Advanced

Mapping fractional forest cover across the highlands of mainland Southeast Asia using MODIS data and regression tree modelling

Töttrup, Christian LU ; Rasmussen, M. S.; Eklundh, Lars LU and Jonsson, P. (2007) In International Journal of Remote Sensing 28(1-2). p.23-46
Abstract
Data from the moderate-resolution imaging spectroradiometer (MODIS) sensor, in combination with new mapping techniques, has the potential to improve regional research on tropical forest resources and land use dynamics. In this study, a supervised regression tree model was used to map fractions of (1) mature forest, (2) secondary forest, and (3) non-forest, using multi-temporal MODIS 250-m data as explanatory variables, and land cover information derived from high-spatial resolution image data as the response variables. From independent validation data, the overall mean absolute deviation of the resulting maps are estimated at 14.6% for mature forest, 21.6% for secondary forest, and 17.1% for non-forest cover. This study shows the increased... (More)
Data from the moderate-resolution imaging spectroradiometer (MODIS) sensor, in combination with new mapping techniques, has the potential to improve regional research on tropical forest resources and land use dynamics. In this study, a supervised regression tree model was used to map fractions of (1) mature forest, (2) secondary forest, and (3) non-forest, using multi-temporal MODIS 250-m data as explanatory variables, and land cover information derived from high-spatial resolution image data as the response variables. From independent validation data, the overall mean absolute deviation of the resulting maps are estimated at 14.6% for mature forest, 21.6% for secondary forest, and 17.1% for non-forest cover. This study shows the increased potential of this new mapping technique to infer human imprints on forest cover across the highlands of mainland Southeast Asia, compared to other existing map sources. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
International Journal of Remote Sensing
volume
28
issue
1-2
pages
23 - 46
publisher
Taylor & Francis
external identifiers
  • wos:000244093200004
  • scopus:34250843364
ISSN
1366-5901
DOI
10.1080/01431160600784218
language
English
LU publication?
yes
id
56e839f9-d795-4e06-97c9-d2a17a651631 (old id 674623)
date added to LUP
2008-01-02 14:51:44
date last changed
2017-11-12 03:31:56
@article{56e839f9-d795-4e06-97c9-d2a17a651631,
  abstract     = {Data from the moderate-resolution imaging spectroradiometer (MODIS) sensor, in combination with new mapping techniques, has the potential to improve regional research on tropical forest resources and land use dynamics. In this study, a supervised regression tree model was used to map fractions of (1) mature forest, (2) secondary forest, and (3) non-forest, using multi-temporal MODIS 250-m data as explanatory variables, and land cover information derived from high-spatial resolution image data as the response variables. From independent validation data, the overall mean absolute deviation of the resulting maps are estimated at 14.6% for mature forest, 21.6% for secondary forest, and 17.1% for non-forest cover. This study shows the increased potential of this new mapping technique to infer human imprints on forest cover across the highlands of mainland Southeast Asia, compared to other existing map sources.},
  author       = {Töttrup, Christian and Rasmussen, M. S. and Eklundh, Lars and Jonsson, P.},
  issn         = {1366-5901},
  language     = {eng},
  number       = {1-2},
  pages        = {23--46},
  publisher    = {Taylor & Francis},
  series       = {International Journal of Remote Sensing},
  title        = {Mapping fractional forest cover across the highlands of mainland Southeast Asia using MODIS data and regression tree modelling},
  url          = {http://dx.doi.org/10.1080/01431160600784218},
  volume       = {28},
  year         = {2007},
}