Determining solubility of CO2 in aqueous brine systems via hybrid smart strategies

In this study, Radial Basis Function Neural Network (RBF-NN) and Least Square Support Vector Machine (LSSVM) were established for estimation of equilibrium CO2-water/brine solubility as a function of salt molecular weight, temperature, salt molality and pressure. A reliable database was gathered from the open source literatures, and was split into two groups of testing and training subsets. Optimal structure of the proposed RBF-NN technique and the tuning coefficients of LSSVM model were determined by Cuckoo Optimisation Algorithm (COA). Accordingly, the proposed approaches here can accurately prognosticate CO2 solubility with determination factor (R²) of 0.9966 and average absolute relative deviation (AARD%) of 2.5885% for COA-LSSVM, and AARD% = 3.8832% and R² = 0.9962 for COA-RBF-NN; therefore, the proposed COA-LSSVM gives more accurate results for estimating CO2 solubility. Williams' outliers detection technique reveals that less than 3% of database are outliers. Salt molality is the most affecting variable based on sensitivity analysis.