Detection and mapping vegetation cover based on the Spectral Angle Mapper algorithm using NOAA AVHRR data

Satellite data, taken from the National Oceanic and Atmospheric Administration (NOAA) have been proposed and used for the detection and the cartography of vegetation cover in North Africa. The data used were acquired at the Analysis and Application of Radiation Laboratory (LAAR) from the Advanced Ve...

Full description

Saved in:
Bibliographic Details
Published inAdvances in space research Vol. 53; no. 12; pp. 1686 - 1693
Main Authors Yagoub, Houria, Belbachir, Ahmed Hafid, Benabadji, Noureddine
Format Journal Article
LanguageEnglish
Published Elsevier Ltd 15.06.2014
Subjects
Decision tree
NDVI
NOAA–AVHRR
SAM algorithm
Thresholding
SAM algorithm
NOAA–AVHRR
NDVI
Decision tree
Thresholding
Online AccessGet full text
ISSN0273-1177
1879-1948
DOI10.1016/j.asr.2014.03.020

Cover

More Information
Summary:Satellite data, taken from the National Oceanic and Atmospheric Administration (NOAA) have been proposed and used for the detection and the cartography of vegetation cover in North Africa. The data used were acquired at the Analysis and Application of Radiation Laboratory (LAAR) from the Advanced Very High Resolution Radiometer (AVHRR) sensor of 1km spatial resolution. The Spectral Angle Mapper Algorithm (SAM) is used for the classification of many studies using high resolution satellite data. In the present paper, we propose to apply the SAM algorithm to the moderate resolution of the NOAA AVHRR sensor data for classifying the vegetation cover. This study allows also exploiting other classification methods for the low resolution. First, the normalized difference vegetation index (NDVI) is extracted from two channels 1 and 2 of the AVHRR sensor. In order to obtain an initial density representation of vegetal formation distribution, a methodology, based on the combination between the threshold method and the decision tree, is used. This combination is carried out due to the lack of accurate data related to the thresholds that delimit each class. In a second time, and based on spectral behavior, a vegetation cover map is developed using SAM algorithm. Finally, with the use of low resolution satellite images (NOAA AVHRR) and with only two channels, it is possible to identify the most dominant species in North Africa such as: forests of the Liege oaks, other forests, cereal’s cultivation, steppes and bar soil.
ISSN:0273-1177
1879-1948
DOI:10.1016/j.asr.2014.03.020