|
Records |
Links |
|
Author |
Annys, A.; Jannis, D.; Verbeeck, J. |
![find record details (via OpenURL) openurl](img/xref.gif)
|
|
Title |
Core-loss EELS dataset and neural networks for element identification |
Type |
Dataset |
|
Year |
2023 |
Publication |
|
Abbreviated Journal |
|
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
Dataset; Electron microscopy for materials research (EMAT) |
|
|
Abstract |
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. 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 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. Code on how to – read the simulated data – transform HDF5 format to TFRecord format – train and evaluate neural networks using the simulated data – use the trained networks for automated element identification is available on GitHub at arnoannys/EELS_ID A full report on the simulation of the dataset and the training and evaluation of the neural networks can be found at: Annys, A., Jannis, D. & Verbeeck, J. Deep learning for automated materials characterisation in core-loss electron energy loss spectroscopy. Sci Rep 13, 13724 (2023). https://doi.org/10.1038/s41598-023-40943-7 [1] Zezhong Zhang, Ivan Lobato, Daen Jannis, Johan Verbeeck, Sandra Van Aert, & 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 [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) |
|
|
Address |
|
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Wos |
|
Publication Date |
|
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
|
ISBN |
|
Additional Links |
UA library record |
|
|
Impact Factor |
|
Times cited |
|
Open Access |
|
|
|
Notes |
|
Approved |
Most recent IF: NA |
|
|
Call Number |
UA @ admin @ c:irua:203391 |
Serial ![sorted by Serial field, descending order (down)](img/sort_desc.gif) |
9015 |
|
Permanent link to this record |
|
|
|
|
Author |
Annys, A.; Jannis, D.; Verbeeck, J.; Annys, A.; Jannis, D.; Verbeeck, J. |
![goto web page (via DOI) doi](http://nano.uantwerpen.be/nanorefs/img/doi.gif)
|
|
Title |
Deep learning for automated materials characterisation in core-loss electron energy loss spectroscopy |
Type |
A1 Journal article |
|
Year |
2023 |
Publication |
Scientific reports |
Abbreviated Journal |
|
|
|
Volume |
13 |
Issue |
1 |
Pages |
13724 |
|
|
Keywords |
A1 Journal article; Engineering sciences. Technology; Electron microscopy for materials research (EMAT) |
|
|
Abstract |
Electron energy loss spectroscopy (EELS) is a well established technique in electron microscopy that yields information on the elemental content of a sample in a very direct manner. One of the persisting limitations of EELS is the requirement for manual identification of core-loss edges and their corresponding elements. This can be especially bothersome in spectrum imaging, where a large amount of spectra are recorded when spatially scanning over a sample area. This paper introduces a synthetic dataset with 736,000 labeled EELS spectra, computed from available generalized oscillator strength tables, that represents 107 K, L, M or N core-loss edges and 80 chemical elements. Generic lifetime broadened peaks are used to mimic the fine structure due to band structure effects present in experimental core-loss edges. The proposed dataset is used to train and evaluate a series of neural network architectures, being a multilayer perceptron, a convolutional neural network, a U-Net, a residual neural network, a vision transformer and a compact convolutional transformer. An ensemble of neural networks is used to further increase performance. The ensemble network is used to demonstrate fully automated elemental mapping in a spectrum image, both by directly mapping the predicted elemental content and by using the predicted content as input for a physical model-based mapping. |
|
|
Address |
|
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
|
Place of Publication |
|
Editor |
|
|
|
Language |
|
Wos |
001052937600046 |
Publication Date |
2023-08-22 |
|
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
|
Series Volume |
|
Series Issue |
|
Edition |
|
|
|
ISSN |
2045-2322 |
ISBN |
|
Additional Links |
UA library record; WoS full record |
|
|
Impact Factor |
4.6 |
Times cited |
|
Open Access |
OpenAccess |
|
|
Notes |
A.A. would like to acknowledge the resources and services used in this work provided by the VSC (Flemish Supercomputer Center), funded by the Research Foundation – Flanders (FWO) and the Flemish Government. J.V. acknowledges the IMPRESS project. The IMPRESS project has received funding from the HORIZON EUROPE framework program for research and innovation under grant agreement n. 101094299. |
Approved |
Most recent IF: 4.6; 2023 IF: 4.259 |
|
|
Call Number |
UA @ admin @ c:irua:198647 |
Serial ![sorted by Serial field, descending order (down)](img/sort_desc.gif) |
8846 |
|
Permanent link to this record |