AI Based Stabilization of Sample Environments

Neutron scattering experiments provide unparalleled contributions to physical, chemical, and materials science. At present the US Government through DOE-BES operates two premier neutron scattering centers. These facilities serve a broad and growing user community which necessitates their improved operational efficiency and capacity. The automation of sample alignment procedures using machine learning will result in more efficient use of neutron facilities and therefore increase the overall quality of their scientific output. We will develop and test new machine learning methods for sample alignment and stabilization in neutron beam-lines. We will utilize convolutional neural networks to automatically process images of the sample environment and provide a real time correction to the sample position. Additionally, we will develop machine agnostic tools that deconstruct diagnostic images into geometric primitives which will enable the efficient adoption of our software across the neutron science community. The code will be made available through an open-source web-based graphical user interface. That interface will be able to visualize diagnostic images, train new machine learning algorithms bases on a suite of examples, and display the control input and output provided to the experiment. Data from two operational neutron experiments will be collected and used to train machine learning tools for sample alignment. We will simulate our sample alignment algorithms and fine tune our approach as needed. We will prototype an open source GUI that will allow users easy access to both machine learning tools and templated control displays for fast deployment of our algorithms. Our software will be readily applied to neutron scattering facilities around the globe. We will offer customization through R+D contracts with labs and universities operating these types of systems. Our software will also be extendable to other image based alignment problems for x-ray beam-lines and particle accelerators. Moreover, our work on geometric primitive identification has the potential for broad impact across the science and medical community.