Researchers Use JUWELS to Better Understand How Molecules Bind to Catalyst Surfaces

Principal Investigator:
Prof. Dr. Karsten Reuter

Fritz-Haber-Institut der Max-Planck-Gesellschaft Berlin

Local Project ID:

HPC Platform used:
JUWELS Cluster at JSC

Date published:

A machine learning algorithm predicts the binding of molecules to a catalyst surface. Reprinted with the permission from Copyright © 2022, Wenbin Xu, Karsten Reuter and Mie Andersen, under exclusive licence to Springer Nature America, Inc.

A group of researchers from the Fritz Haber Institute and Aarhus University in Denmark have leveraged the power of the JUWELS supercomputer at the Jülich Supercomputing Centre (JSC) to develop a machine learning algorithm that helps predict how specific molecules bind to the surface of a catalyst. Catalysts play an essential role in many chemical processes, and how specific molecules interact with these materials can influence the efficiency, effectiveness, and safety of chemical reactions at an industrial scale.

The team developed an algorithm by training it with similar calculations done on molecules interacting with catalysts. By scaling up this machine learning workflow, the team was able to move beyond simple molecules by including the connectivity between atoms within the molecule. The team’s work was published in Nature Computational Science.

For the full report, please click here.

For the full journal article, please click here.