LaueNN: neural-network-based hkl recognition of Laue spots and its application to polycrystalline materials

A feed-forward neural-network-based model is presented to index, in real time, the diffraction spots recorded during synchrotron X-ray Laue microdiffraction experiments. Data dimensionality reduction is applied to extract physical 1D features from the 2D X-ray diffraction Laue images, thereby making it possible to train a neural network on the fly for any crystal system. The capabilities of the LaueNN model are illustrated through three examples: a two-phase nanostructure, a textured high-symmetry specimen deformed in situ and a polycrystalline low-symmetry material. This work provides a novel way to efficiently index Laue spots in simple and complex recorded images in <1 s, thereby opening up avenues for the realization of real-time analysis of synchrotron Laue diffraction data.

Automated summary

A feed-forward neural network model is presented to index diffraction spots recorded during synchrotron X-ray Laue microdiffraction experiments in real time. The model applies data dimensionality reduction to extract physical features from 2D X-ray diffraction Laue images, enabling on-the-fly training for any crystal system. The capabilities of the model are demonstrated with three examples, showcasing its ability to efficiently index Laue spots in simple and complex recorded images.