Inside Back Cover: Accelerating Catalyst Materials Discovery With Large Artificial Intelligence Models (Angew. Chem. Int. Ed. 16/2026)
Abstract
Catalysis is entering a fourth plus data-driven paradigm in which large models complement theory and experiment. The cover links three pillars: catalysis databases, universal machine-learning interatomic potentials that reproduce potential energy surfaces with near density functional theory accuracy at scale, and large language models that extract and connect catalytic concepts from literature. Together, large models compress the path from concept to computation and accelerate the discovery of next-generation catalysts. More in article number e26150, Yuanzheng Chen, Jiayu Peng, Pengfei Ou, Hao Li, and co-workers.
Fields of Study & Subjects
Machine Learning in Materials Science
Catalytic Processes in Materials Science
Advanced Chemical Physics Studies
Publication details
- Journal / source
- Angewandte Chemie International Edition
- Volume
- 65
- Issue
- 16
- Publication date
- 9 March 2026
- Language
- EN