Data-driven discovery of electrocatalysts for CO<sub>2</sub> reduction using active motifs-based machine learning.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 37952012.
- Also identified by DOI 10.1038/s41467-023-43118-0 and PMC identifier 10640609.
- Licence recorded as CC BY.
- The licence permits redistribution, so the abstract is shown in full and the full text is available from the publisher.
Abstract
The electrochemical carbon dioxide reduction reaction (CO<sub>2</sub>RR) is an attractive approach for mitigating CO<sub>2</sub> emissions and generating value-added products. Consequently, discovery of promising CO<sub>2</sub>RR catalysts has become a crucial task, and machine learning (ML) has been utilized to accelerate catalyst discovery. However, current ML approaches are limited to exploring narrow chemical spaces and provide only fragmentary catalytic activity, even though CO<sub>2</sub>RR produces various chemicals. Here, by merging pre-developed ML model and a CO<sub>2</sub>RR selectivity map, we establish high-throughput virtual screening strategy to suggest active and selective catalysts for CO<sub>2</sub>RR without being limited to a database. Further, this strategy can provide guidance on stoichiometry and morphology of the catalyst to researchers. We predict the activity and selectivity of 465 metallic catalysts toward four expected reaction products. During this process, we discover previously unreported and promising behavior of Cu-Ga and Cu-Pd alloys. These findings are then validated through experimental methods.