Modelling of MOF-based CO2 capture using Categorical Boosting (CatBoost), Light Gradient Boosting Machine (LightGBM), Extreme Gradient Boosting (XGBoost), and Random Forest (RF)

https://www.nature.com/articles/s41598-021-04168-w

“With increasing pressure, the saturation process of the MOFs’ pores will be facilitated according to the room-temperature isotherms. From these isotherms, it can be perceived that the uptake capacity of each MOF is qualitatively related to its surface area and among all types of assessed MOFs in the current study, the MOF-177, BeBTB, MOF-5 and PCN-11 showed outstanding and considerable CO₂ adsorption capacity. As the pore sizes are greater and more efficient, the contribution of the pressure regime appearance gets more influence on the CO₂ uptake capacity^69,70. Comparison among all mentioned porous materials, the MOF-177 had a maximum capacity of 33.5 mmol/g, because of its high surface area (4508 m²/g) nearly twice of IRMOF-11. Figure 6a illustrates a detailed representation of uptake capacities in different pressures at 298 K for the investigated MOFs. Also, Fig. 6b draws a comparison between the CO₂ adsorption efficiency of MOF-177 at 313 K and a range of other MOFs. It has also been discovered that the amount of CO₂ adsorption on the MOF structure is directly related to the surface area and the polarity of the surface. As these features are higher, more CO₂ will be absorbed and even in low pressures a high adsorption will be achieved using some MOFs like Cu-BTTri and Mg₂(dobdc). Moreover, operating at a high pressure significantly affects the CO₂ adsorption capacity.”

“Figure 6 Comparison between experimental and predicted CO₂ uptake capacities by XGBoost model for the investigated MOFs at different temperatures: (a) 298 K and (b) 313 K.”

“Ability of various models in prediction of CO₂ adsorption capacity at low pressure ranges is shown in Fig. S6, in which the models were utilized to estimate CO₂ removal efficiency of Mg₂(dobdc) at 313 K. Among all models, the XGBoost and CatBoost were found to be the most trustable models. Moreover, this model can be successfully compared with different isotherm models. As illustrated in Fig. 8 and Fig. S7, XGBoost as the best model along with Langmuir, Freundlich, Dubinin-Radushkevitch (D-R) and Sips isotherm models were fitted with experimental data for PCN-11 and Mg-MOF-74. Figures show that both Langmuir and XGBoost models predicted the results well. Langmuir isotherm model showed well-fitting with correlation coefficient of 0.999 and 0.980 for PCN-11 and Mg-MOF-174, respectively, but totally the XGBoost models represented better fitting correlation with R² values of 0.998 for both MOFs.”