Modeling CO₂ Solubility in Water at High Pressure and Temperature Conditions

Abstract

CO 2 dissolution in water at different temperature and pressure conditions is of essential interest for various environmental, geochemical, and thermodynamic related problems. The topic is of special interest in studies of CO 2 geological sequestration in brine-bearing aquifers. In this Article, four powerful machine learning (ML) techniquesRadial Basis Function Neural Network (RBFNN), Multilayer Perceptron (MLP), Least-Squares Support Vector Machine (LSSVM), and Gene Expression Programming (GEP)are implemented to develop economical, rapid, and reliable models to predict the solubility of CO 2 in water. To expand the prediction capability of the ML approaches, their control parameters are optimized by various techniques. To this end, four back-propagation algorithms are applied in the MLP learning phase, while Particle Swarm Optimization (PSO), Differential Evolution (DE), Genetic Algorithm (GA), and Firefly Algorithm (FFA) are used to optimize the RBFNN and LSSVM control parameters. A wide-ranged database including temperature and pressure as inputs and CO 2 solubility in pure water as output is utilized to develop the models, which are then compared with each other and also against existing models. The results demonstrate that the prediction performance of the proposed models is quite satisfactory. In addition, the comparison results reveal that the LSSVM-FFA is the best paradigm to estimate the solubility of CO 2 in pure water, as it outperforms the other proposed ML techniques as well as prior models. The overall RMSE and R 2 values for LSSVM-FFA are 0.3261 and 0.9930, respectively.

Design of a Neuro‐Based Computing Paradigm for Simulation of Industrial Olefin Plants

“…3–9. The cross plot is a well‐known visual method to evaluate the predictive performance of different artificial intelligent techniques 34–36. The concentration of the symbols of these figures around the diagonal line confirmed that the proposed MLP model is an appropriate tool for estimating the tonnage of the main products of the olefin unit.…”

Modeling of carbon dioxide solubility in ionic liquids based on group method of data handling

“…On the country, CO 2 solubility in ILs represents an opposite behavior against critical pressure. In other words, CO 2 solubility lowers by increasing critical pressure (Hemmati-Sarapardeh et al, 2020;Menad et al, 2019;Mokarizadeh et al, 2020). In order to compare the experimental and predicted result values and check the physical validity of the proposed model, variation of CO 2 solubility in one ionic liquid ([bmim][Tf2N]) against input parameters of pressure and temperature was investigated in Figure 8.…”

Modeling solubility of CO2–N2 gas mixtures in aqueous electrolyte systems using artificial intelligence techniques and equations of state

“…Average absolute relative error and root mean square error (RMSE) values of their proposed CSA-LSSVM model were 10.71% and 0.0011, respectively. Hemmati-Sarapardeh et al 43 investigated the solubility of CO 2 in water at high pressures and temperatures using four powerful machine learning techniques. In this study, Multilayer Perceptron (MLP), Radial Basis Function (RBF), Least-Squares Support Vector Machine (LSSVM), and Gene Expression Programming (GEP) models were developed using temperature and pressure as input data to estimate the solubility of CO 2 in water.…”