First Demonstration of AI-assisted automation of single crystal neutron diffraction
ORAL
Abstract
Single-crystal neutron diffraction experiments can provide insight into a material's atomic structure and the origin of a material's properties. Current methods of analyzing data from these experiments rely on Bragg peak recognition, signal extraction and multiple codes' executions. This type of analysis is time-consuming and inefficient. Automated real-time analysis of the images and a common coding language would greatly increase the efficiency of single-crystal neutron diffraction experiments. We present the first demonstration of machine-learning-assisted automated single-crystal neutron diffraction experiments at Oak Ridge National Laboratory. Real-time analysis will optimize the use of neutron beam time and more precisely reduce the data.~We plan to integrate our demonstration into real-time analysis methods which will become the new analysis standard at the neutron-scattering user facility at Oak Ridge National Laboratory.
*The authors thank Bryan Chakoumakos and Guannan Zhang for useful discussions. This work was supported in part by the U.S. Department of Energy, Office of Science, Office of Workforce Development for Teachers and Scientists (WDTS) under the Science Undergraduate Laboratory Internship program
–