Integrating Machine Learning and DFT Descriptors for Screening Dual Metal‐Site Catalysts for CO 2 Reduction to C 2 Products

ABSTRACT The electrochemical reduction of CO 2 (CO 2 RR) offers a sustainable route to generate multi‐carbon products (C 2 ), but achieving high activity and selectivity remains a challenge. Dual metal‐site catalysts (DMSCs), composed of two adjacent metal sites, provide unique active centers that enable simultaneous CO adsorption, a key step for C─C coupling. Here, we systematically investigated 156 DMSCs supported on nitrogen‐doped carbon to identify promising candidates for CO 2 RR. Stability screening revealed that 8 DMSCs are unstable, while hydrogen adsorption calculations excluded 6 additional systems due to strong * H binding. Among the remaining catalysts, 33 DMSCs exhibit CO dimerization energies (∆G *CO dimer‐2*CO ) below 0.75 eV, indicating favorable activity toward C 2 products. To explain these trends, we performed a linear correlation analysis of CO dimerization energy against 71 electronic parameters, which revealed that the occupancy of the dz 2 ↓ orbital (denoted O‐dz 2 ↓) exhibits the highest correlation (R 2 = 0.69). This suggested that combinations of electronic parameters could further improve the correlation and accurately predict CO 2 RR toward C 2 products. To achieve this, multiple machine learning models were trained, with the random forest regressor (RFR) achieving superior performance (R 2 = 0.98 for training and 0.96 for testing), demonstrating its suitability for predicting CO dimerization energy. Furthermore, the overpotential for C 2 production of the 33 DMSCs was correlated with electronic descriptors, revealing that O‐dz 2 ↓ exhibited the highest correlation (R 2 = 0.87), attributable to the substantial population of dz 2 ↓ states near the Fermi level (E F ), thereby underscoring its significance as a key descriptor. Overall, we emphasize the importance of using a multi‐descriptor predictive model to accurately estimate CO dimerization energies, and we identify key electronic parameters of DMSCs that can predict the overpotential for C 2 products. These insights offer a valuable framework for the rapid screening of low‐cost materials with high selectivity toward C 2 products.