On the left is a human visual depiction of a pulsed laser deposition plasma plume. On the right is an image from a video showing an AI interpretation of the plasma plume to predict film growth characteristics. Credit: Sumner Harris/ORNL, U.S. Department of Energy
In a paper published in the journal npj Computational Materials, scientists at Oak Ridge National Laboratory developed a deep learning model — a type of artificial intelligence that mimics the functions of the human brain — to analyze high-speed videos of plasma plumes during a process called pulsed laser deposition (PLD).
PLD technology uses intense laser pulses to vaporize a target material, creating a cloud-like stream of atoms and particles (plasma plume) that then settles onto the target surface to form ultra-thin films, a method essential for creating advanced materials used in electronics and energy technologies.
“We’ve taught the AI ​​to do what experienced scientists have always done intuitively: evaluate the plasma plume to check whether its color, shape, size and brightness are the same as the last time we made a good sample,” said ORNL’s Sumner Harris, lead author of the study. “Not only does this automate quality control, it also reveals unexpected insights into how these tiny particles behave during film formation.”
This innovation builds on ORNL’s previous development of an autonomous PLD system that accelerates materials discovery by 10 times and is expected to transform the oversight of materials synthesis, making the creation of next-generation materials even more efficient.
Further information: Sumner B. Harris et al., “Deep Learning with Plasma Plume Image Sequences for Anomaly Detection and Growth Rate Prediction During Pulsed Laser Deposition,” npj Computational Materials (2024). DOI: 10.1038/s41524-024-01275-w
Courtesy of Oak Ridge National Laboratory
Source: AI Enhances Plasma Plume Analysis (September 16, 2024) Retrieved September 17, 2024 from https://phys.org/news/2024-09-ai-plasma-plume-analysis.html
This document is subject to copyright. It may not be reproduced without written permission, except for fair dealing for the purposes of personal study or research. The content is provided for informational purposes only.
