Disentangling multiple scattering with deep learning: application to strain mapping from electron diffraction patterns

Implementation of a fast, robust, and fully-automated pipeline for crystal structure determination and underlying strain mapping for crystalline materials is important for many technological applications. Scanning electron nanodiffraction offers a procedure for identifying and collecting strain maps...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Munshi, Joydeep, Rakowski, Alexander, Savitzky, Benjamin H, Zeltmann, Steven E, Ciston, Jim, Henderson, Matthew, Cholia, Shreyas, Minor, Andrew M, Chan, Maria KY, Ophus, Colin
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Munshi, Joydeep
Rakowski, Alexander
Savitzky, Benjamin H
Zeltmann, Steven E
Ciston, Jim
Henderson, Matthew
Cholia, Shreyas
Minor, Andrew M
Chan, Maria KY
Ophus, Colin
description Implementation of a fast, robust, and fully-automated pipeline for crystal structure determination and underlying strain mapping for crystalline materials is important for many technological applications. Scanning electron nanodiffraction offers a procedure for identifying and collecting strain maps with good accuracy and high spatial resolutions. However, the application of this technique is limited, particularly in thick samples where the electron beam can undergo multiple scattering, which introduces signal nonlinearities. Deep learning methods have the potential to invert these complex signals, but previous implementations are often trained only on specific crystal systems or a small subset of the crystal structure and microscope parameter phase space. In this study, we implement a Fourier space, complex-valued deep neural network called FCU-Net, to invert highly nonlinear electron diffraction patterns into the corresponding quantitative structure factor images. We trained the FCU-Net using over 200,000 unique simulated dynamical diffraction patterns which include many different combinations of crystal structures, orientations, thicknesses, microscope parameters, and common experimental artifacts. We evaluated the trained FCU-Net model against simulated and experimental 4D-STEM diffraction datasets, where it substantially out-performs conventional analysis methods. Our simulated diffraction pattern library, implementation of FCU-Net, and trained model weights are freely available in open source repositories, and can be adapted to many different diffraction measurement problems.
doi_str_mv 10.48550/arxiv.2202.00204
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2202_00204</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2202_00204</sourcerecordid><originalsourceid>FETCH-LOGICAL-a674-4aebf6329e374ba88612a9dda30b247ab234cf1355b3103246e370cb8e301f233</originalsourceid><addsrcrecordid>eNotkMtOwzAQRb1hgQofwAr_QILjcR7tDpWnVIlN99E4GbeWHMdyTIG_JwmsRjpz5kpzGbsrRK6ashQPGL_tJZdSyFwIKdQ1uzzZiXxCf3LWn_jw6ZINjvjUYUoUF_Zl05n3RIE7wuhntOMYgrOzYkfP08inFNF6Psx4uTBxHDg56lKc9701JmK3umFN9dMNuzLoJrr9nxt2fHk-7t-yw8fr-_7xkGFVq0whaVOB3BLUSmPTVIXEbd8jCC1VjVqC6kwBZamhECBVNYui0w2BKIwE2LD7v9j18TZEO2D8aZcC2rUA-AV9xli-</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Disentangling multiple scattering with deep learning: application to strain mapping from electron diffraction patterns</title><source>arXiv.org</source><creator>Munshi, Joydeep ; Rakowski, Alexander ; Savitzky, Benjamin H ; Zeltmann, Steven E ; Ciston, Jim ; Henderson, Matthew ; Cholia, Shreyas ; Minor, Andrew M ; Chan, Maria KY ; Ophus, Colin</creator><creatorcontrib>Munshi, Joydeep ; Rakowski, Alexander ; Savitzky, Benjamin H ; Zeltmann, Steven E ; Ciston, Jim ; Henderson, Matthew ; Cholia, Shreyas ; Minor, Andrew M ; Chan, Maria KY ; Ophus, Colin</creatorcontrib><description>Implementation of a fast, robust, and fully-automated pipeline for crystal structure determination and underlying strain mapping for crystalline materials is important for many technological applications. Scanning electron nanodiffraction offers a procedure for identifying and collecting strain maps with good accuracy and high spatial resolutions. However, the application of this technique is limited, particularly in thick samples where the electron beam can undergo multiple scattering, which introduces signal nonlinearities. Deep learning methods have the potential to invert these complex signals, but previous implementations are often trained only on specific crystal systems or a small subset of the crystal structure and microscope parameter phase space. In this study, we implement a Fourier space, complex-valued deep neural network called FCU-Net, to invert highly nonlinear electron diffraction patterns into the corresponding quantitative structure factor images. We trained the FCU-Net using over 200,000 unique simulated dynamical diffraction patterns which include many different combinations of crystal structures, orientations, thicknesses, microscope parameters, and common experimental artifacts. We evaluated the trained FCU-Net model against simulated and experimental 4D-STEM diffraction datasets, where it substantially out-performs conventional analysis methods. Our simulated diffraction pattern library, implementation of FCU-Net, and trained model weights are freely available in open source repositories, and can be adapted to many different diffraction measurement problems.</description><identifier>DOI: 10.48550/arxiv.2202.00204</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition ; Physics - Applied Physics ; Physics - Materials Science</subject><creationdate>2022-01</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2202.00204$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2202.00204$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Munshi, Joydeep</creatorcontrib><creatorcontrib>Rakowski, Alexander</creatorcontrib><creatorcontrib>Savitzky, Benjamin H</creatorcontrib><creatorcontrib>Zeltmann, Steven E</creatorcontrib><creatorcontrib>Ciston, Jim</creatorcontrib><creatorcontrib>Henderson, Matthew</creatorcontrib><creatorcontrib>Cholia, Shreyas</creatorcontrib><creatorcontrib>Minor, Andrew M</creatorcontrib><creatorcontrib>Chan, Maria KY</creatorcontrib><creatorcontrib>Ophus, Colin</creatorcontrib><title>Disentangling multiple scattering with deep learning: application to strain mapping from electron diffraction patterns</title><description>Implementation of a fast, robust, and fully-automated pipeline for crystal structure determination and underlying strain mapping for crystalline materials is important for many technological applications. Scanning electron nanodiffraction offers a procedure for identifying and collecting strain maps with good accuracy and high spatial resolutions. However, the application of this technique is limited, particularly in thick samples where the electron beam can undergo multiple scattering, which introduces signal nonlinearities. Deep learning methods have the potential to invert these complex signals, but previous implementations are often trained only on specific crystal systems or a small subset of the crystal structure and microscope parameter phase space. In this study, we implement a Fourier space, complex-valued deep neural network called FCU-Net, to invert highly nonlinear electron diffraction patterns into the corresponding quantitative structure factor images. We trained the FCU-Net using over 200,000 unique simulated dynamical diffraction patterns which include many different combinations of crystal structures, orientations, thicknesses, microscope parameters, and common experimental artifacts. We evaluated the trained FCU-Net model against simulated and experimental 4D-STEM diffraction datasets, where it substantially out-performs conventional analysis methods. Our simulated diffraction pattern library, implementation of FCU-Net, and trained model weights are freely available in open source repositories, and can be adapted to many different diffraction measurement problems.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Physics - Applied Physics</subject><subject>Physics - Materials Science</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotkMtOwzAQRb1hgQofwAr_QILjcR7tDpWnVIlN99E4GbeWHMdyTIG_JwmsRjpz5kpzGbsrRK6ashQPGL_tJZdSyFwIKdQ1uzzZiXxCf3LWn_jw6ZINjvjUYUoUF_Zl05n3RIE7wuhntOMYgrOzYkfP08inFNF6Psx4uTBxHDg56lKc9701JmK3umFN9dMNuzLoJrr9nxt2fHk-7t-yw8fr-_7xkGFVq0whaVOB3BLUSmPTVIXEbd8jCC1VjVqC6kwBZamhECBVNYui0w2BKIwE2LD7v9j18TZEO2D8aZcC2rUA-AV9xli-</recordid><startdate>20220131</startdate><enddate>20220131</enddate><creator>Munshi, Joydeep</creator><creator>Rakowski, Alexander</creator><creator>Savitzky, Benjamin H</creator><creator>Zeltmann, Steven E</creator><creator>Ciston, Jim</creator><creator>Henderson, Matthew</creator><creator>Cholia, Shreyas</creator><creator>Minor, Andrew M</creator><creator>Chan, Maria KY</creator><creator>Ophus, Colin</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20220131</creationdate><title>Disentangling multiple scattering with deep learning: application to strain mapping from electron diffraction patterns</title><author>Munshi, Joydeep ; Rakowski, Alexander ; Savitzky, Benjamin H ; Zeltmann, Steven E ; Ciston, Jim ; Henderson, Matthew ; Cholia, Shreyas ; Minor, Andrew M ; Chan, Maria KY ; Ophus, Colin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a674-4aebf6329e374ba88612a9dda30b247ab234cf1355b3103246e370cb8e301f233</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Physics - Applied Physics</topic><topic>Physics - Materials Science</topic><toplevel>online_resources</toplevel><creatorcontrib>Munshi, Joydeep</creatorcontrib><creatorcontrib>Rakowski, Alexander</creatorcontrib><creatorcontrib>Savitzky, Benjamin H</creatorcontrib><creatorcontrib>Zeltmann, Steven E</creatorcontrib><creatorcontrib>Ciston, Jim</creatorcontrib><creatorcontrib>Henderson, Matthew</creatorcontrib><creatorcontrib>Cholia, Shreyas</creatorcontrib><creatorcontrib>Minor, Andrew M</creatorcontrib><creatorcontrib>Chan, Maria KY</creatorcontrib><creatorcontrib>Ophus, Colin</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Munshi, Joydeep</au><au>Rakowski, Alexander</au><au>Savitzky, Benjamin H</au><au>Zeltmann, Steven E</au><au>Ciston, Jim</au><au>Henderson, Matthew</au><au>Cholia, Shreyas</au><au>Minor, Andrew M</au><au>Chan, Maria KY</au><au>Ophus, Colin</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Disentangling multiple scattering with deep learning: application to strain mapping from electron diffraction patterns</atitle><date>2022-01-31</date><risdate>2022</risdate><abstract>Implementation of a fast, robust, and fully-automated pipeline for crystal structure determination and underlying strain mapping for crystalline materials is important for many technological applications. Scanning electron nanodiffraction offers a procedure for identifying and collecting strain maps with good accuracy and high spatial resolutions. However, the application of this technique is limited, particularly in thick samples where the electron beam can undergo multiple scattering, which introduces signal nonlinearities. Deep learning methods have the potential to invert these complex signals, but previous implementations are often trained only on specific crystal systems or a small subset of the crystal structure and microscope parameter phase space. In this study, we implement a Fourier space, complex-valued deep neural network called FCU-Net, to invert highly nonlinear electron diffraction patterns into the corresponding quantitative structure factor images. We trained the FCU-Net using over 200,000 unique simulated dynamical diffraction patterns which include many different combinations of crystal structures, orientations, thicknesses, microscope parameters, and common experimental artifacts. We evaluated the trained FCU-Net model against simulated and experimental 4D-STEM diffraction datasets, where it substantially out-performs conventional analysis methods. Our simulated diffraction pattern library, implementation of FCU-Net, and trained model weights are freely available in open source repositories, and can be adapted to many different diffraction measurement problems.</abstract><doi>10.48550/arxiv.2202.00204</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2202.00204
ispartof
issn
language eng
recordid cdi_arxiv_primary_2202_00204
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
Physics - Applied Physics
Physics - Materials Science
title Disentangling multiple scattering with deep learning: application to strain mapping from electron diffraction patterns
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T07%3A32%3A42IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Disentangling%20multiple%20scattering%20with%20deep%20learning:%20application%20to%20strain%20mapping%20from%20electron%20diffraction%20patterns&rft.au=Munshi,%20Joydeep&rft.date=2022-01-31&rft_id=info:doi/10.48550/arxiv.2202.00204&rft_dat=%3Carxiv_GOX%3E2202_00204%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true