Interpretable design of Ir-free trimetallic electrocatalysts for ammonia oxidation with graph neural networks.
Hemanth Somarajan PillaiYi LiShih-Han WangNoushin OmidvarQingmin MuLuke E K AchenieFrank Abild-PedersenJuan YangGang WuHongliang XinPublished in: Nature communications (2023)
The electrochemical ammonia oxidation to dinitrogen as a means for energy and environmental applications is a key technology toward the realization of a sustainable nitrogen cycle. The state-of-the-art metal catalysts including Pt and its bimetallics with Ir show promising activity, albeit suffering from high overpotentials for appreciable current densities and the soaring price of precious metals. Herein, the immense design space of ternary Pt alloy nanostructures is explored by graph neural networks trained on ab initio data for concurrently predicting site reactivity, surface stability, and catalyst synthesizability descriptors. Among a few Ir-free candidates that emerge from the active learning workflow, Pt 3 Ru-M (M: Fe, Co, or Ni) alloys were successfully synthesized and experimentally verified to be more active toward ammonia oxidation than Pt, Pt 3 Ir, and Pt 3 Ru. More importantly, feature attribution analyses using the machine-learned representation of site motifs provide fundamental insights into chemical bonding at metal surfaces and shed light on design strategies for high-performance catalytic systems beyond the d-band center metric of binding sites.
Keyphrases
- neural network
- room temperature
- hydrogen peroxide
- visible light
- metal organic framework
- deep learning
- gold nanoparticles
- electronic health record
- ionic liquid
- anaerobic digestion
- reduced graphene oxide
- convolutional neural network
- high resolution
- electron transfer
- resistance training
- biofilm formation
- cystic fibrosis
- drinking water
- artificial intelligence
- aqueous solution
- amino acid