Challenges and Opportunities of Pretrained Machine Learning Interatomic Potentials in Heterogeneous Catalysis
ACS Catalysis · 06.03.2026 · 16 (5) · 4113-4124
DOI: 10.1021/acscatal.5c08945 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift ACS Catalysis, online erschienen am 18.02.2026. Verfasst von Oliver Loveday und 2 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Chemical Research of Catalonia (ICIQ-CERCA), The Barcelona Institute of Science and Technology, Av. Països Catalans 16, Tarragona 43007,…. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 85 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministerio de Ciencia, Innovación y Universidades, Agencia Estatal de Investigación, Total.
Abstract (Originalsprache)
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.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute of Chemical Research of Catalonia (ICIQ-CERCA), The Barcelona Institute of Science and Technology, Av. Països Catalans 16, Tarragona 43007, Spain.
- Department of Physical and Inorganic Chemistry, Universitat Rovira i Virgili, Campus Sescelades, N4 Block, C. Marcellí Domingo 1, Tarragona 43007, Spain.
- TotalEnergies, TotalEnergies One Tech Belgium, Zone Industrielle C, Feluy 7181, Belgium.
ORCID-Profile: Oliver Loveday, Núria López
Förderung
- Ministerio de Ciencia, Innovación y Universidades
- Agencia Estatal de Investigación
- Total
- Generalitat de Catalunya
- European Social Fund Plus
Zitieren
APA
Loveday, O., Kaźmierczak, K., & López, N. (2026). Challenges and Opportunities of Pretrained Machine Learning Interatomic Potentials in Heterogeneous Catalysis. ACS Catalysis, 16(5), 4113-4124. https://doi.org/10.1021/acscatal.5c08945
Vancouver
Loveday O, Kaźmierczak K, López N. Challenges and Opportunities of Pretrained Machine Learning Interatomic Potentials in Heterogeneous Catalysis. ACS Catalysis. 2026;16(5):4113-4124. doi:10.1021/acscatal.5c08945
BibTeX
@article{Loveday2026,
author = {Loveday, Oliver and Kaźmierczak, Kamila and López, Núria},
title = {Challenges and Opportunities of Pretrained Machine Learning Interatomic Potentials in Heterogeneous Catalysis},
journal = {ACS Catalysis},
year = {2026},
volume = {16},
number = {5},
pages = {4113--4124},
doi = {10.1021/acscatal.5c08945}
}
EUVIMED