Versatile domain mapping of scanning electron nanobeam diffraction datasets utilising variational autoencoders
Abstract Characterisation of structure across the nanometre scale is key to bridging the gap between the local atomic environment and macro-scale and can be achieved by means of scanning electron nanobeam diffraction (SEND). As a technique, SEND allows for a broad range of samples, due to being rela...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-01-01
|
| Series: | npj Computational Materials |
| Online Access: | https://doi.org/10.1038/s41524-022-00960-y |
| _version_ | 1797864077965393920 |
|---|---|
| author | A. Bridger W. I. F. David T. J. Wood M. Danaie K. T. Butler |
| author_facet | A. Bridger W. I. F. David T. J. Wood M. Danaie K. T. Butler |
| author_sort | A. Bridger |
| collection | DOAJ |
| description | Abstract Characterisation of structure across the nanometre scale is key to bridging the gap between the local atomic environment and macro-scale and can be achieved by means of scanning electron nanobeam diffraction (SEND). As a technique, SEND allows for a broad range of samples, due to being relatively tolerant of specimen thickness with low electron dosage. This, coupled with the capacity for automation of data collection over wide areas, allows for statistically representative probing of the microstructure. This paper outlines a versatile, data-driven approach for producing domain maps, and a statistical approach for assessing their applicability. The workflow utilises a Variational AutoEncoder to identify the sources of variance in the diffraction signal, and this, in combination with clustering techniques, is used to produce domain maps. This approach is agnostic to domain crystallinity, requires no prior knowledge of crystal structure, and does not require simulation of a library of expected diffraction patterns. |
| first_indexed | 2024-04-09T22:45:46Z |
| format | Article |
| id | doaj.art-4ef03ac5f64d427c9cbcae8ff5e4297e |
| institution | Directory Open Access Journal |
| issn | 2057-3960 |
| language | English |
| last_indexed | 2024-04-09T22:45:46Z |
| publishDate | 2023-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Computational Materials |
| spelling | doaj.art-4ef03ac5f64d427c9cbcae8ff5e4297e2023-03-22T11:50:32ZengNature Portfolionpj Computational Materials2057-39602023-01-019111810.1038/s41524-022-00960-yVersatile domain mapping of scanning electron nanobeam diffraction datasets utilising variational autoencodersA. Bridger0W. I. F. David1T. J. Wood2M. Danaie3K. T. Butler4Inorganic Chemistry Laboratory, University of OxfordInorganic Chemistry Laboratory, University of OxfordISIS Neutron and Muon Spallation Source, STFC Rutherford Appleton LaboratoryElectron Physical Science Imaging Centre, Diamond Light Source Ltd.School of Engineering and Materials Science, Queen Mary University of LondonAbstract Characterisation of structure across the nanometre scale is key to bridging the gap between the local atomic environment and macro-scale and can be achieved by means of scanning electron nanobeam diffraction (SEND). As a technique, SEND allows for a broad range of samples, due to being relatively tolerant of specimen thickness with low electron dosage. This, coupled with the capacity for automation of data collection over wide areas, allows for statistically representative probing of the microstructure. This paper outlines a versatile, data-driven approach for producing domain maps, and a statistical approach for assessing their applicability. The workflow utilises a Variational AutoEncoder to identify the sources of variance in the diffraction signal, and this, in combination with clustering techniques, is used to produce domain maps. This approach is agnostic to domain crystallinity, requires no prior knowledge of crystal structure, and does not require simulation of a library of expected diffraction patterns.https://doi.org/10.1038/s41524-022-00960-y |
| spellingShingle | A. Bridger W. I. F. David T. J. Wood M. Danaie K. T. Butler Versatile domain mapping of scanning electron nanobeam diffraction datasets utilising variational autoencoders npj Computational Materials |
| title | Versatile domain mapping of scanning electron nanobeam diffraction datasets utilising variational autoencoders |
| title_full | Versatile domain mapping of scanning electron nanobeam diffraction datasets utilising variational autoencoders |
| title_fullStr | Versatile domain mapping of scanning electron nanobeam diffraction datasets utilising variational autoencoders |
| title_full_unstemmed | Versatile domain mapping of scanning electron nanobeam diffraction datasets utilising variational autoencoders |
| title_short | Versatile domain mapping of scanning electron nanobeam diffraction datasets utilising variational autoencoders |
| title_sort | versatile domain mapping of scanning electron nanobeam diffraction datasets utilising variational autoencoders |
| url | https://doi.org/10.1038/s41524-022-00960-y |
| work_keys_str_mv | AT abridger versatiledomainmappingofscanningelectronnanobeamdiffractiondatasetsutilisingvariationalautoencoders AT wifdavid versatiledomainmappingofscanningelectronnanobeamdiffractiondatasetsutilisingvariationalautoencoders AT tjwood versatiledomainmappingofscanningelectronnanobeamdiffractiondatasetsutilisingvariationalautoencoders AT mdanaie versatiledomainmappingofscanningelectronnanobeamdiffractiondatasetsutilisingvariationalautoencoders AT ktbutler versatiledomainmappingofscanningelectronnanobeamdiffractiondatasetsutilisingvariationalautoencoders |