Machine Learning in Catalysis

Optimization of catalysts is often difficult because the exact mechanisms leading to the desired result are often unclear. An example of this is the stabilization of palladium(I) dimers, which relies on a very small class of phosphine ligands. Based on the research of Hueffel et al, JARA-CSD scientist Franziska Schoenebeck has now succeeded in synthesizing eight previously undescribed dimers. Hueffel et al. used machine learning to search for patterns in this known class of ligands. The research group led by Prof. Schoenebeck used unsupervised machine learning. The results of the research were recently published in the journal Science.

Original publication on the website of Science: https://www.science.org/doi/10.1126/science.abj0999