Catalyst search shows how computing can take the guesswork out of chemistry Imagine synthesizing and then testing over 50 different complex molecules to identify the most effective catalyst for a particular chemical reaction. The traditional approach to developing new catalysts for chemical reactions in this "try it and see" manner is often extremely labor intensive, requiring numerous repeated experiments with potential candidate molecules. The now ubiquitous technique of machine learning can make this task much more efficient by predicting the performance of catalysts ahead of time based on theoretical characteristics.
https://phys.org/news/2024-05-....catalyst-guesswork-c