acm-header
Sign In

Communications of the ACM

ACM Careers

Using AI, Argonne Scientists Develop Self-Driving Microscopy Technique


View as: Print Mobile App Share:
X-ray beam focused using a zone plate setup, illustration

The position of the X-ray beam in this zone plate setup, and of the 2D detector, is autonomously controlled by an AI-based workflow.

Credit: Argonne National Laboratory

Researchers at the U.S. Department of Energy's Argonne National Laboratory have developed an autonomous microscopy technique. It uses AI to selectively target points of interest for scanning. Unlike the traditional point-by-point raster scan, this approach identifies clusters of intriguing features and bypasses other regions.

"Such self-driving or autonomous experimentation methods . . . combine automated experimental control with on-the-fly data-driven decision-making so that an algorithm adaptively explores parameter spaces of interest and conducts new experiments until it achieves a pre-defined completion criterion," the researchers say in a study published in Nature Communications.

"The ability to automate experiments with AI will significantly accelerate scientific progress in the coming years," says Argonne group leader and computational scientist Mathew Cherukara, an author of the study. ‚Äč"This is a demonstration of our ability to do autonomous research with a very complex instrument."

From Argonne National Laboratory
View Full Article


 

No entries found