Core-loss EELS dataset and neural networks for element identification

<p>We present a large dataset containing simulated core-loss electron energy loss spectroscopy (EELS) spectra with the elemental content as ground-truth labels. Additionally we present some neural networks trained on this data for element identification.&nbsp;</p> <p>The simulated dataset contains zero padded core-loss spectra from 0 to 3072 eV, which represents 107 core-loss edges through all 80 elements from Be up to Bi. The core-loss edges are calculated from the generalised oscillator strength (GOS) database presented by Zhang&nbsp;et al.[1] Generic fine structures using lifetime broadened peaks are used to imitate fine structure due to solid-state effects in experimental spectra. Generic low-loss regions are used to imitate the effect of multiple scattering. Each spectrum contains at least one edge of a given query element and possibly additional edges depending on samples drawn from The Materials Project [2]. The dataset contains for each of the 80 elements: 7000 training spectra, 1500 test spectra, 600 validation spectra and 100 spectra representing only the query element. This results in a total 736 000 labeled spectra.</p> <p>Code on how to&nbsp;<br> - read the simulated data<br> - transform HDF5 format to TFRecord format<br> - train and evaluate neural networks using the simulated data<br> - use the trained networks for automated element identification<br> is available on GitHub at arnoannys/EELS_ID</p> <p>A full report on the simulation of the dataset and the training and evaluation of the neural networks can be found at: &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp;Annys, A., Jannis, D. &amp; Verbeeck, J. Deep learning for automated materials characterisation in core-loss electron energy loss spectroscopy.&nbsp;<em>Sci Rep</em>&nbsp;13, 13724 (2023). https://doi.org/10.1038/s41598-023-40943-7</p> <p>[1] Zezhong Zhang, Ivan Lobato, Daen Jannis, Johan Verbeeck, Sandra Van Aert, &amp; Peter Nellist. (2023). Generalised oscillator strength for core-shell electron excitation by fast electrons based on Dirac solutions (1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.7729585<br> [2] Anubhav Jain, Shyue Ping Ong, Geoffroy Hautier, Wei Chen, William Davidson Richards, Stephen Dacek, Shreyas Cholia, Dan Gunter, David Skinner, Gerbrand Ceder, Kristin A. Persson; Commentary: The Materials Project: A materials genome approach to accelerating materials innovation. __APL Mater__ 1 July 2013; 1 (1): 011002. [https://doi.org/10.1063/1.4812323](https://doi.org/10.1063/1.4812323)</p>