Machine-Learning-Driven High-Entropy Alloy Catalyst Discovery to Circumvent the Scaling Relation for CO 2 Reduction Reaction

To achieve an equitable energy transition toward net-zero 2050 goals, the electrochemical reduction of CO 2 (CO 2 RR) to chemical feedstocks through utilizing both CO 2 and renewable energy is particularly attractive. However, the catalytic activity of CO 2 RR is limited by the scaling relation of the adsorption energies of intermediates. Circumventing the scaling relation is a potential strategy to achieve a breakthrough in catalytic activity. Herein, based on density functional theory (DFT) calculations, we designed a high-entropy alloy (HEA) system of FeCoNiCuMo with high catalytic activity for CO 2 RR. Machine learning models were developed by considering 1280 adsorption sites to predict the adsorption energies of COOH*, CO*, and CHO*. The scaling relation between the adsorption energies of COOH*, CO*, and CHO* is circumvented by the rotation of COOH* and CHO* on the designed HEA surface, resulting in the outstanding catalytic activity of CO 2 RR with the limiting potential of 0.29–0.51 V. This work not only accelerates the development of HEA catalysts but also provides an effective strategy to circumvent the scaling relation.