A1 Journal article (refereed)
Graphs and Kernelized Learning Applied to Interactions of Hydrogen with Doped Gold Nanoparticle Electrocatalysts (2023)
Pihlajamäki, A., Malola, S., Kärkkäinen, T., & Häkkinen, H. (2023). Graphs and Kernelized Learning Applied to Interactions of Hydrogen with Doped Gold Nanoparticle Electrocatalysts. Journal of Physical Chemistry C, 127(29), 14211-14221. https://doi.org/10.1021/acs.jpcc.3c02539
JYU authors or editors
Publication details
All authors or editors: Pihlajamäki, Antti; Malola, Sami; Kärkkäinen, Tommi; Häkkinen, Hannu
Journal or series: Journal of Physical Chemistry C
ISSN: 1932-7447
eISSN: 1932-7455
Publication year: 2023
Publication date: 18/07/2023
Volume: 127
Issue number: 29
Pages range: 14211-14221
Publisher: American Chemical Society
Publication country: United States
Publication language: English
DOI: https://doi.org/10.1021/acs.jpcc.3c02539
Research data link: https://doi.org/10.17011/jyx/dataset/87521
Publication open access: Openly available
Publication channel open access: Partially open access channel
Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/88949
Additional information: Published as part of The Journal of Physical Chemistry C virtual special issue “Machine Learning in Physical Chemistry, Volume 2".
Abstract
Understanding hydrogen adsorption on metal nanoparticles is a key prerequisite for designing efficient electrocatalysts for water splitting and the hydrogen evolution reaction. However, this seemingly simple elementary reaction step is affected by several factors arising from the chemical environment at the catalyst, and deciphering the most important contributions to optimal interactions requires numerically heavy electronic structure calculations. Here, we combine graph-based representations of the local atomic environment of hydrogen in copper- and palladium-doped 25-atom gold nanoparticles with several kernel-based machine learning (ML) methods to predict the interaction energy between hydrogen and the nanoparticle catalyst. We demonstrate that simple distance-based kernel models are able to predict the interaction energy within 0.1 eV when trained by reference data from state-of-the-art density functional theory calculations. Analyzing the model performance with respect to attributes of the hydrogen node highlights the locality of hydrogen adsorption. This implies the viability of combining graphs with kernel-based ML models for studying hydrogen chemisorption in complex environment data efficiently.
Keywords: machine learning; adsorption; gold; hydrogen; water; nanoparticles
Free keywords: interaction energies
Contributing organizations
Related projects
- High performing machine learning for novel catalyst design
- Häkkinen, Hannu
- Research Council of Finland
- High performing machine learning for novel catalyst design
- Kärkkäinen, Tommi
- Research Council of Finland
Ministry reporting: Yes
Reporting Year: 2023
Preliminary JUFO rating: 2
- Nanoscience Center (Department of Physics PHYS, JYFL) (Faculty of Mathematics and Science) (Department of Chemistry CHEM) (Department of Biological and Environmental Science BIOENV) NSC
- Engineering (Faculty of Information Technology IT) OHTE; Formerly Software and Communications Engineering
- Human and Machine based Intelligence in Learning (Faculty of Information Technology IT) HUMBLE