Mapping grain orientation in crystalline solids is crucial for understanding the link between microstructure and material properties. Electron backscatter diffraction (EBSD) is a standard technique, but its low throughput limits its application to large samples or material libraries. This paper introduces a machine learning approach for high-throughput crystal orientation mapping using directional reflectance microscopy (DRM). The method, successfully applied to Inconel 718 specimens from additive manufacturing, demonstrates the feasibility of optical orientation mapping in metal alloys. Its data-driven nature allows easy extension to other alloys and manufacturing processes.

Mallory Wittwer, Matteo Seita