Mapping natural habitats using remote sensing and sparse partial least square discriminant analysis
| Autor: | Deshayes, M., Guttler, F., Alleaume, S., Corbane, C., Ienco, D., Nin, J., Poncelet, P., Teisseire, M. |
|---|---|
| Přispěvatelé: | Territoires, Environnement, Télédétection et Information Spatiale (UMR TETIS), Institut national de recherche en sciences et technologies pour l'environnement et l'agriculture (IRSTEA)-AgroParisTech-Centre de Coopération Internationale en Recherche Agronomique pour le Développement (Cirad), Centre de Coopération Internationale en Recherche Agronomique pour le Développement (Cirad)-AgroParisTech-Institut national de recherche en sciences et technologies pour l'environnement et l'agriculture (IRSTEA), Laboratoire d'étude des interactions entre sols, agrosystèmes et hydrosystèmes (LISAH), Institut National de la Recherche Agronomique (INRA), University of Waikato [Hamilton], Laboratoire d'étude des Interactions Sol - Agrosystème - Hydrosystème (UMR LISAH), Institut de Recherche pour le Développement (IRD)-Institut National de la Recherche Agronomique (INRA)-Centre international d'études supérieures en sciences agronomiques (Montpellier SupAgro)-Institut de Recherche pour le Développement (IRD [ Madagascar])-Institut national d’études supérieures agronomiques de Montpellier (Montpellier SupAgro), Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement (Institut Agro)-Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement (Institut Agro) |
| Jazyk: | angličtina |
| Rok vydání: | 2014 |
| Předmět: |
EUROPE
010504 meteorology & atmospheric sciences [SHS.INFO]Humanities and Social Sciences/Library and information sciences 0211 other engineering and technologies FRANCE Improved method Feature selection PLS 02 engineering and technology Spatial distribution 01 natural sciences Natural (archaeology) MS MONINA TELEDETECTION HABITAT SUD CARTOGRAPHIE ComputingMilieux_MISCELLANEOUS 021101 geological & geomatics engineering 0105 earth and related environmental sciences Riparian zone Mathematics Remote sensing geography geography.geographical_feature_category [SDE.IE]Environmental Sciences/Environmental Engineering BIODIVERSITE LARZAC 15. Life on land Linear discriminant analysis Field (geography) SPLSDA GMES Thematic map Habitat Remote sensing (archaeology) 13. Climate action [SDE]Environmental Sciences General Earth and Planetary Sciences Habitats Directive Natura 2000 Cartography RESEAU NATURA 2000 |
| Zdroj: | IGARSS 2014-2014 IEEE International Geoscience and Remote Sensing Symposium IGARSS 2014-2014 IEEE International Geoscience and Remote Sensing Symposium, Jul 2014, Quebec City, France. pp.7625-7647, ⟨10.1080/01431161.2013.822603⟩ International Journal of Remote Sensing International Journal of Remote Sensing, Taylor & Francis, 2013, 34 (21), p. 7625-p. 7647. ⟨10.1080/01431161.2013.822603⟩ GI_Forum GI_Forum, Jul 2013, Salzbourg, Austria. pp.221-225, ⟨10.1553/giscience2013s504⟩ |
| ISSN: | 0143-1161 1366-5901 |
| DOI: | 10.1080/01431161.2013.822603⟩ |
| Popis: | This work presents a novel approach for mapping the spatial distribution of natural habitats in the "Foothills of Larzac" Natura 2000 listed site located in a French Mediterranean Biogeographical Region. Sparse Partial Least Square Discriminant Analysis was used to analyze two RapidEye datasets (June 2009 and July 2010) with the purpose of choosing the most informative spectral, textural and thematic variables that allow discriminating the classes of habitats. The Sparse Partial Least Square Discriminant Analysis selected relevant and stable variables for the discrimination of habitat classes that could be linked to ecological or biophysical characteristics. It also gave insight into the similarities and the differences between habitats classes with comparable physiognomic characteristics. The highest user accuracy was obtained for dry improved grasslands (u=91.97%) followed by riparian ash woods (u= 88.38%). These results are very encouraging given that these two classes were identified in Annex 1 of the EC Habitats Directive as of community interest. Due to limited data input requirements and to its computational efficiency, the approach developed in this paper is a good alternative to other types of variable selection approaches in a supervised classification framework and can be easily transferred to other Natura 2000 sites. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|