000878382 001__ 878382
000878382 005__ 20240712100914.0
000878382 0247_ $$2doi$$a10.5194/amt-13-3661-2020
000878382 0247_ $$2ISSN$$a1867-1381
000878382 0247_ $$2ISSN$$a1867-8548
000878382 0247_ $$2Handle$$a2128/25512
000878382 0247_ $$2WOS$$aWOS:000548519300003
000878382 037__ $$aFZJ-2020-02819
000878382 082__ $$a550
000878382 1001_ $$0P:(DE-Juel1)178695$$aSedona, Rocco$$b0$$eCorresponding author
000878382 245__ $$aExploration of machine learning methods for the classification of infrared limb spectra of polar stratospheric clouds
000878382 260__ $$aKatlenburg-Lindau$$bCopernicus$$c2020
000878382 3367_ $$2DRIVER$$aarticle
000878382 3367_ $$2DataCite$$aOutput Types/Journal article
000878382 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1604414601_754
000878382 3367_ $$2BibTeX$$aARTICLE
000878382 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000878382 3367_ $$00$$2EndNote$$aJournal Article
000878382 520__ $$aPolar stratospheric clouds (PSCs) play a key role in polar ozone depletion in the stratosphere. Improved observations and continuous monitoring of PSCs can help to validate and improve chemistry–climate models that are used to predict the evolution of the polar ozone hole. In this paper, we explore the potential of applying machine learning (ML) methods to classify PSC observations of infrared limb sounders. Two datasets were considered in this study. The first dataset is a collection of infrared spectra captured in Northern Hemisphere winter 2006/2007 and Southern Hemisphere winter 2009 by the Michelson Interferometer for Passive Atmospheric Sounding (MIPAS) instrument on board the European Space Agency's (ESA) Envisat satellite. The second dataset is the cloud scenario database (CSDB) of simulated MIPAS spectra. We first performed an initial analysis to assess the basic characteristics of the CSDB and to decide which features to extract from it. Here, we focused on an approach using brightness temperature differences (BTDs). From both the measured and the simulated infrared spectra, more than 10 000 BTD features were generated. Next, we assessed the use of ML methods for the reduction of the dimensionality of this large feature space using principal component analysis (PCA) and kernel principal component analysis (KPCA) followed by a classification with the support vector machine (SVM). The random forest (RF) technique, which embeds the feature selection step, has also been used as a classifier. All methods were found to be suitable to retrieve information on the composition of PSCs. Of these, RF seems to be the most promising method, being less prone to overfitting and producing results that agree well with established results based on conventional classification methods.
000878382 536__ $$0G:(DE-HGF)POF3-244$$a244 - Composition and dynamics of the upper troposphere and middle atmosphere (POF3-244)$$cPOF3-244$$fPOF III$$x0
000878382 536__ $$0G:(DE-HGF)POF3-511$$a511 - Computational Science and Mathematical Methods (POF3-511)$$cPOF3-511$$fPOF III$$x1
000878382 536__ $$0G:(DE-HGF)POF3-512$$a512 - Data-Intensive Science and Federated Computing (POF3-512)$$cPOF3-512$$fPOF III$$x2
000878382 588__ $$aDataset connected to CrossRef
000878382 7001_ $$0P:(DE-Juel1)129125$$aHoffmann, Lars$$b1
000878382 7001_ $$0P:(DE-Juel1)129154$$aSpang, Reinhold$$b2
000878382 7001_ $$0P:(DE-Juel1)171343$$aCavallaro, Gabriele$$b3
000878382 7001_ $$0P:(DE-Juel1)129121$$aGriessbach, Sabine$$b4
000878382 7001_ $$00000-0002-4174-9531$$aHöpfner, Michael$$b5
000878382 7001_ $$00000-0003-2472-5201$$aBook, Matthias$$b6
000878382 7001_ $$0P:(DE-Juel1)132239$$aRiedel, Morris$$b7
000878382 773__ $$0PERI:(DE-600)2505596-3$$a10.5194/amt-13-3661-2020$$gVol. 13, no. 7, p. 3661 - 3682$$n7$$p3661 - 3682$$tAtmospheric measurement techniques$$v13$$x1867-8548$$y2020
000878382 8564_ $$uhttps://juser.fz-juelich.de/record/878382/files/invoice_Helmholtz-PUC-2020-89.pdf
000878382 8564_ $$uhttps://juser.fz-juelich.de/record/878382/files/amt-13-3661-2020.pdf$$yOpenAccess
000878382 8564_ $$uhttps://juser.fz-juelich.de/record/878382/files/invoice_Helmholtz-PUC-2020-89.pdf?subformat=pdfa$$xpdfa
000878382 8564_ $$uhttps://juser.fz-juelich.de/record/878382/files/amt-13-3661-2020.pdf?subformat=pdfa$$xpdfa$$yOpenAccess
000878382 8767_ $$8Helmholtz-PUC-2020-89$$92020-10-01$$d2020-10-15$$eAPC$$jZahlung erfolgt$$pamt-2019-481$$zBelegnr. 1200158044
000878382 909CO $$ooai:juser.fz-juelich.de:878382$$pdnbdelivery$$popenCost$$pVDB$$pVDB:Earth_Environment$$pdriver$$pOpenAPC$$popen_access$$popenaire
000878382 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)178695$$aForschungszentrum Jülich$$b0$$kFZJ
000878382 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)129125$$aForschungszentrum Jülich$$b1$$kFZJ
000878382 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)129154$$aForschungszentrum Jülich$$b2$$kFZJ
000878382 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)171343$$aForschungszentrum Jülich$$b3$$kFZJ
000878382 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)129121$$aForschungszentrum Jülich$$b4$$kFZJ
000878382 9101_ $$0I:(DE-HGF)0$$60000-0002-4174-9531$$aExternal Institute$$b5$$kExtern
000878382 9101_ $$0I:(DE-HGF)0$$60000-0003-2472-5201$$aExternal Institute$$b6$$kExtern
000878382 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)132239$$aForschungszentrum Jülich$$b7$$kFZJ
000878382 9131_ $$0G:(DE-HGF)POF3-244$$1G:(DE-HGF)POF3-240$$2G:(DE-HGF)POF3-200$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bErde und Umwelt$$lAtmosphäre und Klima$$vComposition and dynamics of the upper troposphere and middle atmosphere$$x0
000878382 9131_ $$0G:(DE-HGF)POF3-511$$1G:(DE-HGF)POF3-510$$2G:(DE-HGF)POF3-500$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lSupercomputing & Big Data$$vComputational Science and Mathematical Methods$$x1
000878382 9131_ $$0G:(DE-HGF)POF3-512$$1G:(DE-HGF)POF3-510$$2G:(DE-HGF)POF3-500$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lSupercomputing & Big Data$$vData-Intensive Science and Federated Computing$$x2
000878382 9141_ $$y2020
000878382 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2020-01-18
000878382 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2020-01-18
000878382 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000878382 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2020-01-18
000878382 915__ $$0StatID:(DE-HGF)1150$$2StatID$$aDBCoverage$$bCurrent Contents - Physical, Chemical and Earth Sciences$$d2020-01-18
000878382 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2020-01-18
000878382 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2020-01-18
000878382 915__ $$0StatID:(DE-HGF)0111$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2020-01-18
000878382 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2020-01-18
000878382 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2020-01-18
000878382 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5$$d2020-01-18
000878382 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000878382 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2020-01-18
000878382 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$f2020-01-18
000878382 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bATMOS MEAS TECH : 2018$$d2020-01-18
000878382 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2020-01-18
000878382 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2020-01-18
000878382 920__ $$lyes
000878382 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
000878382 9201_ $$0I:(DE-Juel1)IEK-7-20101013$$kIEK-7$$lStratosphäre$$x1
000878382 9801_ $$aAPC
000878382 9801_ $$aFullTexts
000878382 980__ $$ajournal
000878382 980__ $$aVDB
000878382 980__ $$aI:(DE-Juel1)JSC-20090406
000878382 980__ $$aI:(DE-Juel1)IEK-7-20101013
000878382 980__ $$aAPC
000878382 980__ $$aUNRESTRICTED
000878382 981__ $$aI:(DE-Juel1)ICE-4-20101013