Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Land cover data of Upper Parana River Basin, South America, at high spatial resolution

Rudke, Anderson Paulo ; Fujita, Thais ; Almeida, Daniela Sanches de ; Eiras, Marilia Moreira ; Xavier, Ana Carolina Freitas ; Rafee, Sameh Adib Abou LU ; Santos, Eliane Barbosa ; Morais, Marcos Vinícius Bueno de ; Martins, Leila Droprinchinski LU and Souza, Rita Valéria Andreoli de , et al. (2019) In International Journal of Applied Earth Observation and Geoinformation 83.
Abstract

This study presents a new land cover map for the Upper Paraná River Basin (UPRB-2015), with high spatial resolution (30 m), and a high number of calibration and validation sites. To the new map, 50 Landsat-8 scenes were classified with the Support Vector Machine (SVM) algorithm and their level of agreement was assessed using overall accuracy and Kappa coefficient. The generated map was compared by area and by pixel with six global products (MODIS, GlobCover, Globeland30, FROM-GLC, CCI-LC and, GLCNMO). The results of the new classification showed an overall accuracy ranging from 67% to 100%, depending on the sub-basin (80.0% for the entire UPRB). Kappa coefficient was observed ranging from 0.50 to 1.00 (average of 0.73 in the whole... (More)

This study presents a new land cover map for the Upper Paraná River Basin (UPRB-2015), with high spatial resolution (30 m), and a high number of calibration and validation sites. To the new map, 50 Landsat-8 scenes were classified with the Support Vector Machine (SVM) algorithm and their level of agreement was assessed using overall accuracy and Kappa coefficient. The generated map was compared by area and by pixel with six global products (MODIS, GlobCover, Globeland30, FROM-GLC, CCI-LC and, GLCNMO). The results of the new classification showed an overall accuracy ranging from 67% to 100%, depending on the sub-basin (80.0% for the entire UPRB). Kappa coefficient was observed ranging from 0.50 to 1.00 (average of 0.73 in the whole basin). Anthropic areas cover more than 70% of the entire UPRB in the new product, with Croplands covering 46.0%. The new mapped areas of croplands are consistent with local socio-economic statistics but don't agree with global products, especially FROM-GLC (14,9%), MODIS (33.8%), GlobCover (71.2%), and CCI (67.8%). In addition, all global products show generalized spatial disagreement, with some sub-basins showing areas of cropland varying by an order of magnitude, compared to UPRB-2015. In the case of Grassland, covering 25.6% of the UPRB, it was observed a strong underestimation by all global products. Even for the Globeland30 and MODIS, which show some significant fraction of pasture areas, there is a high level of disagreement in the spatial distribution. In terms of general agreement, the seven compared mappings (including the new map) agree in only 6.6% of the study area, predominantly areas of forest and agriculture. Finally, the new classification proposed in this study provides better inputs for regional studies, especially for those involving hydrological modeling as well as offers a more refined LU/LC data set for atmospheric numerical models.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and , et al. (More)
; ; ; ; ; ; ; ; ; ; ; ; ; and (Less)
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Global land cover dataset, Land use/land cover, Landsat satellite, Paraná River Basin, Support vector machine
in
International Journal of Applied Earth Observation and Geoinformation
volume
83
article number
101926
publisher
Elsevier
external identifiers
  • scopus:85081205163
ISSN
1569-8432
DOI
10.1016/j.jag.2019.101926
language
English
LU publication?
yes
id
9328f8f3-20d5-4cb7-b421-8c91052d0d00
date added to LUP
2020-05-22 11:29:57
date last changed
2024-03-20 10:28:50
@article{9328f8f3-20d5-4cb7-b421-8c91052d0d00,
  abstract     = {{<p>This study presents a new land cover map for the Upper Paraná River Basin (UPRB-2015), with high spatial resolution (30 m), and a high number of calibration and validation sites. To the new map, 50 Landsat-8 scenes were classified with the Support Vector Machine (SVM) algorithm and their level of agreement was assessed using overall accuracy and Kappa coefficient. The generated map was compared by area and by pixel with six global products (MODIS, GlobCover, Globeland30, FROM-GLC, CCI-LC and, GLCNMO). The results of the new classification showed an overall accuracy ranging from 67% to 100%, depending on the sub-basin (80.0% for the entire UPRB). Kappa coefficient was observed ranging from 0.50 to 1.00 (average of 0.73 in the whole basin). Anthropic areas cover more than 70% of the entire UPRB in the new product, with Croplands covering 46.0%. The new mapped areas of croplands are consistent with local socio-economic statistics but don't agree with global products, especially FROM-GLC (14,9%), MODIS (33.8%), GlobCover (71.2%), and CCI (67.8%). In addition, all global products show generalized spatial disagreement, with some sub-basins showing areas of cropland varying by an order of magnitude, compared to UPRB-2015. In the case of Grassland, covering 25.6% of the UPRB, it was observed a strong underestimation by all global products. Even for the Globeland30 and MODIS, which show some significant fraction of pasture areas, there is a high level of disagreement in the spatial distribution. In terms of general agreement, the seven compared mappings (including the new map) agree in only 6.6% of the study area, predominantly areas of forest and agriculture. Finally, the new classification proposed in this study provides better inputs for regional studies, especially for those involving hydrological modeling as well as offers a more refined LU/LC data set for atmospheric numerical models.</p>}},
  author       = {{Rudke, Anderson Paulo and Fujita, Thais and Almeida, Daniela Sanches de and Eiras, Marilia Moreira and Xavier, Ana Carolina Freitas and Rafee, Sameh Adib Abou and Santos, Eliane Barbosa and Morais, Marcos Vinícius Bueno de and Martins, Leila Droprinchinski and Souza, Rita Valéria Andreoli de and Souza, Rodrigo Augusto Ferreira and Hallak, Ricardo and Freitas, Edmilson Dias de and Uvo, Cintia Bertacchi and Martins, Jorge Alberto}},
  issn         = {{1569-8432}},
  keywords     = {{Global land cover dataset; Land use/land cover; Landsat satellite; Paraná River Basin; Support vector machine}},
  language     = {{eng}},
  month        = {{11}},
  publisher    = {{Elsevier}},
  series       = {{International Journal of Applied Earth Observation and Geoinformation}},
  title        = {{Land cover data of Upper Parana River Basin, South America, at high spatial resolution}},
  url          = {{http://dx.doi.org/10.1016/j.jag.2019.101926}},
  doi          = {{10.1016/j.jag.2019.101926}},
  volume       = {{83}},
  year         = {{2019}},
}