000845666 001__ 845666
000845666 005__ 20210129233543.0
000845666 0247_ $$2doi$$a10.1016/j.isprsjprs.2017.07.003
000845666 0247_ $$2ISSN$$a0924-2716
000845666 0247_ $$2ISSN$$a1872-8235
000845666 0247_ $$2Handle$$a2128/18767
000845666 0247_ $$2WOS$$aWOS:000411775100006
000845666 037__ $$aFZJ-2018-02879
000845666 041__ $$aEnglish
000845666 082__ $$a550
000845666 1001_ $$0P:(DE-HGF)0$$aSchmitter, P.$$b0$$eCorresponding author
000845666 245__ $$aUnsupervised domain adaptation for early detection of drought stress in hyperspectral images
000845666 260__ $$aAmsterdam [u.a.]$$bElsevier$$c2017
000845666 3367_ $$2DRIVER$$aarticle
000845666 3367_ $$2DataCite$$aOutput Types/Journal article
000845666 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1527687931_27516
000845666 3367_ $$2BibTeX$$aARTICLE
000845666 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000845666 3367_ $$00$$2EndNote$$aJournal Article
000845666 520__ $$aHyperspectral images can be used to uncover physiological processes in plants if interpreted properly. Machine Learning methods such as Support Vector Machines (SVM) and Random Forests have been applied to estimate development of biomass and detect and predict plant diseases and drought stress. One basic requirement of machine learning implies, that training and testing is done in the same domain and the same distribution. Different genotypes, environmental conditions, illumination and sensors violate this requirement in most practical circumstances. Here, we present an approach, which enables the detection of physiological processes by transferring the prior knowledge within an existing model into a related target domain, where no label information is available. We propose a two-step transformation of the target features, which enables a direct application of an existing model. The transformation is evaluated by an objective function including additional prior knowledge about classification and physiological processes in plants. We have applied the approach to three sets of hyperspectral images, which were acquired with different plant species in different environments observed with different sensors. It is shown, that a classification model, derived on one of the sets, delivers satisfying classification results on the transformed features of the other data sets. Furthermore, in all cases early non-invasive detection of drought stress was possible.
000845666 536__ $$0G:(DE-HGF)POF3-582$$a582 - Plant Science (POF3-582)$$cPOF3-582$$fPOF III$$x0
000845666 588__ $$aDataset connected to CrossRef
000845666 7001_ $$0P:(DE-HGF)0$$aSteinrücken, J.$$b1
000845666 7001_ $$0P:(DE-HGF)0$$aRömer, C.$$b2
000845666 7001_ $$0P:(DE-HGF)0$$aBallvora, A.$$b3
000845666 7001_ $$0P:(DE-HGF)0$$aLéon, J.$$b4
000845666 7001_ $$0P:(DE-Juel1)129388$$aRascher, U.$$b5$$ufzj
000845666 7001_ $$0P:(DE-HGF)0$$aPlümer, L.$$b6
000845666 773__ $$0PERI:(DE-600)2012663-3$$a10.1016/j.isprsjprs.2017.07.003$$gVol. 131, p. 65 - 76$$p65 - 76$$tISPRS journal of photogrammetry and remote sensing$$v131$$x0924-2716$$y2017
000845666 8564_ $$uhttps://juser.fz-juelich.de/record/845666/files/1-s2.0-S092427161730271X-main.pdf$$yOpenAccess
000845666 8564_ $$uhttps://juser.fz-juelich.de/record/845666/files/1-s2.0-S092427161730271X-main.gif?subformat=icon$$xicon$$yOpenAccess
000845666 8564_ $$uhttps://juser.fz-juelich.de/record/845666/files/1-s2.0-S092427161730271X-main.jpg?subformat=icon-1440$$xicon-1440$$yOpenAccess
000845666 8564_ $$uhttps://juser.fz-juelich.de/record/845666/files/1-s2.0-S092427161730271X-main.jpg?subformat=icon-180$$xicon-180$$yOpenAccess
000845666 8564_ $$uhttps://juser.fz-juelich.de/record/845666/files/1-s2.0-S092427161730271X-main.jpg?subformat=icon-640$$xicon-640$$yOpenAccess
000845666 8564_ $$uhttps://juser.fz-juelich.de/record/845666/files/1-s2.0-S092427161730271X-main.pdf?subformat=pdfa$$xpdfa$$yOpenAccess
000845666 909CO $$ooai:juser.fz-juelich.de:845666$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
000845666 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)129388$$aForschungszentrum Jülich$$b5$$kFZJ
000845666 9131_ $$0G:(DE-HGF)POF3-582$$1G:(DE-HGF)POF3-580$$2G:(DE-HGF)POF3-500$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lKey Technologies for the Bioeconomy$$vPlant Science$$x0
000845666 9141_ $$y2018
000845666 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS
000845666 915__ $$0StatID:(DE-HGF)1160$$2StatID$$aDBCoverage$$bCurrent Contents - Engineering, Computing and Technology
000845666 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search
000845666 915__ $$0LIC:(DE-HGF)CCBYNCND4$$2HGFVOC$$aCreative Commons Attribution-NonCommercial-NoDerivs CC BY-NC-ND 4.0
000845666 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bISPRS J PHOTOGRAMM : 2015
000845666 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection
000845666 915__ $$0StatID:(DE-HGF)0111$$2StatID$$aWoS$$bScience Citation Index Expanded
000845666 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5
000845666 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000845666 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC
000845666 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline
000845666 915__ $$0StatID:(DE-HGF)0420$$2StatID$$aNationallizenz
000845666 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bThomson Reuters Master Journal List
000845666 920__ $$lyes
000845666 9201_ $$0I:(DE-Juel1)IBG-2-20101118$$kIBG-2$$lPflanzenwissenschaften$$x0
000845666 980__ $$ajournal
000845666 980__ $$aVDB
000845666 980__ $$aUNRESTRICTED
000845666 980__ $$aI:(DE-Juel1)IBG-2-20101118
000845666 9801_ $$aFullTexts