An interpretable surrogate model for H2S solubility forecasting in ionic liquids based on machine learning

Abstract

Here we investigated four different ML-based models, i.e., gaussian process regression (GPR), extreme gradient boosting (i.e., XGBoost), random forest (RF), and support vector machine (SVM), for predicting the solubility of H₂S in various ionic liquids (ILs). The dataset was divided into training and testing sets in an 80:20 ratio while the model performance for all models were evaluated using the coefficient of determination (R²), mean absolute error (MAE), and root mean square error (RMSE). Overall, all models effectively predicted H₂S solubility, albeit with varying degrees of performance. The GPR provides the best performance, with R² of 0.9918, MAE of 0.0090, and RMSE of 0.0147. Following this is the XGBoost model with an R² value of 0.9827, MAE of 0.0155, and RMSE of 0.0213. The RF model displayed slightly lower performance, with an R² value of 0.9395, MAE of 0.0261, and RMSE of 0.0398 while the lowest performance was demonstrated by the SVM model, which gave an R² value of 0.9036, MAE of 0.0402, and RMSE of 0.0508. We used SHAP analysis, identified pressure, temperature, Estate_VSA3, Estate_VSA5, and MinEStateIndex as the top five dominant input features in our model interpretation. In a nutshell, this work presents new insights into the molecular characteristics that affect the solubility of H₂S in ILs, paving future research path in this field.