation from wastewater by 10 different metal-organic frameworks (MOFs). A comprehensive databank was gathered, including 374 data points from the photodegradation percentage of MOFs in various practical conditions. The inputs of the employed models were chosen as catalyst dosage, antibiotic concentration, Illumination time, solution pH, and specific surface area and pore volume of the investigated MOFs, and the output was TC degradation efficiency. Different statistical criteria were calculated for the validation of the developed models. Average absolute percent relative error (AAPRE) and standard deviation error (STD) values of 1.19% and 0.0431, 3.07% and 0.0628, 2.88% and 0.0751, 2.86% and 0.1304, 8.73% and 0.2751, 4.24% and 0.1024, 2.83% and 0.0934, and 11.56% and 0.4459 were obtained for CatBoost, LightGBM, XGBoost, AdaBoost, GBDT, ET, DT, and RF approaches, respectively. Among all implemented models, the CatBoost was found to be the most trustable model. Moreover, this model followed the expected trends of the TC degradation process with variation of catalyst dosage, initial TC concentration, and reaction pH. The developed CatBoost model predicted the removal of TC by MOFs accurately, which proved the capability of this approach in solving complex problems with numerous data points and its straightforwardness and cost-effectiveness for environmental applications.

Modeling of CO2 adsorption capacity by porous metal organic frameworks using advanced decision tree-based models.

In recent years, metal organic frameworks (MOFs) have been distinguished as a very promising and efficient group of materials which can be used in carbon capture and storage (CCS) projects. In the present study, the potential ability of modern and powerful decision tree-based methods such as Categorical Boosting (CatBoost), Light Gradient Boosting Machine (LightGBM), Extreme Gradient Boosting (XGBoost), and Random Forest (RF) was investigated to predict carbon dioxide adsorption by 19 different MOFs. Reviewing the literature, a comprehensive databank was gathered including 1191 data points related to the adsorption capacity of different MOFs in various conditions. The inputs of the implemented models were selected as temperature (K), pressure (bar), specific surface area (m2/g) and pore volume (cm3/g) of the MOFs and the output was CO2 uptake capacity (mmol/g). Root mean square error (RMSE) values of 0.5682, 1.5712, 1.0853, and 1.9667 were obtained for XGBoost, CatBoost, LightGBM, and RF models, respectively. The sensitivity analysis showed that among all investigated parameters, only the temperature negatively impacts the CO2 adsorption capacity and the pressure and specific surface area of the MOFs had the most significant effects. Among all implemented models, the XGBoost was found to be the most trustable model. Moreover, this model showed well-fitting with experimental data in comparison with different isotherm models. The accurate prediction of CO2 adsorption capacity by MOFs using the XGBoost approach confirmed that it is capable of handling a wide range of data, cost-efficient and straightforward to apply in environmental applications.