AI-Powered Material Analysis and Discovery using Coherent X-Rays in Pulsed Laser Deposition*
Session Number
2
Advisor(s)
Dr. Dillon Fong, Argonne National Laboratory
Location
A113
Discipline
Computer Science
Start Date
15-4-2026 11:10 AM
End Date
15-4-2026 11:55 AM
Abstract
Pulsed laser deposition is a method in which atoms and molecules from a select material are broken off from a larger mass using a targeted laser. These particles arrive onto a heated crystal substrate, allowing for the diffusion of particles and the creation of a new thin film crystal atop the heated substrate. The properties of these thin film materials are actively being studied, with the hopes of improving microelectronics or discovering useful properties such as high-temperature superconductivity. The upgraded Advanced Photon Source at Argonne National Laboratory enables data collection methods, such as X-ray spectroscopy or diffraction, to be performed on materials inside pulsed laser deposition systems. This project aimed to assess the effectiveness of a Machine Learning-based approach for analyzing the resulting data from pulsed laser deposition. A Physics-Informed Neural Network was used to analyze the output of multiple lanthanum cobalt oxide X-ray diffraction datasets.
AI-Powered Material Analysis and Discovery using Coherent X-Rays in Pulsed Laser Deposition*
A113
Pulsed laser deposition is a method in which atoms and molecules from a select material are broken off from a larger mass using a targeted laser. These particles arrive onto a heated crystal substrate, allowing for the diffusion of particles and the creation of a new thin film crystal atop the heated substrate. The properties of these thin film materials are actively being studied, with the hopes of improving microelectronics or discovering useful properties such as high-temperature superconductivity. The upgraded Advanced Photon Source at Argonne National Laboratory enables data collection methods, such as X-ray spectroscopy or diffraction, to be performed on materials inside pulsed laser deposition systems. This project aimed to assess the effectiveness of a Machine Learning-based approach for analyzing the resulting data from pulsed laser deposition. A Physics-Informed Neural Network was used to analyze the output of multiple lanthanum cobalt oxide X-ray diffraction datasets.