Multiple machine learning models for prediction of CO2 solubility in potassium and sodium based amino acid salt solutions

In this work, we developed artificial intelligence-based models for prediction and correlation of CO2 solubility in amino acid solutions the purpose capture. The were used to correlate process parameters loading solvent. Indeed, loading/solubility solvent was considered as sole model’s output. studied work potassium sodium-based salt solutions. For predictions, tried three potential models, including Multi-layer Perceptron (MLP), Decision Tree (DT), AdaBoost-DT. order discover ideal hyperparameters each model, ran method multiple times find out best model. R2 scores all exceeded 0.9 after optimization confirming great capabilities models. AdaBoost-DT indicated highest Score 0.998. With an 0.98, second most accurate one, followed by MLP with 0.9.