Graph Neural Network-Accelerated Multitasking Genetic Algorithm for Optimizing Pd _x Ti _{1– x} H _y Surfaces under Various CO ₂ Reduction Reaction Conditions

Palladium (Pd) hydride-based catalysts have been reported to have excellent performance in the CO 2 reduction reaction (CO 2 RR) and hydrogen evolution reaction (HER). Our previous work on doped PdH and Pd alloy hydrides showed that Ti-doped and Ti-alloyed Pd hydrides could improve the performance of the CO 2 reduction reaction compared with pure Pd hydride. Compositions and chemical orderings of the surfaces with only one adsorbate under certain reaction conditions are linked to their stability, activity, and selectivity toward the CO 2 RR and HER, as shown in our previous work. In fact, various coverages, types, and mixtures of the adsorbates, as well as state variables such as temperature, pressure, applied potential, and chemical potential, could impact their stability, activity, and selectivity. However, these factors are usually fixed at common values to reduce the complexity of the structures and the complexity of the reaction conditions in most theoretical work. To address the complexities above and the huge search space, we apply a deep learning-assisted multitasking genetic algorithm to screen for Pd x Ti 1– x H y surfaces containing multiple adsorbates for CO 2 RR under different reaction conditions. The ensemble deep learning model can greatly speed up the structure relaxations and retain a high accuracy and low uncertainty of the energy and forces. The multitasking genetic algorithm simultaneously finds globally stable surface structures under each reaction condition. Finally, 23 stable structures are screened out under different reaction conditions. Among these, Pd 0.56 Ti 0.44 H 1.06 + 25%CO, Pd 0.31 Ti 0.69 H 1.25 + 50%CO, Pd 0.31 Ti 0.69 H 1.25 + 25%CO, and Pd 0.88 Ti 0.12 H 1.06 + 25%CO are found to be very active for CO 2 RR and suitable to generate syngas consisting of CO and H 2 .