Machine Learning and DFT-Driven Catalyst Design for CO2 Conversion

The aim of this project is to develop a machine learning model for predicting the activation barriers on the catalyst surface for CO2 conversion reactions, with the assistance of density functional theory (DFT) calculations. The project will involve DFT calculations for the collection and preparation of a dataset, generate features that capture the electronic and geometric properties of the catalysts, the development and optimization of a machine learning model, and the use of the model to predict barriers that will aid in the design of novel catalysts.