Prediction of CO2 solubility in aqueous amine solutions using machine learning method

Abstract

In this study, a quantitative structure–property relationship (QSPR) model has been designed based on machine learning (ML) to offer a new method to accurately predict carbon dioxide (CO2) solubility in aqueous amine solutions. Molecular descriptors are used to denote representative features of the amine molecular structure supplemented with amine solution concentration, CO2 partial pressure, and temperature as inputs to the model. The coefficient of determination (R2) of the well-trained ML model reaches 0.971, and the average absolute deviation (AAD) of independent experimental validation is 4.785 %, effectively demonstrating the model’s reliability and generalization performance. Finally, SHapley Additive exPlanations (SHAP) is adopted to reveal the contribution of different features to the model predictions, making the model more transparent and interpretable. Overall work provides a novel, low-cost, efficient method to predict equilibrium CO2 solubility in aqueous amine solution and offers a new perspective in developing advanced amine for CO2 capture.