Applying Active Learning to the Screening of Molecular Oxygen Evolution Catalysts

The oxygen evolution reaction (OER) can enable green hydrogen production; however, the state-of-the-art catalysts for this reaction are composed of prohibitively expensive materials. In addition, cheap catalysts have associated overpotentials that render the reaction inefficient. This impels the sea...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Michael John Craig, Max García-Melchor
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	water splitting oxygen evolution reaction machine learning catalyst design scaling relations Organic chemistry QD241-441
Acceso en línea:	https://doaj.org/article/fe79bb7b23244080b71098502a9dc5c6
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:fe79bb7b23244080b71098502a9dc5c6
record_format	dspace
spelling	oai:doaj.org-article:fe79bb7b23244080b71098502a9dc5c62021-11-11T18:23:24ZApplying Active Learning to the Screening of Molecular Oxygen Evolution Catalysts10.3390/molecules262163621420-3049https://doaj.org/article/fe79bb7b23244080b71098502a9dc5c62021-10-01T00:00:00Zhttps://www.mdpi.com/1420-3049/26/21/6362https://doaj.org/toc/1420-3049The oxygen evolution reaction (OER) can enable green hydrogen production; however, the state-of-the-art catalysts for this reaction are composed of prohibitively expensive materials. In addition, cheap catalysts have associated overpotentials that render the reaction inefficient. This impels the search to discover novel catalysts for this reaction computationally. In this communication, we present machine learning algorithms to enhance the hypothetical screening of molecular OER catalysts. By predicting calculated binding energies using Gaussian process regression (GPR) models and applying active learning schemes, we provide evidence that our algorithm can improve computational efficiency by guiding simulations towards candidates with promising OER descriptor values. Furthermore, we derive an acquisition function that, when maximized, can identify catalysts that can exhibit theoretical overpotentials that circumvent the constraints imposed by linear scaling relations by attempting to enforce a specific mechanism. Finally, we provide a brief perspective on the appropriate sets of molecules to consider when screening complexes that could be stable and active for this reaction.Michael John CraigMax García-MelchorMDPI AGarticlewater splittingoxygen evolution reactionmachine learningcatalyst designscaling relationsOrganic chemistryQD241-441ENMolecules, Vol 26, Iss 6362, p 6362 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	water splitting oxygen evolution reaction machine learning catalyst design scaling relations Organic chemistry QD241-441
spellingShingle	water splitting oxygen evolution reaction machine learning catalyst design scaling relations Organic chemistry QD241-441 Michael John Craig Max García-Melchor Applying Active Learning to the Screening of Molecular Oxygen Evolution Catalysts
description	The oxygen evolution reaction (OER) can enable green hydrogen production; however, the state-of-the-art catalysts for this reaction are composed of prohibitively expensive materials. In addition, cheap catalysts have associated overpotentials that render the reaction inefficient. This impels the search to discover novel catalysts for this reaction computationally. In this communication, we present machine learning algorithms to enhance the hypothetical screening of molecular OER catalysts. By predicting calculated binding energies using Gaussian process regression (GPR) models and applying active learning schemes, we provide evidence that our algorithm can improve computational efficiency by guiding simulations towards candidates with promising OER descriptor values. Furthermore, we derive an acquisition function that, when maximized, can identify catalysts that can exhibit theoretical overpotentials that circumvent the constraints imposed by linear scaling relations by attempting to enforce a specific mechanism. Finally, we provide a brief perspective on the appropriate sets of molecules to consider when screening complexes that could be stable and active for this reaction.
format	article
author	Michael John Craig Max García-Melchor
author_facet	Michael John Craig Max García-Melchor
author_sort	Michael John Craig
title	Applying Active Learning to the Screening of Molecular Oxygen Evolution Catalysts
title_short	Applying Active Learning to the Screening of Molecular Oxygen Evolution Catalysts
title_full	Applying Active Learning to the Screening of Molecular Oxygen Evolution Catalysts
title_fullStr	Applying Active Learning to the Screening of Molecular Oxygen Evolution Catalysts
title_full_unstemmed	Applying Active Learning to the Screening of Molecular Oxygen Evolution Catalysts
title_sort	applying active learning to the screening of molecular oxygen evolution catalysts
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/fe79bb7b23244080b71098502a9dc5c6
work_keys_str_mv	AT michaeljohncraig applyingactivelearningtothescreeningofmolecularoxygenevolutioncatalysts AT maxgarciamelchor applyingactivelearningtothescreeningofmolecularoxygenevolutioncatalysts
_version_	1718431861018984448

Applying Active Learning to the Screening of Molecular Oxygen Evolution Catalysts

Ejemplares similares