Sub-pixel estimation of tree cover and bare surface densities using regression tree analysis

Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Carlos Augusto Zangrando Toneli
Format: Artículo científico
Sprache:en
Veröffentlicht: Universidade Federal de Lavras 2011
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866586831077769216
author Carlos Augusto Zangrando Toneli
author_facet Carlos Augusto Zangrando Toneli
contents Sub-pixel estimation of tree cover and bare surface densities using regression tree analysis Carlos Augusto Zangrando Toneli Luis Marcelo Tavares de Carvalho Agrociencias mapping cerrado Remote sensing Sub-pixel analysis is capable of generating continuous fi elds, which represent the spatial variability of certain thematic classes. The aim of this work was to develop numerical models to represent the variability of tree cover and bare surfaces within the study area. This research was conducted in the riparian buffer within a watershed of the São Francisco River in the North of Minas Gerais, Brazil. IKONOS and Landsat TM imagery were used with the GUIDE algorithm to construct the models. The results were two index images derived with regression trees for the entire study area, one representing tree cover and the other representing baresurface. The use of non-parametric and non-linear regression tree models presented satisfactory results to characterize wetland, deciduous and savanna patterns of forest formation. 2011 artículo científico 0104-7760 https://www.redalyc.org/articulo.oa?id=74419332016 en http://www.redalyc.org/revista.oa?id=744 CERNE application/pdf Universidade Federal de Lavras CERNE (Brasil) Num.3 Vol.17
format Artículo científico
id redalyc_74419332016
language en
publishDate 2011
publisher Universidade Federal de Lavras
spellingShingle Sub-pixel estimation of tree cover and bare surface densities using regression tree analysis
Carlos Augusto Zangrando Toneli
Agrociencias
mapping
cerrado
Remote sensing
Sub-pixel estimation of tree cover and bare surface densities using regression tree analysis Carlos Augusto Zangrando Toneli Luis Marcelo Tavares de Carvalho Agrociencias mapping cerrado Remote sensing Sub-pixel analysis is capable of generating continuous fi elds, which represent the spatial variability of certain thematic classes. The aim of this work was to develop numerical models to represent the variability of tree cover and bare surfaces within the study area. This research was conducted in the riparian buffer within a watershed of the São Francisco River in the North of Minas Gerais, Brazil. IKONOS and Landsat TM imagery were used with the GUIDE algorithm to construct the models. The results were two index images derived with regression trees for the entire study area, one representing tree cover and the other representing baresurface. The use of non-parametric and non-linear regression tree models presented satisfactory results to characterize wetland, deciduous and savanna patterns of forest formation. 2011 artículo científico 0104-7760 https://www.redalyc.org/articulo.oa?id=74419332016 en http://www.redalyc.org/revista.oa?id=744 CERNE application/pdf Universidade Federal de Lavras CERNE (Brasil) Num.3 Vol.17
title Sub-pixel estimation of tree cover and bare surface densities using regression tree analysis
topic Agrociencias
mapping
cerrado
Remote sensing
url https://www.redalyc.org/articulo.oa?id=74419332016