Machine Learning-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 predictive prowess, 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 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 nuanced contributions to CO2 uptake and providing invaluable insights for the MOF design process. Through this work, we aim to foster a deeper understanding and application of ML algorithms in environmental sustainability, thereby building upon the foundational research of Abdi et al. and pushing the boundaries of machine learning applications in the field.