Description
Modelling nanoscaled catalysts is an important goal for better utilizing energy and chemicals, but it is a challenging task involving combining several methodologies able to capture the structural and functional complexity. Each methodology can provide a significant amount of valuable data, including material composition, geometrical features, structural architecture, and electronic and chemical capabilities.
By combining the data accumulated by European research experts during our Cost Action with available databases we will develop and train machine learning algorithms that are capable of predicting catalytic performance. As a result, we will provide the scientific and industrial community with chatGPT-type and machine learning tools for identifying the composition and shape of efficient nanocatalysts.
Action keywords
Density Functional Theory - Machine learning - Multiscale modelling - heterogenous catalysis
Main Contacts
Action Contacts
COST Staff
Leadership
| Role | Leader |
|---|---|
| Action Chair | |
| Action Vice-Chair |