000905288 001__ 905288
000905288 005__ 20240712113145.0
000905288 0247_ $$2doi$$a10.1039/D1NR06435E
000905288 0247_ $$2ISSN$$a2040-3364
000905288 0247_ $$2ISSN$$a2040-3372
000905288 0247_ $$2Handle$$a2128/30300
000905288 0247_ $$2altmetric$$aaltmetric:117526502
000905288 0247_ $$2pmid$$apmid:34846412
000905288 0247_ $$2WOS$$aWOS:000723812900001
000905288 037__ $$aFZJ-2022-00559
000905288 082__ $$a600
000905288 1001_ $$0P:(DE-Juel1)188204$$aColliard-Granero, André$$b0
000905288 245__ $$aDeep learning for the automation of particle analysis in catalyst layers for polymer electrolyte fuel cells
000905288 260__ $$aCambridge$$bRSC Publ.$$c2022
000905288 3367_ $$2DRIVER$$aarticle
000905288 3367_ $$2DataCite$$aOutput Types/Journal article
000905288 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1676461577_10240
000905288 3367_ $$2BibTeX$$aARTICLE
000905288 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000905288 3367_ $$00$$2EndNote$$aJournal Article
000905288 520__ $$aThe rapidly growing use of imaging infrastructure in the energy materials domain drives significant data accumulation in terms of their amount and complexity. The applications of routine techniques for image processing in materials research are often ad hoc, indiscriminate, and empirical, which renders the crucial task of obtaining reliable metrics for quantifications obscure. Moreover, these techniques are expensive, slow, and often involve several preprocessing steps. This paper presents a novel deep learning-based approach for the high-throughput analysis of the particle size distributions from transmission electron microscopy (TEM) images of carbon-supported catalysts for polymer electrolyte fuel cells. A dataset of 40 high-resolution TEM images at different magnification levels, from 10 to 100 nm scales, was annotated manually. This dataset was used to train the U-Net model, with the StarDist formulation for the loss function, for the nanoparticle segmentation task. StarDist reached a precision of 86%, recall of 85%, and an F1-score of 85% by training on datasets as small as thirty images. The segmentation maps outperform models reported in the literature for a similar problem, and the results on particle size analyses agree well with manual particle size measurements, albeit at a significantly lower cost.
000905288 536__ $$0G:(DE-HGF)POF4-1231$$a1231 - Electrochemistry for Hydrogen (POF4-123)$$cPOF4-123$$fPOF IV$$x0
000905288 536__ $$0G:(DE-HGF)POF4-5112$$a5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x1
000905288 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
000905288 7001_ $$0P:(DE-HGF)0$$aBatool, Mariah$$b1
000905288 7001_ $$0P:(DE-HGF)0$$aJankovic, Jasna$$b2
000905288 7001_ $$0P:(DE-Juel1)158080$$aJitsev, Jenia$$b3$$ufzj
000905288 7001_ $$0P:(DE-Juel1)178034$$aEikerling, Michael H.$$b4
000905288 7001_ $$0P:(DE-Juel1)181057$$aMalek, Kourosh$$b5$$eCorresponding author
000905288 7001_ $$0P:(DE-Juel1)181059$$aEslamibidgoli, Mohammad Javad$$b6$$eCorresponding author
000905288 773__ $$0PERI:(DE-600)2515664-0$$a10.1039/D1NR06435E$$gVol. 14, no. 1, p. 10 - 18$$n1$$p10 - 18$$tNanoscale$$v14$$x2040-3364$$y2022
000905288 8564_ $$uhttps://juser.fz-juelich.de/record/905288/files/Invoice_INV_017301.pdf
000905288 8564_ $$uhttps://juser.fz-juelich.de/record/905288/files/Nanoscale_2021.pdf$$yPublished on 2021-11-24. Available in OpenAccess from 2022-11-24.
000905288 8564_ $$uhttps://juser.fz-juelich.de/record/905288/files/d1nr06435e.pdf$$yRestricted
000905288 8767_ $$8INV_017301$$92022-02-24$$d2022-03-09$$eCover$$jZahlung erfolgt$$zBelegnr. 1200178038; GBP 1000,-
000905288 909CO $$ooai:juser.fz-juelich.de:905288$$pdnbdelivery$$popenCost$$pVDB$$pdriver$$pOpenAPC$$popen_access$$popenaire
000905288 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)188204$$aForschungszentrum Jülich$$b0$$kFZJ
000905288 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)158080$$aForschungszentrum Jülich$$b3$$kFZJ
000905288 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)178034$$aForschungszentrum Jülich$$b4$$kFZJ
000905288 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)181057$$aForschungszentrum Jülich$$b5$$kFZJ
000905288 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)181059$$aForschungszentrum Jülich$$b6$$kFZJ
000905288 9131_ $$0G:(DE-HGF)POF4-123$$1G:(DE-HGF)POF4-120$$2G:(DE-HGF)POF4-100$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-1231$$aDE-HGF$$bForschungsbereich Energie$$lMaterialien und Technologien für die Energiewende (MTET)$$vChemische Energieträger$$x0
000905288 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5112$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x1
000905288 9141_ $$y2022
000905288 915__ $$0StatID:(DE-HGF)0530$$2StatID$$aEmbargoed OpenAccess
000905288 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2021-01-27
000905288 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2021-01-27
000905288 915__ $$0StatID:(DE-HGF)0430$$2StatID$$aNational-Konsortium$$d2022-11-12$$wger
000905288 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2022-11-12
000905288 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2022-11-12
000905288 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2022-11-12
000905288 915__ $$0StatID:(DE-HGF)1150$$2StatID$$aDBCoverage$$bCurrent Contents - Physical, Chemical and Earth Sciences$$d2022-11-12
000905288 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bNANOSCALE : 2021$$d2022-11-12
000905288 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2022-11-12
000905288 915__ $$0StatID:(DE-HGF)9905$$2StatID$$aIF >= 5$$bNANOSCALE : 2021$$d2022-11-12
000905288 920__ $$lyes
000905288 9201_ $$0I:(DE-Juel1)IEK-13-20190226$$kIEK-13$$lIEK-13$$x0
000905288 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x1
000905288 9801_ $$aAPC
000905288 9801_ $$aFullTexts
000905288 980__ $$ajournal
000905288 980__ $$aVDB
000905288 980__ $$aI:(DE-Juel1)IEK-13-20190226
000905288 980__ $$aI:(DE-Juel1)JSC-20090406
000905288 980__ $$aAPC
000905288 980__ $$aUNRESTRICTED
000905288 981__ $$aI:(DE-Juel1)IET-3-20190226