Charting the low-loss region in electron energy loss spectroscopy with machine learning

Exploiting the information provided by electron energy-loss spectroscopy (EELS) requires reliable access to the low-loss region where the zero-loss peak (ZLP) often overwhelms the contributions associated to inelastic scatterings off the specimen. Here we deploy machine learning techniques developed in particle physics to realise a model-independent, multidimensional determination of the ZLP with a faithful uncertainty estimate. This novel method is then applied to subtract the ZLP for EEL spectra acquired in flower-like WS2 nanostructures characterised by a 2H/3R mixed polytypism. From the resulting subtracted spectra we determine the nature and value of the bandgap of polytypic WS2, finding E-BG = 1.6(-0.2)(+0.3) eV with a clear preference for an indirect bandgap. Further, we demonstrate how this method enables us to robustly identify excitonic transitions down to very small energy losses. Our approach has been implemented and made available in an open source PYTHON package dubbed EELSfitter.

Automated summary

Machine learning techniques were deployed to determine the ZLP in a model-independent, multidimensional manner, enabling the subtraction of ZLP in EEL spectra of flower-like WS2 nanostructures to determine the bandgap nature and value of WS2. The method also allows robust identification of excitonic transitions at very small energy losses.