Gaussian process analysis of electron energy loss spectroscopy data: multivariate reconstruction and kernel control

Abstract Advances in hyperspectral imaging including electron energy loss spectroscopy bring forth the challenges of exploratory and physics-based analysis of multidimensional data sets. The multivariate linear unmixing methods generally explore similarities in the energy dimension, but ignore corre...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Sergei V. Kalinin, Andrew R. Lupini, Rama K. Vasudevan, Maxim Ziatdinov
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765
Acceso en línea:	https://doaj.org/article/50212b02eba0430fb30e01559ae93cc2
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:50212b02eba0430fb30e01559ae93cc2
record_format	dspace
spelling	oai:doaj.org-article:50212b02eba0430fb30e01559ae93cc22021-12-02T18:51:13ZGaussian process analysis of electron energy loss spectroscopy data: multivariate reconstruction and kernel control10.1038/s41524-021-00611-82057-3960https://doaj.org/article/50212b02eba0430fb30e01559ae93cc22021-09-01T00:00:00Zhttps://doi.org/10.1038/s41524-021-00611-8https://doaj.org/toc/2057-3960Abstract Advances in hyperspectral imaging including electron energy loss spectroscopy bring forth the challenges of exploratory and physics-based analysis of multidimensional data sets. The multivariate linear unmixing methods generally explore similarities in the energy dimension, but ignore correlations in the spatial domain. At the same time, Gaussian process (GP) explicitly incorporate spatial correlations in the form of kernel functions but is computationally intensive. Here, we implement a GP method operating on the full spatial domain and reduced representations in the energy domain. In this multivariate GP, the information between the components is shared via a common spatial kernel structure, while allowing for variability in the relative noise magnitude or image morphology. We explore the role of kernel constraints on the quality of the reconstruction, and suggest an approach for estimating them from the experimental data. We further show that spatial information contained in higher-order components can be reconstructed and spatially localized.Sergei V. KalininAndrew R. LupiniRama K. VasudevanMaxim ZiatdinovNature PortfolioarticleMaterials of engineering and construction. Mechanics of materialsTA401-492Computer softwareQA76.75-76.765ENnpj Computational Materials, Vol 7, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765
spellingShingle	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765 Sergei V. Kalinin Andrew R. Lupini Rama K. Vasudevan Maxim Ziatdinov Gaussian process analysis of electron energy loss spectroscopy data: multivariate reconstruction and kernel control
description	Abstract Advances in hyperspectral imaging including electron energy loss spectroscopy bring forth the challenges of exploratory and physics-based analysis of multidimensional data sets. The multivariate linear unmixing methods generally explore similarities in the energy dimension, but ignore correlations in the spatial domain. At the same time, Gaussian process (GP) explicitly incorporate spatial correlations in the form of kernel functions but is computationally intensive. Here, we implement a GP method operating on the full spatial domain and reduced representations in the energy domain. In this multivariate GP, the information between the components is shared via a common spatial kernel structure, while allowing for variability in the relative noise magnitude or image morphology. We explore the role of kernel constraints on the quality of the reconstruction, and suggest an approach for estimating them from the experimental data. We further show that spatial information contained in higher-order components can be reconstructed and spatially localized.
format	article
author	Sergei V. Kalinin Andrew R. Lupini Rama K. Vasudevan Maxim Ziatdinov
author_facet	Sergei V. Kalinin Andrew R. Lupini Rama K. Vasudevan Maxim Ziatdinov
author_sort	Sergei V. Kalinin
title	Gaussian process analysis of electron energy loss spectroscopy data: multivariate reconstruction and kernel control
title_short	Gaussian process analysis of electron energy loss spectroscopy data: multivariate reconstruction and kernel control
title_full	Gaussian process analysis of electron energy loss spectroscopy data: multivariate reconstruction and kernel control
title_fullStr	Gaussian process analysis of electron energy loss spectroscopy data: multivariate reconstruction and kernel control
title_full_unstemmed	Gaussian process analysis of electron energy loss spectroscopy data: multivariate reconstruction and kernel control
title_sort	gaussian process analysis of electron energy loss spectroscopy data: multivariate reconstruction and kernel control
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/50212b02eba0430fb30e01559ae93cc2
work_keys_str_mv	AT sergeivkalinin gaussianprocessanalysisofelectronenergylossspectroscopydatamultivariatereconstructionandkernelcontrol AT andrewrlupini gaussianprocessanalysisofelectronenergylossspectroscopydatamultivariatereconstructionandkernelcontrol AT ramakvasudevan gaussianprocessanalysisofelectronenergylossspectroscopydatamultivariatereconstructionandkernelcontrol AT maximziatdinov gaussianprocessanalysisofelectronenergylossspectroscopydatamultivariatereconstructionandkernelcontrol
_version_	1718377446287343616

Gaussian process analysis of electron energy loss spectroscopy data: multivariate reconstruction and kernel control

Ejemplares similares