1
|
Del-Pozo-Bueno D, Kepaptsoglou D, Peiró F, Estradé S. Comparative of machine learning classification strategies for electron energy loss spectroscopy: Support vector machines and artificial neural networks. Ultramicroscopy 2023; 253:113828. [PMID: 37556961 DOI: 10.1016/j.ultramic.2023.113828] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/25/2023] [Revised: 07/26/2023] [Accepted: 08/02/2023] [Indexed: 08/11/2023]
Abstract
Machine Learning (ML) strategies applied to Scanning and conventional Transmission Electron Microscopy have become a valuable tool for analyzing the large volumes of data generated by various S/TEM techniques. In this work, we focus on Electron Energy Loss Spectroscopy (EELS) and study two ML techniques for classifying spectra in detail: Support Vector Machines (SVM) and Artificial Neural Networks (ANN). Firstly, we systematically analyze the optimal configurations and architectures for ANN classifiers using random search and the tree-structured Parzen estimator methods. Secondly, a new kernel strategy is introduced for the soft-margin SVMs, the cosine kernel, which offers a significant advantage over the previously studied kernels and other ML classification strategies. This kernel allows us to bypass the normalization of EEL spectra, achieving accurate classification. This result is highly relevant for the EELS community since we also assess the impact of common normalization techniques on our spectra using Uniform Manifold Approximation and Projection (UMAP), revealing a strong bias introduced in the spectra once normalized. In order to evaluate and study both classification strategies, we focus on determining the oxidation state of transition metals through their EEL spectra, examining which feature is more suitable for oxidation state classification: the oxygen K peak or the transition metal white lines. Subsequently, we compare the resistance to energy loss shifts for both classifiers and present a strategy to improve their resistance. The results of this study suggest the use of soft-margin SVMs for simpler EELS classification tasks with a limited number of spectra, as they provide performance comparable to ANNs while requiring lower computational resources and reduced training times. Conversely, ANNs are better suited for handling complex classification problems with extensive training data.
Collapse
Affiliation(s)
- Daniel Del-Pozo-Bueno
- Departament d'Enginyeria Electrònica i Biomèdica, LENS-MIND, Universitat de Barcelona, Barcelona 08028, Spain; Institute of Nanoscience and Nanotechnology (IN2UB), Universitat de Barcelona, Barcelona 08028, Spain.
| | - Demie Kepaptsoglou
- SuperSTEM, Sci-Tech Daresbury Campus, Daresbury WA4 4AD, UK; School of Physics, Engineering and Technology, University of York, Heslington YO10 5DD, UK
| | - Francesca Peiró
- Departament d'Enginyeria Electrònica i Biomèdica, LENS-MIND, Universitat de Barcelona, Barcelona 08028, Spain; Institute of Nanoscience and Nanotechnology (IN2UB), Universitat de Barcelona, Barcelona 08028, Spain
| | - Sònia Estradé
- Departament d'Enginyeria Electrònica i Biomèdica, LENS-MIND, Universitat de Barcelona, Barcelona 08028, Spain; Institute of Nanoscience and Nanotechnology (IN2UB), Universitat de Barcelona, Barcelona 08028, Spain
| |
Collapse
|
2
|
Ryu J, Kim H, Kim RM, Kim S, Jo J, Lee S, Nam KT, Joo YC, Yi GC, Lee J, Kim M. Dimensionality reduction and unsupervised clustering for EELS-SI. Ultramicroscopy 2021; 231:113314. [PMID: 34024663 DOI: 10.1016/j.ultramic.2021.113314] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/21/2020] [Revised: 04/29/2021] [Accepted: 05/05/2021] [Indexed: 11/18/2022]
Abstract
A novel combination of machine learning algorithms is proposed for the differentiation of distinct spectra in a large electron energy loss spectroscopy spectrum image (EELS-SI) dataset. For clustering of the EEL spectra including similar fine structures in an efficient space, linear and nonlinear dimensionality reduction methods are used to project the EEL spectra onto a low-dimensional space. Then, a density-based clustering algorithm is applied to distinguish the meaningful data clusters. By applying this strategy to various experimental EELS-SI datasets, differentiation of several groups of EEL spectra representing specific fine structures was achieved. It is possible to investigate particular fine structures by averaging all of the spectra in each cluster. Also, the spatial distributions of each cluster in the scanning regions can be observed, which enables investigation of the locations of different fine structures in materials. This method does not require any prior knowledge, i.e., it is a data-driven analysis; therefore, it can be applied to any hyperspectral image.
Collapse
Affiliation(s)
- Jinseok Ryu
- Department of Materials Science & Engineering and Research Institute of Advanced Materials (RIAM), Seoul National University, 08826, Seoul, South Korea
| | - Hyeohn Kim
- Department of Materials Science & Engineering and Research Institute of Advanced Materials (RIAM), Seoul National University, 08826, Seoul, South Korea
| | - Ryeong Myeong Kim
- Department of Materials Science & Engineering and Research Institute of Advanced Materials (RIAM), Seoul National University, 08826, Seoul, South Korea
| | - Sungtae Kim
- Department of Materials Science & Engineering and Research Institute of Advanced Materials (RIAM), Seoul National University, 08826, Seoul, South Korea
| | - Jaeyeon Jo
- Department of Materials Science & Engineering and Research Institute of Advanced Materials (RIAM), Seoul National University, 08826, Seoul, South Korea
| | - Sangmin Lee
- Department of Materials Science & Engineering and Research Institute of Advanced Materials (RIAM), Seoul National University, 08826, Seoul, South Korea
| | - Ki Tae Nam
- Department of Materials Science & Engineering and Research Institute of Advanced Materials (RIAM), Seoul National University, 08826, Seoul, South Korea
| | - Young-Chang Joo
- Department of Materials Science & Engineering and Research Institute of Advanced Materials (RIAM), Seoul National University, 08826, Seoul, South Korea
| | - Gyu-Chul Yi
- Department of Physics & Astronomy, Seoul National University, 08826, Seoul, South Korea
| | - Jaejin Lee
- Department of Computer Science & Engineering, Seoul National University, 08826, Seoul, South Korea
| | - Miyoung Kim
- Department of Materials Science & Engineering and Research Institute of Advanced Materials (RIAM), Seoul National University, 08826, Seoul, South Korea.
| |
Collapse
|
3
|
Zhang S, Scheu C. Evaluation of EELS spectrum imaging data by spectral components and factors from multivariate analysis. Microscopy (Oxf) 2018; 67:i133-i141. [PMID: 29136225 PMCID: PMC7207561 DOI: 10.1093/jmicro/dfx091] [Citation(s) in RCA: 26] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2017] [Indexed: 11/13/2022] Open
Abstract
Multivariate analysis is a powerful tool to process spectrum imaging datasets of electron energy loss spectroscopy. Most spatial variance of the datasets can be explained by a limited numbers of components. We explore such dimension reduction to facilitate quantitative analyses of spectrum imaging data, supervising the spectral components instead of spectra at individual pixels. In this study, we use non-negative matrix factorization to decompose datasets from Fe2O3 thin films with different Sn doping profiles on SnO2 and Si substrates. Case studies are presented to analyse spectral features including background models, signal integrals, peak positions and widths. Matlab codes are written to guide microscopists to perform these data analyses.
Collapse
Affiliation(s)
- Siyuan Zhang
- Max-Planck-Institut für Eisenforschung GmbH, Max-Planck-Straße 1, 40237 Düsseldorf, Germany
| | - Christina Scheu
- Max-Planck-Institut für Eisenforschung GmbH, Max-Planck-Straße 1, 40237 Düsseldorf, Germany.,Materials Analytics, RWTH Aachen University, Kopernikusstraße 10, 52074 Aachen, Germany
| |
Collapse
|
4
|
Fujita N, Hasnip PJ, Probert MIJ, Yuan J. Theoretical study of core-loss electron energy-loss spectroscopy at graphene nanoribbon edges. JOURNAL OF PHYSICS. CONDENSED MATTER : AN INSTITUTE OF PHYSICS JOURNAL 2015; 27:305301. [PMID: 26173149 DOI: 10.1088/0953-8984/27/30/305301] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/04/2023]
Abstract
A systematic study of simulated atomic-resolution electronic energy-loss spectroscopy (EELS) for different graphene nanoribbons (GNRs) is presented. The results of ab initio studies of carbon [Formula: see text] core-loss EELS on GNRs with different ribbon edge structures and different hydrogen terminations show that theoretical core-loss EELS can distinguish key structural features at the atomic scale. In addition, the combination of polarized core-loss EELS with symmetry resolved electronic partial density of states calculations can be used to identify the origins of all the primary features in the spectra. For example, the nature of the GNR edge structure (armchair, zigzag, etc) can be identified, along with the degree of hydrogenation. Hence it is possible to use the combination of ab initio calculations with high resolution, high energy transmission core-loss EELS experiments to determine the local atomic arrangement and chemical bonding states (i.e. a structural fingerprint) in GNRs, which is essential for future practical applications of graphene.
Collapse
Affiliation(s)
- N Fujita
- Simulation and Analysis R&D Center, Canon Inc. 30-2, Shimomaruko 3-chome, Ohta-Ku, Tokyo 146-8501, Japan
| | | | | | | |
Collapse
|
5
|
Mapping defects in a carbon nanotube by momentum transfer dependent electron energy loss spectromicroscopy. Ultramicroscopy 2012. [DOI: 10.1016/j.ultramic.2011.11.017] [Citation(s) in RCA: 15] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
|
6
|
Zhao Y, Feltes TE, Regalbuto JR, Meyer RJ, Klie RF. In-Situ Electron Energy Loss Spectroscopy Study of Mn-Promoted Co/TiO2 Fischer–Tropsch Catalysts. Catal Letters 2011. [DOI: 10.1007/s10562-011-0559-5] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
|
7
|
Allen F, Watanabe M, Lee Z, Balsara N, Minor A. Chemical mapping of a block copolymer electrolyte by low-loss EFTEM spectrum-imaging and principal component analysis. Ultramicroscopy 2011; 111:239-44. [DOI: 10.1016/j.ultramic.2010.11.035] [Citation(s) in RCA: 28] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/21/2010] [Revised: 11/16/2010] [Accepted: 11/23/2010] [Indexed: 11/26/2022]
|
8
|
Yakovlev S, Misra M, Shi S, Firlar E, Libera M. Quantitative nanoscale water mapping in frozen-hydrated skin by low-loss electron energy-loss spectroscopy. Ultramicroscopy 2010; 110:866-76. [DOI: 10.1016/j.ultramic.2010.03.014] [Citation(s) in RCA: 32] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/18/2009] [Revised: 03/13/2010] [Accepted: 03/26/2010] [Indexed: 11/30/2022]
|