RapidEELS: machine learning for denoising and classification in rapid acquisition electron energy loss spectroscopy

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, sig...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Cassandra M. Pate, James L. Hart, Mitra L. Taheri
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/9695c40528ec45e6bdfa40569fdb0f50
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9695c40528ec45e6bdfa40569fdb0f50
record_format	dspace
spelling	oai:doaj.org-article:9695c40528ec45e6bdfa40569fdb0f502021-12-02T18:51:07ZRapidEELS: machine learning for denoising and classification in rapid acquisition electron energy loss spectroscopy10.1038/s41598-021-97668-82045-2322https://doaj.org/article/9695c40528ec45e6bdfa40569fdb0f502021-09-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-97668-8https://doaj.org/toc/2045-2322Abstract 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.Cassandra M. PateJames L. HartMitra L. TaheriNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Cassandra M. Pate James L. Hart Mitra L. Taheri RapidEELS: machine learning for denoising and classification in rapid acquisition electron energy loss spectroscopy
description	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.
format	article
author	Cassandra M. Pate James L. Hart Mitra L. Taheri
author_facet	Cassandra M. Pate James L. Hart Mitra L. Taheri
author_sort	Cassandra M. Pate
title	RapidEELS: machine learning for denoising and classification in rapid acquisition electron energy loss spectroscopy
title_short	RapidEELS: machine learning for denoising and classification in rapid acquisition electron energy loss spectroscopy
title_full	RapidEELS: machine learning for denoising and classification in rapid acquisition electron energy loss spectroscopy
title_fullStr	RapidEELS: machine learning for denoising and classification in rapid acquisition electron energy loss spectroscopy
title_full_unstemmed	RapidEELS: machine learning for denoising and classification in rapid acquisition electron energy loss spectroscopy
title_sort	rapideels: machine learning for denoising and classification in rapid acquisition electron energy loss spectroscopy
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/9695c40528ec45e6bdfa40569fdb0f50
work_keys_str_mv	AT cassandrampate rapideelsmachinelearningfordenoisingandclassificationinrapidacquisitionelectronenergylossspectroscopy AT jameslhart rapideelsmachinelearningfordenoisingandclassificationinrapidacquisitionelectronenergylossspectroscopy AT mitraltaheri rapideelsmachinelearningfordenoisingandclassificationinrapidacquisitionelectronenergylossspectroscopy
_version_	1718377461699313664

RapidEELS: machine learning for denoising and classification in rapid acquisition electron energy loss spectroscopy

Ejemplares similares