Data?Driven High?Throughput Rational Design of Double?Atom Catalysts for Oxygen Evolution and Reduction

Surging interests exist in double-atom catalysts (DACs), which not only inherit the advantages of single-atom (SACs) (e.g., ultimate atomic utilization, high activity, and selectivity) but also overcome drawbacks SACs low loading isolated active site). The design DACs, however, remains cost-prohibitive for both experimental computational studies, due to their huge space. Herein, by means density functional theory (DFT) topological information-based machine-learning (ML) algorithms, we present a data-driven high-throughput principle evaluate stability activity 16 767 DACs oxygen evolution (OER) reduction (ORR) reactions. rational reveals 511 types with OER superior IrO2 (110), 855 ORR Pt (111), 248 bifunctional catalytic performance ORR. An intrinsic descriptor is revealed correlate DAC electronic structures its bonding carbon surface structure. This approach yields remarkable prediction precision (>0.926 R-squared) enables notable 144 000-fold screening time compared pure DFT calculations, holding promise drastically accelerate high-performance DACs.