000916745 001__ 916745
000916745 005__ 20231027114350.0
000916745 0247_ $$2doi$$a10.1109/JSTARS.2022.3231380
000916745 0247_ $$2ISSN$$a1939-1404
000916745 0247_ $$2ISSN$$a2151-1535
000916745 0247_ $$2Handle$$a2128/33664
000916745 0247_ $$2pmid$$a36644656
000916745 0247_ $$2WOS$$aWOS:000981757000002
000916745 037__ $$aFZJ-2023-00073
000916745 041__ $$aEnglish
000916745 082__ $$a520
000916745 1001_ $$00000-0002-0537-6803$$aMorata, Miguel$$b0$$eCorresponding author
000916745 245__ $$aNeural Network Emulation of Synthetic Hyperspectral Sentinel-2-like Imagery with Uncertainty
000916745 260__ $$aNew York, NY$$bIEEE$$c2023
000916745 3367_ $$2DRIVER$$aarticle
000916745 3367_ $$2DataCite$$aOutput Types/Journal article
000916745 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1673958744_27886
000916745 3367_ $$2BibTeX$$aARTICLE
000916745 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000916745 3367_ $$00$$2EndNote$$aJournal Article
000916745 520__ $$aHyperspectral satellite imagery provides highly-resolved spectral information for large areas and can provide vital information. However, only a few imaging spectrometer missions are currently in operation. Aiming to generate synthetic satellite-based hyperspectral imagery potentially covering any region, we explored the possibility of applying statistical learning, i.e. emulation. Based on the relationship of a Sentinel-2 (S2) scene and a hyperspectral HyPlant airborne image, this work demonstrates the possibility to emulate a hyperspectral S2-like image. We tested the role of different machine learning regression algorithms (MLRA) and varied the image-extracted training dataset size. We found superior performance of Neural Network (NN) as opposed to the other algorithms when trained with large datasets (up to 100'000 samples). The developed emulator was then applied to the L2A (bottom-of-atmosphere reflectance) S2 subset, and the obtained S2-like hyperspectral reflectance scene was evaluated. The validation of emulated against reference spectra demonstrated the potential of the technique. R2 values between 0.75-0.9 and NRMSE between 2-5% across the full 402-2356 nm range were obtained. Moreover, epistemic uncertainty is obtained using the dropout technique, revealing spatial fidelity of the emulated scene. We obtained highest SD values of 0.05 (CV of 8%) in clouds and values below 0.01 (CV of 7%) in vegetation land covers. Finally, the emulator was applied to an entire S2 tile (5490x5490 pixels) to generate a hyperspectral reflectance datacube with the texture of S2 (60Gb, at a speed of 0.14sec/10000pixels). As the emulator can convert any S2 tile into a hyperspectral image, such scenes give perspectives how future satellite imaging spectroscopy will look like.
000916745 536__ $$0G:(DE-HGF)POF4-2173$$a2173 - Agro-biogeosystems: controls, feedbacks and impact (POF4-217)$$cPOF4-217$$fPOF IV$$x0
000916745 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
000916745 7001_ $$0P:(DE-Juel1)172711$$aSiegmann, Bastian$$b1
000916745 7001_ $$00000-0002-8258-4454$$aPerez-Suay, Adrian$$b2
000916745 7001_ $$00000-0002-7693-0891$$aGarcia-Soria, Jose Luis$$b3
000916745 7001_ $$00000-0003-3188-1448$$aRivera-Caicedo, Juan Pablo$$b4
000916745 7001_ $$00000-0002-6313-2081$$aVerrelst, Jochem$$b5
000916745 773__ $$0PERI:(DE-600)2457423-5$$a10.1109/JSTARS.2022.3231380$$gp. 1 - 11$$p762-772$$tIEEE journal of selected topics in applied earth observations and remote sensing$$v16$$x1939-1404$$y2023
000916745 8564_ $$uhttps://juser.fz-juelich.de/record/916745/files/Neural_Network_Emulation_of_Synthetic_Hyperspectral_Sentinel-2-Like_Imagery_With_Uncertainty.pdf$$yOpenAccess
000916745 909CO $$ooai:juser.fz-juelich.de:916745$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
000916745 9101_ $$0I:(DE-HGF)0$$60000-0002-0537-6803$$aExternal Institute$$b0$$kExtern
000916745 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)172711$$aForschungszentrum Jülich$$b1$$kFZJ
000916745 9101_ $$0I:(DE-HGF)0$$60000-0002-8258-4454$$aExternal Institute$$b2$$kExtern
000916745 9101_ $$0I:(DE-HGF)0$$60000-0002-7693-0891$$aExternal Institute$$b3$$kExtern
000916745 9101_ $$0I:(DE-HGF)0$$60000-0003-3188-1448$$aExternal Institute$$b4$$kExtern
000916745 9101_ $$0I:(DE-HGF)0$$60000-0002-6313-2081$$aExternal Institute$$b5$$kExtern
000916745 9131_ $$0G:(DE-HGF)POF4-217$$1G:(DE-HGF)POF4-210$$2G:(DE-HGF)POF4-200$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-2173$$aDE-HGF$$bForschungsbereich Erde und Umwelt$$lErde im Wandel – Unsere Zukunft nachhaltig gestalten$$vFür eine nachhaltige Bio-Ökonomie – von Ressourcen zu Produkten$$x0
000916745 9141_ $$y2023
000916745 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2022-11-17
000916745 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000916745 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2022-11-17
000916745 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2022-11-17
000916745 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000916745 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2022-11-17
000916745 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2023-05-02T11:24:31Z
000916745 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2023-05-02T11:24:31Z
000916745 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Anonymous peer review$$d2023-05-02T11:24:31Z
000916745 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2023-10-25
000916745 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2023-10-25
000916745 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2023-10-25
000916745 915__ $$0StatID:(DE-HGF)1150$$2StatID$$aDBCoverage$$bCurrent Contents - Physical, Chemical and Earth Sciences$$d2023-10-25
000916745 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bIEEE J-STARS : 2022$$d2023-10-25
000916745 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2023-10-25
000916745 915__ $$0StatID:(DE-HGF)9905$$2StatID$$aIF >= 5$$bIEEE J-STARS : 2022$$d2023-10-25
000916745 920__ $$lyes
000916745 9201_ $$0I:(DE-Juel1)IBG-2-20101118$$kIBG-2$$lPflanzenwissenschaften$$x0
000916745 980__ $$ajournal
000916745 980__ $$aVDB
000916745 980__ $$aUNRESTRICTED
000916745 980__ $$aI:(DE-Juel1)IBG-2-20101118
000916745 9801_ $$aFullTexts