Solubility predictions through LSBoost for supercritical carbon dioxide in ionic liquids
Abstract
The solubility of supercritical carbon dioxide in ionic liquids (ILs) is a key parameter for designing chemical processes in a biphasic system. Experimental measurements to determine the molar solubility requires specially-designed apparatus, which may be resource-intensive. Alternatively, predictive models can facilitate the estimation of the solubility by modeling via computational intelligence approaches. In the current work, we develop the least-squares boosting model to predict the solubility of supercritical carbon dioxide in 24 ionic liquids by using critical properties of ILs and biphasic system parameters as descriptors. The model is highly accurate, stable, and promising as a fast, robust, and low-cost tool for solubility estimations.