Accurate prediction of binding energies for two-dimensional catalytic materials using machine learning

Julia Melisande Fischer, Michelle Hunter, Marlies Hankel, Debra J. Searles, Amanda J. Parker, Amanda S. Barnard*

*Corresponding author for this work

    Research output: Contribution to journalArticlepeer-review

    15 Citations (Scopus)

    Abstract

    The binding energy of small molecules on two-dimensional (2D) single atom catalysts influences their reaction efficiency and suitability for different applications. In this study, the binding energy on single metal atoms to N-doped graphene defects was predicted using random forest regression based on approximately 1700 previously generated density functional theory simulations of catalytic reactions. Three different structural feature groups containing hundreds of individual structural features were created and used to characterise the active sites. This approach was found to be accurate and reliable using either fully relaxed output structures or pre-simulation input structures, with coefficients of determination of (Formula presented.) =0.952 and (Formula presented.) =0.865, respectively. The ability to predict optimal 2D-catalysts before undertaking expensive quantum chemical calculations is an attractive basis for future research, and could be extended to other 2D-materials.

    Original languageEnglish
    Pages (from-to)5109-5120
    Number of pages12
    JournalChemCatChem
    Volume12
    Issue number20
    DOIs
    Publication statusPublished - 20 Oct 2020

    Fingerprint

    Dive into the research topics of 'Accurate prediction of binding energies for two-dimensional catalytic materials using machine learning'. Together they form a unique fingerprint.

    Cite this