Catalysts play a central role in modern society, enabling the production of a wide range of chemicals, energy conversion processes, and the treatment of harmful waste. Discovering new catalytic materials and improving existing ones is essential for making more efficient and sustainable use of our resources.

In recent years, Machine Learning (ML) and Artificial Intelligence (AI)–assisted workflows have increasingly contributed to the discovery and optimization of materials across many applications. However, Materials and Catalyst Informatics remain emerging fields, and there is still no established, systematic methodology for catalyst design.

My research focuses on developing Machine Learning–assisted methodologies for inverse catalyst design, in which predictive models trained on existing materials are used to screen and identify promising new catalyst candidates. By establishing robust informatics-based design frameworks, this approach can be connected to automated experimental platforms, integrating data-driven modeling with robotic experimentation. Ultimately, this workflow aims to accelerate the discovery and development of efficient catalysts and functional materials.