Accelerated discovery of M 6 @g-N 4 catalysts for CO 2 electroreduction via machine learning and DFT: descriptor engineering and activity trend validation

ML combined with DFT is used to evaluate the CO 2 RR catalytic performance of M 6 @g-N 4 catalysts. The optimal RR model identifies key descriptors and screens promising Cd 6 @g-N 4 , Zn 6 @g-N 4 , Sn 6 @g-N 4 for accelerated catalyst discovery.