Accelerating Catalytic Reaction Network Exploration via Local Fine-tuning with Universal Machine Learning Interatomic Potentials
Abstract
Theoretical exploration of complex catalytic reaction networks (CRNs) is limited by the trade-off between the cost of quantum mechanical calculations and the reduced accuracy of approximate methods. We introduce the LFT-CRN, an active learning framework combining pretrained universal machine learning interatomic potentials (MLIPs) with a local fine-tuning (LFT) algorithm for efficient CRN exploration. The LFT-CRN accelerates geometry optimization, transition-state search, and vibrational analysis while maintaining consistent performance across different exchange–correlation functionals and density functional theory (DFT) settings. Applied to methanol synthesis on CuZn catalysts, the LFT-CRN achieves over a 14-fold acceleration compared with the conventional DFT workflow, retaining chemical accuracy (
Fields of Study & Subjects
Machine Learning in Materials Science
CO2 Reduction Techniques and Catalysts
Electrocatalysts for Energy Conversion
Publication details
- Journal / source
- ACS Catalysis
- Publisher
- American Chemical Society (ACS)
- Volume
- 16
- Issue
- 7
- Pages
- 6443–6452
- Publication date
- 24 March 2026
- Language
- EN