Skip to main content

page search

Library Mapping fallow lands in Vietnam's north-central mountains using yearly Landsat imagery and a land-cover succession model

Mapping fallow lands in Vietnam's north-central mountains using yearly Landsat imagery and a land-cover succession model

Mapping fallow lands in Vietnam's north-central mountains using yearly Landsat imagery and a land-cover succession model

Resource information

Date of publication
December 2012
Resource Language
ISBN / Resource ID
AGRIS:US201400155187
Pages
6281-6303

The objective of this article is to investigate whether it is possible to use Landsat data together with ancillary data and temporal context to accurately identify land covers found in the fallow areas of Montane Mainland Southeast Asia's (MMSEA's) difficult-to-map swidden landscapes. A rule-based non-parametric hybrid classification method that integrates knowledge about the vegetation regrowth patterns in these landscapes with analysis of Landsat imagery is developed. The method is applied to three upland districts of the Nghe An Province, Vietnam. The results show that the hybrid classification approach, with an overall accuracy of 90%, is superior to using a traditional maximum likelihood classifier, which generated an overall accuracy of 68%. The hybrid classification results indicate that the landscape is dominated by bush and bamboo, while the maximum likelihood classification suggests a landscape that is predominantly grass covered. The hybrid classification results are in agreement with local knowledge and information from fieldwork-based reports and articles on swidden systems in the study area and other parts of MMSEA.

Share on RLBI navigator
NO

Authors and Publishers

Author(s), editor(s), contributor(s)

Leisz, Stephen J.
Rasmussen, Michael Schultz

Publisher(s)
Data Provider
Geographical focus