Communications of the ACM
AI Agent Helps Identify Material Properties Faster
When searching for promising new materials in material libraries, artificial intelligence can help analyze extensive X-ray diffraction data faster and better.
Credit: Lehrstuhl Materials Discovery and Interfaces
Researchers at Brookhaven National Laboratory, the University of Liverpool in the U.K., and the Ruhr-University Bochum in Germany demonstrated that artificial intelligence (AI) can speed up X-ray diffraction data (XRD) analysis and improve accuracy in searches for new materials.
The researchers developed an AI agent, Crystallography Companion Agent (XCA), that collaborates with scientists when it comes to decision-making.
XCA can perform autonomous phase identifications from XRD data while it is measured and works with both organic and inorganic material systems.
The algorithm was trained using a large-scale simulation of physically correct X-ray diffraction data.
Ruhr's Lars Banko said the decision-making process "is simulated by an ensemble of neural networks, similar to a vote among experts. This is accomplished without manual, human-labelled data and is robust to many sources of experimental complexity."
Ruhr's Alfred Ludwig called the research "an important step in accelerating the discovery of new materials."
From Ruhr-University Bochum (Germany)
View Full Article
Abstracts Copyright © 2021 SmithBucklin, Washington, DC, USA
No entries found