Identifying crystal structure is a crucial step in the analysis of proteins, microand macro-molecules, pharmaceuticals, geological specimens, and synthetic materials [1-3]. The most common practices involve analysis of diffraction patterns produced in laboratory X-ray diffractometers, transmission electron microscopes, and synchrotron X-ray sources. However, these techniques are slow, require careful sample preparation, can be difficult to access, and are prone to human error during analysis. Traditional electron backscatter diffraction (EBSD) is comparatively faster and easier to perform; however, contains the caveat that you have already determined the phases in your sample.
Paper
Full text
High-Throughput Identification of Crystal Structures Via Machine Learning
Semantic Scholar · Materials Science · 2019
Abstract
Identifying crystal structure is a crucial step in the analysis of proteins, microand macro-molecules, pharmaceuticals, geological specimens, and synthetic materials [1-3]. The most common practices involve analysis of diffraction patterns produced in laboratory X-ray diffractometers, transmission electron microscopes, and synchrotron X-ray sources. However, these techniques are slow, require careful sample preparation, can be difficult to access, and are prone to human error during analysis. Traditional electron backscatter diffraction (EBSD) is comparatively faster and easier to perform; however, contains the caveat that you have already determined the phases in your sample.