“Machine learning based unsupervised approach for nanostructure characterization using theoretical and experimental X-ray absorption spectroscopy”

Local structural information about nanoparticles during catalysis can be measured quantitatively by X-ray absorption fine structure spectra. While there are theoretical approaches to analyze the extended part of XAFS, namely EXAFS fitting, the near edge region (XANES) is only qualitatively analyzed using forward modeling approaches. Deep learning-based XANES analysis (Xiang et. a. 2022) was successfully applied to this new materials system to characterize the atomic neighborhood of single atoms.