Centre de documentation
scientifique

Mapping tree cover with Sentinel-2 data using the Support Vector Machine (SVM) / Anna Mirończuk in Geoinformation issues, Vol 9 n° 1 (2017)  

Public [article]  inGeoinformation issues > Vol 9 n° 1 (2017) . - pp 27 - 38 Titre : Mapping tree cover with Sentinel-2 data using the Support Vector Machine (SVM) Type de document : Article/Communication Auteurs : Anna Mirończuk, Auteur ; Agata Hościło, Auteur Année de publication : 2018 Article en page(s) : pp 27 - 38 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] carte de la végétation [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] couvert forestier [Termes IGN] image multitemporelle [Termes IGN] image Sentinel-MSI [Termes IGN] parc naturel [Termes IGN] Pologne Résumé : (auteur) The knowledge on forest resources is important for sustainable forest management at local and national level. The aim of this paper is to examine the efficacy of the Support Vector Machine (SVM) approach for tree cover mapping based on Sentinel-2 images and to explore the potential of the Sentinel-2 data for the assessment of tree cover. Sentinel-2 is a constellation of two European satellites providing innovative wide-swath (up to 290 km), high-resolution and multispectral data (13 spectral bands at 10, 20 and 60 m spatial resolution).The study area is located in the Forest Promotion Complex, which is a part of the Knyszyn Forest Landscape Park in Poland. The SVM classification was performed on the single images (spring and summer season) and on multi-date Sentinel-2 images (images from two dates classified simultaneously). In addition, the use of high-resolution bands and a combination of the 10 m and 20 m spatial resolution data was examined. The overall accuracy for all performed classification was very high and reached the level of 96.7%–99.6%, which con-firms that SVM classification can be successfully applied for tree cover mapping. The analysis showed that the Sentinel-2 images acquired in the middle of the vegetation season, when the leaves are fully developed are more suitable for tree cover mapping than the images acquired in spring. Numéro de notice : A2018-629 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : sans Date de publication en ligne : 01/03/2018 En ligne : http://www.igik.edu.pl/upload/File/wydawnictwa/GI9MiroczukA.pdf Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92885 [article]