Premium
Accurate prediction of binding energies for two‐dimensional catalytic materials using machine learning
Author(s) -
Melisande Fischer Julia,
Hunter Michelle,
Hankel Marlies,
Searles Debra J.,
Parker Amanda J.,
Barnard Amanda S.
Publication year - 2020
Publication title -
chemcatchem
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.497
H-Index - 106
eISSN - 1867-3899
pISSN - 1867-3880
DOI - 10.1002/cctc.202000536
Subject(s) - catalysis , density functional theory , binding energy , atom (system on chip) , graphene , molecule , quantum chemical , materials science , computational chemistry , feature (linguistics) , chemical physics , nanotechnology , chemistry , biological system , computer science , physics , atomic physics , organic chemistry , linguistics , philosophy , biology , embedded system
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 R 2 =0.952 and R 2 =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.