000084843 001 __ 84843
000084843 024 8_ $9 driver $a oai:ddd.uab.cat:84843
000084843 035 __ $9 hdl_2072_16099 $a oai:www.recercat.cat:2072/172946
000084843 041 __ $a eng
000084843 080 __ $a 504
000084843 100 1_ $a Paneque-Gálvez, Jaime
000084843 245 10 $a Textural classification of land cover using support vector machines : $b  an empirical comparison with parametric, non parametric and hybrid classifiers in the Bolivian Amazon
000084843 260 __ $c 2011
000084843 300 __ $a 25 p.
000084843 520 __ $a Land cover classification is a key research field in remote sensing and land change science as thematic maps derived from remotely sensed data have become the basis for analyzing many socio-ecological issues. However, land cover classification remains a difficult task and it is especially challenging in heterogeneous tropical landscapes where nonetheless such maps are of great importance. The present study aims to establish an efficient classification approach to accurately map all broad land cover classes in a large, heterogeneous tropical area of Bolivia, as a basis for further studies (e.g., land cover-land use change). Specifically, we compare the performance of parametric (maximum likelihood), non-parametric (k-nearest neighbour and four different support vector machines - SVM), and hybrid classifiers, using both hard and soft (fuzzy) accuracy assessments. In addition, we test whether the inclusion of a textural index (homogeneity) in the classifications improves their  performance. We classified Landsat imagery for two dates corresponding to dry and wet seasons and found that non-parametric, and particularly SVM classifiers, outperformed both parametric and hybrid classifiers. We also found that the use of the homogeneity index along with reflectance bands significantly increased the overall accuracy of all the classifications, but particularly of SVM algorithms. We observed that improvements in producer’s and user’s accuracies through the inclusion of the homogeneity index were different depending on land cover classes. Earlygrowth/degraded forests, pastures, grasslands and savanna were the classes most improved, especially with the SVM radial basis function and SVM sigmoid classifiers, though with both classifiers all land cover classes were mapped with producer’s and user’s accuracies of around 90%. Our approach seems very well suited to accurately map land cover in tropical regions, thus having the potential to contribute to conservation initiatives, climate change mitigation schemes such as REDD+, and rural development policies.
000084843 540 __ $9 info:eu-repo/semantics/openAccess $a L'accés als continguts d'aquest document queda condicionat a l'acceptació de les condicions d'ús establertes per la següent llicència Creative Commons:  $u http://creativecommons.org/licenses/by-nc-nd/3.0/es/
000084843 653 __ $a Sòls, Ús dels -- Bolívia
000084843 653 __ $a Sòls, Ús dels -- Classificació
000084843 653 __ $a Cartografia digital
000084843 653 __ $a Prospecció de dades
000084843 653 __ $a Algorismes
000084843 653 __ $a Teledetecció
000084843 655 _4 $a info:eu-repo/semantics/workingPaper
000084843 700 1_ $a Mas, Jean-François
000084843 700 1_ $a Moré, Gerard
000084843 700 1_ $a Cristóbal, Jordi
000084843 700 1_ $a Orta-Martínez, Martí
000084843 700 1_ $a Luz, Ana Catarina
000084843 700 1_ $a Guèze, Maximiliem
000084843 700 1_ $a Macía, Manuel
000084843 700 1_ $a Reyes-García, Victoria
000084843 710 1_ $a Institut de Ciència i Tecnologia Ambientals
000084843 710 1_ $a Universitat Autònoma de Barcelona
000084843 830 __ $a Working Papers on Environmental Sciences ; $v 
000084843 856 40 $p 25 $s 790027 $u http://ddd.uab.cat/pub/worpap/2011/hdl_2072_172946/WorkPapEnvSci_2011_05.pdf
000084843 856 42 $3 Adreça alternativa $u http://hdl.handle.net/2072/172946
000084843 980 __ $a WORPAP $b UAB