Utilizing molecular simulation, ideal adsorbed solution theory and ensemble learning algorithms to investigate adsorption and separation of sulfides on amorphous nanoporous materials

Using grand canonical Monte Carlo method, we investigated the adsorption of pure H 2 S and SO 2 gases on amorphous materials, and the separation of CH 4 -H 2 S and CO 2 -SO 2 mixtures. At 303 K, the optimal adsorbent for both gases was found to be HCP-Colina-id016, with 16 mmol/g. For CH 4 -H 2 S mixture, despite aCarbon-Marks-id002 exhibiting the highest selectivity (approximately 80), the H 2 S adsorption was low (around 1 mmol/g), while Kerogen-Coasne-id013 demonstrated a high H 2 S adsorption of 12 mmol/g with a selectivity of 20. In the case of CO 2 -SO 2 , HCP-Colina-id018 exhibited a SO 2 selectivity exceeding 30, with a high SO 2 adsorption of 12 mmol/g. The Ideal Adsorbed Solution Theory underestimated the adsorption and selectivity of both mixtures, particularly evident in CO 2 -SO 2 . Molecular simulations revealed that, for the CO 2 -SO 2 system, CO 2 underwent condensation, resulting in a sudden drop in the SO 2 adsorption isotherm. However, IAST accurately predicted this abrupt change. Based on the adsorption data obtained from molecular simulations, we compared the predictive performance of four ensemble learning algorithms, namely Random Forest (RF), Gradient Boosted Decision Trees (GBDT), Extreme Gradient Boosting (XGBoost), and CatBoost, for H 2 S and SO 2 pure gases in amorphous porous materials. The rankings were observed to be XGBoost > GBDT > RF > CatBoost. • Optimal Adsorbent: HCP-Colina-id016 exhibits high capacity for pure H 2 S and SO 2 gases. • Algorithm Ranking: XGBoost outperforms GBDT, RF, and CatBoost in predicting H 2 S and SO 2 adsorption. • Kerogen-Coasne-id013 effectively adsorbs H 2 S in CH 4 -H 2 S mixture. • HCP-Colina-id018 shows high SO 2 selectivity and adsorption in CO 2 -SO 2 mixture. • Ideal Adsorbed Solution Theory accurately predicts abrupt changes in CO 2 -SO 2 system.