A machine-learning-powered framework, CARE, enables the automated generation of reaction networks in heterogeneous catalysis. Integrating tasks routinely handled by computational scientists, CARE facilitates the fast prediction of experimental reaction rates and the elucidation of reaction mechanisms, enabling the systematic study of previously inaccessible processes.
This is a preview of subscription content, access via your institution
Access options
Subscribe to this journal
Receive 12 digital issues and online access to articles
$119.00 per year
only $9.92 per issue
Buy this article
- Purchase on SpringerLink
- Instant access to the full article PDF.
USD 39.95
Prices may be subject to local taxes which are calculated during checkout
References
Rosen, A. S. Beyond big data in quantum chemistry. Nat. Chem. Eng. 3, 79 (2026). A discussion on the current and future challenges related to big data and atomistic simulations.
Wen, M. et al. Chemical reaction networks and opportunities for machine learning. Nat. Comput. Sci. 3, 12–24 (2023). A perspective on the integration of ML into the exploration of chemical reaction networks.
Batatia, I. et al. A foundation model for atomistic materials chemistry. J. Chem. Phys. 163, 184110 (2025). This article presents MACE-MP-0, a foundation MLIP for materials science.
Kreitz, B. et al. Detailed microkinetics for the oxidation of exhaust gas emissions through automated mechanism generation. ACS Catal. 12, 11137–11151 (2022). This article presents an early example of automated reaction mechanism development assisted by MLIPs.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This is a summary of: Morandi, S. et al. An end-to-end framework for reactivity in heterogeneous catalysis. Nat. Chem. Eng. https://doi.org/10.1038/s44286-026-00361-8 (2026).
Rights and permissions
About this article
Cite this article
Accelerating multiscale modeling in heterogeneous catalysis. Nat Chem Eng (2026). https://doi.org/10.1038/s44286-026-00363-6
Published:
Version of record:
DOI: https://doi.org/10.1038/s44286-026-00363-6
