Skip to main content

Land cover classification in the Argentine Pampas using multi-temporal Landsat TM data

Buy Article:

$59.35 plus tax (Refund Policy)

Abstract:

The objective of this study was to explore the use of multi-temporal Landsat TM data from the same growing season for the classification of land cover types in the south-western portion of the Argentine Pampas. Investigations were made on how many dates are necessary to obtain an accurate classification and, given a fixed number of dates, which is the particular combination of dates that yield the best results. Additionally, the effect of using the NDVI instead of all the bands available on the classification accuracy and the use of a moving window filter over the classified image were tested. Scenes acquired in spring, early summer, late summer and early fall of the 1996-1997 growing season were used. Land cover information for the same period was collected from farms and ranches and this information was included in a GIS. Supervised classifications were performed using all the 15 possible ways to combine the four dates. At least two scenes are needed for a satisfactory classification. These scenes must embrace the shift between winter and summer crops (i.e. one spring and one summer image). Using the NDVI instead of Landsat TM bands 3, 4 and 5 increased the biological interpretability of the results but caused a decrease in accuracy.

Document Type: Research Article

DOI: http://dx.doi.org/10.1080/0143116021000021288

Affiliations: 1: IFEVA and Departamento de Recursos Naturales y Ambiente, Facultad de Agronomía, Universidad de Buenos Aires--CONICET, Av. San Martín 4453, C1417DSE Buenos Aires, Argentina 2: Instituto de Clima y Agua, INTA, Los Reseros y Las Cabañas s/n, Castelar (1712), Buenos Aires, Argentina 3: Asociación Argentina de Consorcios Regionales de Experimentación Agrícola (AACREA), Sarmiento 1236 P5 (1041), Buenos Aires, Argentina

Publication date: September 1, 2003

More about this publication?
tandf/tres/2003/00000024/00000017/art00004
dcterms_title,dcterms_description,pub_keyword
6
5
20
40
5

Access Key

Free Content
Free content
New Content
New content
Open Access Content
Open access content
Subscribed Content
Subscribed content
Free Trial Content
Free trial content
Cookie Policy
X
Cookie Policy
ingentaconnect website makes use of cookies so as to keep track of data that you have filled in. I am Happy with this Find out more