ML-driven models for predicting CO2 uptake in metal–organic frameworks (MOFs)

This study advances the discourse on the application of machine learning (ML) algorithms for the predictive analysis of CO₂ uptake in metal–organic frameworks (MOFs), with a nuanced focus on the CATBoost model's capability to navigate the complexities inherent in MOFs' heterogeneous landscape. Building upon and extending the comparative analysis, our investigation underscores the CATBoost model's remarkable prediction robustness, characterized by a significant reduction in root mean square error (RMSE) and an enhanced R-squared (R²) value, thereby affirming its superior accuracy and reliability in forecasting CO₂ adsorption. A pivotal aspect of our research is the integration of SHapley Additive exPlanations (SHAP) values for a detailed assessment of feature importance, which not only corroborated ‘pressure’ and ‘surface area’ as pivotal determinants of CO₂ uptake but also illuminated the model's advanced analytical capabilities in handling categorical features and mitigating overfitting, even within a dataset marked by intricate and non-linear patterns. Our quantitative and conceptual analysis, showcasing up to a 15% improvement in RMSE over previous models, reveals the CATBoost model's unparalleled efficiency in discerning the multifaceted interplay of factors influencing CO₂ adsorption. This is crucial for the strategic engineering of MOFs with optimized properties. Beyond ‘pressure’ and ‘surface area’, our SHAP analysis highlighted other descriptors with substantial values, elucidating their contributions to CO₂ uptake and providing invaluable insights for the MOF design process.