000902093 001__ 902093
000902093 005__ 20220930130329.0
000902093 0247_ $$2doi$$a10.1109/JSTARS.2021.3115604
000902093 0247_ $$2ISSN$$a1939-1404
000902093 0247_ $$2ISSN$$a2151-1535
000902093 0247_ $$2Handle$$a2128/28855
000902093 0247_ $$2WOS$$aWOS:000707442300013
000902093 037__ $$aFZJ-2021-04028
000902093 082__ $$a520
000902093 1001_ $$0P:(DE-Juel1)178695$$aSedona, Rocco$$b0
000902093 245__ $$aA High-Performance Multispectral Adaptation GAN for Harmonizing Dense Time Series of Landsat-8 and Sentinel-2 Images
000902093 260__ $$aNew York, NY$$bIEEE$$c2021
000902093 3367_ $$2DRIVER$$aarticle
000902093 3367_ $$2DataCite$$aOutput Types/Journal article
000902093 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1635428684_19920
000902093 3367_ $$2BibTeX$$aARTICLE
000902093 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000902093 3367_ $$00$$2EndNote$$aJournal Article
000902093 520__ $$aThe combination of data acquired by Landsat-8 and Sentinel-2 earth observation missions produces dense time series (TSs) of multispectral images that are essential for monitoring the dynamics of land-cover and land-use classes across the earth's surface with high temporal resolution. However, the optical sensors of the two missions have different spectral and spatial properties, thus they require a harmonization processing step before they can be exploited in remote sensing applications. In this work, we propose a workflow-based on a deep learning approach to harmonize these two products developed and deployed on an high-performance computing environment. In particular, we use a multispectral generative adversarial network with a U-Net generator and a PatchGan discriminator to integrate existing Landsat-8 TSs with data sensed by the Sentinel-2 mission. We show a qualitative and quantitative comparison with an existing physical method [National Aeronautics and Space Administration (NASA) Harmonized Landsat and Sentinel (HLS)] and analyze original and generated data in different experimental setups with the support of spectral distortion metrics. To demonstrate the effectiveness of the proposed approach, a crop type mapping task is addressed using the harmonized dense TS of images, which achieved an overall accuracy of 87.83% compared to 81.66% of the state-of-the-art method.
000902093 536__ $$0G:(DE-HGF)POF4-5112$$a5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
000902093 536__ $$0G:(EU-Grant)951733$$aAISee - AI- and Simulation-Based Engineering at Exascale (951733)$$c951733$$fH2020-INFRAEDI-2019-1$$x1
000902093 536__ $$0G:(EU-Grant)754304$$aDEEP-EST - DEEP - Extreme Scale Technologies (754304)$$c754304$$fH2020-FETHPC-2016$$x2
000902093 536__ $$0G:(EU-Grant)956748$$aADMIRE - Adaptive multi-tier intelligent data manager for Exascale (956748)$$c956748$$fH2020-JTI-EuroHPC-2019-1$$x3
000902093 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
000902093 7001_ $$0P:(DE-HGF)0$$aParis, Claudia$$b1
000902093 7001_ $$0P:(DE-Juel1)171343$$aCavallaro, Gabriele$$b2$$eCorresponding author
000902093 7001_ $$0P:(DE-HGF)0$$aBruzzone, Lorenzo$$b3
000902093 7001_ $$0P:(DE-Juel1)132239$$aRiedel, Morris$$b4
000902093 773__ $$0PERI:(DE-600)2457423-5$$a10.1109/JSTARS.2021.3115604$$gVol. 14, p. 10134 - 10146$$p10134 - 10146$$tIEEE journal of selected topics in applied earth observations and remote sensing$$v14$$x2151-1535$$y2021
000902093 8564_ $$uhttps://juser.fz-juelich.de/record/902093/files/Invoice_APC600261810_.pdf
000902093 8564_ $$uhttps://juser.fz-juelich.de/record/902093/files/A_High-Performance_Multispectral_Adaptation_GAN_for_Harmonizing_Dense_Time_Series_of_Landsat-8_and_Sentinel-2_Images.pdf$$yOpenAccess
000902093 8767_ $$8APC600261810$$92021-10-28$$d2021-11-02$$eAPC$$jZahlung erfolgt$$z1250 USD /Belegnr.: 1200173022
000902093 909CO $$ooai:juser.fz-juelich.de:902093$$popenCost$$pec_fundedresources$$pVDB$$pdriver$$pOpenAPC$$popen_access$$popenaire$$pdnbdelivery
000902093 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)178695$$aForschungszentrum Jülich$$b0$$kFZJ
000902093 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)171343$$aForschungszentrum Jülich$$b2$$kFZJ
000902093 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)132239$$aForschungszentrum Jülich$$b4$$kFZJ
000902093 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$$x0
000902093 9141_ $$y2021
000902093 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2021-02-03
000902093 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2021-02-03
000902093 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000902093 915__ $$0StatID:(DE-HGF)1150$$2StatID$$aDBCoverage$$bCurrent Contents - Physical, Chemical and Earth Sciences$$d2021-02-03
000902093 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2021-02-03
000902093 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2021-02-03
000902093 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5$$d2021-02-03
000902093 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000902093 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bIEEE J-STARS : 2019$$d2021-02-03
000902093 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2021-02-03
000902093 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2021-02-03
000902093 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
000902093 980__ $$ajournal
000902093 980__ $$aVDB
000902093 980__ $$aUNRESTRICTED
000902093 980__ $$aI:(DE-Juel1)JSC-20090406
000902093 980__ $$aAPC
000902093 9801_ $$aAPC
000902093 9801_ $$aFullTexts