Challenges and Opportunities of Pretrained Machine Learning Interatomic Potentials in Heterogeneous Catalysis

The design of catalysts gets its fundamental rationale from accurate and efficient modeling of reactivity on surfaces and materials. To reach this detailed atomistic understanding, density functional theory (DFT) has been the key computational technique. However, the emergence of machine learning in...

Descripción completa

Detalles Bibliográficos
Autores: Loveday, Oliver, Kaźmierczak, Kamila, López, Núria
Tipo de recurso: artículo
Fecha de publicación:2026
País:España
Institución:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
Repositorio:Recercat. Dipósit de la Recerca de Catalunya
OAI Identifier:oai:recercat.cat:2072/489264
Acceso en línea:https://hdl.handle.net/2072/489264
https://doi.org/10.1021/acscatal.5c08945
Access Level:acceso abierto
Palabra clave:Química
54
id ES_79d4b3fdad03cefcdb4f3ff171e541c2
oai_identifier_str oai:recercat.cat:2072/489264
network_acronym_str ES
network_name_str España
repository_id_str
spelling Challenges and Opportunities of Pretrained Machine Learning Interatomic Potentials in Heterogeneous CatalysisLoveday, OliverKaźmierczak, KamilaLópez, NúriaQuímica54The design of catalysts gets its fundamental rationale from accurate and efficient modeling of reactivity on surfaces and materials. To reach this detailed atomistic understanding, density functional theory (DFT) has been the key computational technique. However, the emergence of machine learning interatomic potentials (MLIPs) marks a significant paradigm shift, offering the potential to match DFT accuracy at a drastically reduced computational cost. This perspective provides an overview of state-of-the-art MLIPs for heterogeneous catalysis as “out-of-the-box” tools. We summarize the different families of MLIPs and their training processes and then apply these pretrained models to heterogeneous catalysis problems. Furthermore, we critically address the challenges of model transferability and integration in unified frameworks, underscoring the necessity for standardized protocols to benchmark performance across different architectures. Finally, we assess the capacity of pretrained models to democratize computational catalysis, highlighting the specific hurdles that remain in achieving reliable, predictive power for widespread use.info:eu-repo/semantics/publishedVersionACS Publications2026info:eu-repo/semantics/article12 p.application/pdfhttps://hdl.handle.net/2072/489264https://doi.org/10.1021/acscatal.5c08945RECERCAT (Dipòsit de la Recerca de Catalunya)reponame:Recercat. Dipósit de la Recerca de Catalunyainstname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)InglésThe work was financed from TotalEnergies “Laboratory of the Future” project.O.L. acknowledges the Joan Oró Predoctoral Program of the Generalitat de Catalunya and the European Social Fund Plus (2023 FI-1 00769)Spanish Ministry of Science and Innovation (PID2024-157556OB-I00 and Severo Ochoa Excellence Accreditation funded by the “Severo Ochoa” Centres of Excellence Programme 2024 CEX2024-001469-S,MCIU/AEI/10.13039/501100011033)Attribution 4.0 Internationalhttp://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:recercat.cat:2072/4892642026-05-29T05:05:01Z
dc.title.none.fl_str_mv Challenges and Opportunities of Pretrained Machine Learning Interatomic Potentials in Heterogeneous Catalysis
title Challenges and Opportunities of Pretrained Machine Learning Interatomic Potentials in Heterogeneous Catalysis
spellingShingle Challenges and Opportunities of Pretrained Machine Learning Interatomic Potentials in Heterogeneous Catalysis
Loveday, Oliver
Química
54
title_short Challenges and Opportunities of Pretrained Machine Learning Interatomic Potentials in Heterogeneous Catalysis
title_full Challenges and Opportunities of Pretrained Machine Learning Interatomic Potentials in Heterogeneous Catalysis
title_fullStr Challenges and Opportunities of Pretrained Machine Learning Interatomic Potentials in Heterogeneous Catalysis
title_full_unstemmed Challenges and Opportunities of Pretrained Machine Learning Interatomic Potentials in Heterogeneous Catalysis
title_sort Challenges and Opportunities of Pretrained Machine Learning Interatomic Potentials in Heterogeneous Catalysis
dc.creator.none.fl_str_mv Loveday, Oliver
Kaźmierczak, Kamila
López, Núria
author Loveday, Oliver
author_facet Loveday, Oliver
Kaźmierczak, Kamila
López, Núria
author_role author
author2 Kaźmierczak, Kamila
López, Núria
author2_role author
author
dc.subject.none.fl_str_mv Química
54
topic Química
54
description The design of catalysts gets its fundamental rationale from accurate and efficient modeling of reactivity on surfaces and materials. To reach this detailed atomistic understanding, density functional theory (DFT) has been the key computational technique. However, the emergence of machine learning interatomic potentials (MLIPs) marks a significant paradigm shift, offering the potential to match DFT accuracy at a drastically reduced computational cost. This perspective provides an overview of state-of-the-art MLIPs for heterogeneous catalysis as “out-of-the-box” tools. We summarize the different families of MLIPs and their training processes and then apply these pretrained models to heterogeneous catalysis problems. Furthermore, we critically address the challenges of model transferability and integration in unified frameworks, underscoring the necessity for standardized protocols to benchmark performance across different architectures. Finally, we assess the capacity of pretrained models to democratize computational catalysis, highlighting the specific hurdles that remain in achieving reliable, predictive power for widespread use.
publishDate 2026
dc.date.none.fl_str_mv 2026
dc.type.none.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/2072/489264
https://doi.org/10.1021/acscatal.5c08945
url https://hdl.handle.net/2072/489264
https://doi.org/10.1021/acscatal.5c08945
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv The work was financed from TotalEnergies “Laboratory of the Future” project.
O.L. acknowledges the Joan Oró Predoctoral Program of the Generalitat de Catalunya and the European Social Fund Plus (2023 FI-1 00769)
Spanish Ministry of Science and Innovation (PID2024-157556OB-I00 and Severo Ochoa Excellence Accreditation funded by the “Severo Ochoa” Centres of Excellence Programme 2024 CEX2024-001469-S,MCIU/AEI/10.13039/501100011033)
dc.rights.none.fl_str_mv Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 12 p.
application/pdf
dc.publisher.none.fl_str_mv ACS Publications
publisher.none.fl_str_mv ACS Publications
dc.source.none.fl_str_mv RECERCAT (Dipòsit de la Recerca de Catalunya)
reponame:Recercat. Dipósit de la Recerca de Catalunya
instname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
instname_str Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
reponame_str Recercat. Dipósit de la Recerca de Catalunya
collection Recercat. Dipósit de la Recerca de Catalunya
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869411392066420736
score 15,811543

Similares en LA Referencia