Unsupervised machine learning applied to scanning precession electron diffraction data
Open Access
- 15 March 2019
- journal article
- research article
- Published by Springer Nature in Advanced Structural and Chemical Imaging
- Vol. 5 (1) , 3
Abstract
Scanning precession electron diffraction involves the acquisition of a two-dimensional precession electron diffraction pattern at every probe position in a two-dimensional scan. The data typically comprise many more diffraction patterns than the number of distinct microstructural volume elements (e.g. crystals) in the region sampled. A dimensionality reduction, ideally to one representative diffraction pattern per distinct element, may then be sought. Further, some diffraction patterns will contain contributions from multiple crystals sampled along the beam path, which may be unmixed by harnessing this oversampling. Here, we report on the application of unsupervised machine learning methods to achieve both dimensionality reduction and signal unmixing. Potential artefacts are discussed and precession electron diffraction is demonstrated to improve results by reducing the impact of bending and dynamical diffraction so that the data better approximate the case in which each crystal yields a given diffraction pattern.Keywords
Funding Information
- Engineering and Physical Sciences Research Council (EP/R008779/1)
- FP7 Ideas: European Research Council (291522-3DIMAGE)
- Seventh Framework Programme (312483-ESTEEM2)
- Royal Society (RG140453, UF130286)
This publication has 35 references indexed in Scilit:
- The evolution of precipitate crystal structures in an Al-Mg-Si(-Cu) alloy studied by a combined HAADF-STEM and SPED approachMaterials Characterization, 2018
- Sparse modeling of EELS and EDX spectral imaging data by nonnegative matrix factorizationUltramicroscopy, 2016
- A New Method for Determining the Composition of Core-Shell Nanoparticles via Dual-EDX+EELS Spectrum ImagingParticle & Particle Systems Characterization, 2016
- Blind source separation aided characterization of the γ′ strengthening phase in an advanced nickel-based superalloy by spectroscopic 4D electron microscopyActa Materialia, 2016
- The rapidly changing face of electron microscopyChemical Physics Letters, 2015
- Scanning precession electron tomography for three-dimensional nanoscale orientation imaging and crystallographic analysisNature Communications, 2015
- Multicomponent Signal Unmixing from Nanoheterostructures: Overcoming the Traditional Challenges of Nanoscale X-ray Analysis via Machine LearningNano Letters, 2015
- Three-dimensional imaging of localized surface plasmon resonances of metal nanoparticlesNature, 2013
- Mapping titanium and tin oxide phases using EELS: An application of independent component analysisUltramicroscopy, 2011
- Coupled microstructural observations and local texture measurements with an automated crystallographic orientation mapping tool attached to a temMaterialwissenschaft und Werkstofftechnik, 2005