Abstract
Recent advances in detectors for imaging and spectroscopy have afforded in situ, rapid acquisition of hyperspectral data. While electron energy loss spectroscopy (EELS) data acquisition speeds with electron counting are regularly reaching 400 frames per second with near-zero read noise, signal to noise ratio (SNR) remains a challenge owing to fundamental counting statistics. In order to advance understanding of transient materials phenomena during rapid acquisition EELS, trustworthy analysis of noisy spectra must be demonstrated. In this study, we applied machine learning techniques to denoise high frame rate spectra, benchmarking with slower frame rate “ground truths”. The results provide a foundation for reliable use of low SNR data acquired in rapid, in-situ spectroscopy experiments. Such a tool-set is a first step toward both automation in microscopy as well as use of these methods to interrogate otherwise poorly understood transformations.
Highlights
Machine learning tools present a solution to raise the information limit of rapidly acquired spectra, building a foundation for characterizing and tracking transient phenomena at shorter time scales
The use of neural networks (NNs) for spectra classification in energy loss spectroscopy (EELS) has been limited, with the majority of NN-based spectra classification having been focused on other techniques, such as Raman or X-ray absorption spectroscopy[12,20,21,22] or denoising of scanning transmission electron microscopy (STEM) images[23,24,25,26]
As a model system to investigate EELS fine structure changes, we study the reduction of a SrFeO3−δ thin film
Summary
Machine learning tools present a solution to raise the information limit of rapidly acquired spectra, building a foundation for characterizing and tracking transient phenomena at shorter time scales. Convolutional neural networks (CNN), have become common in fields with challenges that cannot be overcome by more basic human-driven domain engineering and statistical analysis due the high-dimensionality of the input or a lack of ‘ground truth’, such as speech recognition and natural language p rocessing[7,8,9], image c lassification[10,11,12,13] and feature extractions and classification of electroencephalography signals which tend to have a low SNR and be sensitive to background noise[7,8]. The use of neural networks (NNs) for spectra classification in EELS has been limited, with the majority of NN-based spectra classification having been focused on other techniques, such as Raman or X-ray absorption spectroscopy[12,20,21,22] or denoising of STEM images[23,24,25,26]. The high current density and longer dwell time needed may damage sensitive samples[33,34,35]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
