Active learning accelerated exploration of single-atom local environments in multimetallic systems for oxygen electrocatalysis
Abstract Single-atom catalysts (SACs) with multiple active sites exhibit high activity for a wide range of sluggish reactions, but identifying optimal multimetallic SAC is challenging due to the vast design space. Here, we present a self-driving computational strategy that combines first-principles...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-10-01
|
| Series: | npj Computational Materials |
| Online Access: | https://doi.org/10.1038/s41524-024-01432-1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850181502082482176 |
|---|---|
| author | Hoje Chun Jaclyn R. Lunger Jeung Ku Kang Rafael Gómez-Bombarelli Byungchan Han |
| author_facet | Hoje Chun Jaclyn R. Lunger Jeung Ku Kang Rafael Gómez-Bombarelli Byungchan Han |
| author_sort | Hoje Chun |
| collection | DOAJ |
| description | Abstract Single-atom catalysts (SACs) with multiple active sites exhibit high activity for a wide range of sluggish reactions, but identifying optimal multimetallic SAC is challenging due to the vast design space. Here, we present a self-driving computational strategy that combines first-principles calculations and equivariant graph neural network (GNN) to explore over 30,000 binary metallic sites with varying combinations of 3d transition metals and different ligand environments for oxygen reduction and evolution reactions (ORR/OER). Active learning facilitates the investigation of the search space by balancing the exploration of unseen atomic structures with the exploitation of the active ones. The GNN learns the chemical environments to capture composition-structure-property relationships for ORR/OER activity and selectivity. The computational predictions of promising Co-Fe, Co-Co, and Co-Zn metal pairs are consistent with the state-of-the-art results of experimental measurements reported in the literature. This approach can be extended to a broader class of multi-element high entropic materials systems. |
| format | Article |
| id | doaj-art-8256ee2f7ea24ffb8ae80b39ab72729a |
| institution | OA Journals |
| issn | 2057-3960 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Computational Materials |
| spelling | doaj-art-8256ee2f7ea24ffb8ae80b39ab72729a2025-08-20T02:17:53ZengNature Portfolionpj Computational Materials2057-39602024-10-0110111010.1038/s41524-024-01432-1Active learning accelerated exploration of single-atom local environments in multimetallic systems for oxygen electrocatalysisHoje Chun0Jaclyn R. Lunger1Jeung Ku Kang2Rafael Gómez-Bombarelli3Byungchan Han4Department of Chemical and Biomolecular Engineering, Yonsei UniversityDepartment of Materials Science and Engineering, Massachusetts Institute of TechnologyDepartment of Materials Science & Engineering and NanoCentury Institute, Korea Advanced Institute of Science and TechnologyDepartment of Materials Science and Engineering, Massachusetts Institute of TechnologyDepartment of Chemical and Biomolecular Engineering, Yonsei UniversityAbstract Single-atom catalysts (SACs) with multiple active sites exhibit high activity for a wide range of sluggish reactions, but identifying optimal multimetallic SAC is challenging due to the vast design space. Here, we present a self-driving computational strategy that combines first-principles calculations and equivariant graph neural network (GNN) to explore over 30,000 binary metallic sites with varying combinations of 3d transition metals and different ligand environments for oxygen reduction and evolution reactions (ORR/OER). Active learning facilitates the investigation of the search space by balancing the exploration of unseen atomic structures with the exploitation of the active ones. The GNN learns the chemical environments to capture composition-structure-property relationships for ORR/OER activity and selectivity. The computational predictions of promising Co-Fe, Co-Co, and Co-Zn metal pairs are consistent with the state-of-the-art results of experimental measurements reported in the literature. This approach can be extended to a broader class of multi-element high entropic materials systems.https://doi.org/10.1038/s41524-024-01432-1 |
| spellingShingle | Hoje Chun Jaclyn R. Lunger Jeung Ku Kang Rafael Gómez-Bombarelli Byungchan Han Active learning accelerated exploration of single-atom local environments in multimetallic systems for oxygen electrocatalysis npj Computational Materials |
| title | Active learning accelerated exploration of single-atom local environments in multimetallic systems for oxygen electrocatalysis |
| title_full | Active learning accelerated exploration of single-atom local environments in multimetallic systems for oxygen electrocatalysis |
| title_fullStr | Active learning accelerated exploration of single-atom local environments in multimetallic systems for oxygen electrocatalysis |
| title_full_unstemmed | Active learning accelerated exploration of single-atom local environments in multimetallic systems for oxygen electrocatalysis |
| title_short | Active learning accelerated exploration of single-atom local environments in multimetallic systems for oxygen electrocatalysis |
| title_sort | active learning accelerated exploration of single atom local environments in multimetallic systems for oxygen electrocatalysis |
| url | https://doi.org/10.1038/s41524-024-01432-1 |
| work_keys_str_mv | AT hojechun activelearningacceleratedexplorationofsingleatomlocalenvironmentsinmultimetallicsystemsforoxygenelectrocatalysis AT jaclynrlunger activelearningacceleratedexplorationofsingleatomlocalenvironmentsinmultimetallicsystemsforoxygenelectrocatalysis AT jeungkukang activelearningacceleratedexplorationofsingleatomlocalenvironmentsinmultimetallicsystemsforoxygenelectrocatalysis AT rafaelgomezbombarelli activelearningacceleratedexplorationofsingleatomlocalenvironmentsinmultimetallicsystemsforoxygenelectrocatalysis AT byungchanhan activelearningacceleratedexplorationofsingleatomlocalenvironmentsinmultimetallicsystemsforoxygenelectrocatalysis |