Machine Learning-Assisted Exploration of Chemical Space of MOF-5 Analogs for Enhanced C2H6/C2H4 Separation

Adsorptive separation using C2H6-selective adsorbents can produce high-purity C2H4 directly, making it an energy-efficient separation method with the potential to replace cryogenic distillation. Although many C2H6-selective MOFs have been reported, developing MOFs with both large C2H6 adsorption capacity and high C2H6/C2H4 selectivity remains challenging. Herein, we present a machine learning-assisted molecular simulation strategy to explore the C2H6/C2H4 separation capability of pcu-MOFs isoreticular to MOF-5. The eXtreme gradient boosting (XGBoost) algorithm showed high accuracy in predicting the C2H6/C2H4 selectivity and C2H6 uptake, where Henry coefficient ratio (S0) and Henry coefficient of C2H6 (K(C2H6)) were identified as key factors. We further synthesized the top-performing MOF termed A-66 and experimentally verified its large C2H6 adsorption capacity and excellent C2H6/C2H4 separation performance. This work provides a valuable strategy for exploring the chemical space of MOF-5 analogs and identifying promising candidates for the efficient purification of C2H4 from C2H6/C2H4 mixtures.