Show simple item record

dc.contributorZucca, Claudioen_US
dc.contributorKaram, Fadien_US
dc.contributorLiu, Guangpingen_US
dc.creatorWu, Weichengen_US
dc.date2016-10-01en_US
dc.date.accessioned2017-02-23T13:33:25Z
dc.date.available2017-02-23T13:33:25Z
dc.identifierhttps://mel.cgiar.org/dspace/limiteden_US
dc.identifierhttps://www.sciencedirect.com/science/article/pii/S0303243416301210en_US
dc.identifier.citationWeicheng Wu, Claudio Zucca, Fadi Karam, Guangping Liu. (1/10/2016). Enhancing the performance of regional land cover mapping. International Journal of Applied Earth Observation and Geoinformation, 52, pp. 422-432.en_US
dc.identifier.urihttps://hdl.handle.net/20.500.11766/5927
dc.description.abstractDifferent pixel-based, object-based and subpixel-based methods such as time-series analysis, decision-tree, and different supervised approaches have been proposed to conduct land use/cover classification.However, despite their proven advantages in small dataset tests, their performance is variable and less sat-isfactory while dealing with large datasets, particularly, for regional-scale mapping with high resolutiondata due to the complexity and diversity in landscapes and land cover patterns, and the unacceptably longprocessing time. The objective of this paper is to demonstrate the comparatively highest performanceof an operational approach based on integration of multisource information ensuring high mappingaccuracy in large areas with acceptable processing time. The information used includes phenologicallycontrasted multiseasonal and multispectral bands, vegetation index, land surface temperature, and topo-graphic features. The performance of different conventional and machine learning classifiers namelyMalahanobis Distance (MD), Maximum Likelihood (ML), Artificial Neural Networks (ANNs), Support Vec-tor Machines (SVMs) and Random Forests (RFs) was compared using the same datasets in the same IDL(Interactive Data Language) environment. An Eastern Mediterranean area with complex landscape andsteep climate gradients was selected to test and develop the operational approach. The results showedthat SVMs and RFs classifiers produced most accurate mapping at local-scale (up to 96.85% in OverallAccuracy), but were very time-consuming in whole-scene classification (more than five days per scene)whereas ML fulfilled the task rapidly (about 10 min per scene) with satisfying accuracy (94.2–96.4%).Thus, the approach composed of integration of seasonally contrasted multisource data and samplingat subclass level followed by a ML classification is a suitable candidate to become an operational andeffective regional land cover mapping method.en_US
dc.formatPDFen_US
dc.languageenen_US
dc.publisherElsevieren_US
dc.rightsCC-BY-NC-4.0en_US
dc.sourceInternational Journal of Applied Earth Observation and Geoinformation;52,(2016) Pagination 422,432en_US
dc.subjectmultisource data integrationen_US
dc.subjectphenological contrasten_US
dc.subjecttopographic featuresen_US
dc.subjectseparability accuracyen_US
dc.titleEnhancing the performance of regional land cover mappingen_US
dc.typeJournal Articleen_US
cg.creator.idZucca, Claudio: 0000-0002-8636-0511en_US
cg.creator.ID-typeORCIDen_US
cg.subject.agrovocagricultureen_US
cg.subject.agrovocdataen_US
cg.contributor.centerInternational Center for Agricultural Research in the Dry Areas - ICARDAen_US
cg.contributor.centerThe Litani River Authorityen_US
cg.contributor.centerEast China Institute of Technology - ECITen_US
cg.contributor.crpCGIAR Research Program on Dryland Systems - DSen_US
cg.contributor.funderCGIAR System Organization - CGIARen_US
cg.date.embargo-end-date2116-07-26en_US
cg.coverage.regionWestern Asiaen_US
cg.coverage.countryJOen_US
cg.coverage.countryLBen_US
cg.coverage.countrySYen_US
cg.contactw.wu@cgiar.orgen_US
cg.identifier.doihttps://dx.doi.org/10.1016/j.jag.2016.07.014en_US
dc.identifier.statusLimited accessen_US
mel.impact-factor3.93en_US


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record


DSpace software copyright © 2002-2016  DuraSpace
Disclaimer:
MELSpace content providers and partners accept no liability to any consequence resulting from use of the content or data made available in this repository. Users of this content assume full responsibility for compliance with all relevant national or international regulations and legislation.
Theme by 
Atmire NV