Automatic classification algorithm for NOAA- AVHRR data using mixels

This study proposes an automatic classification algorithm for NOAA (National Oceanic and Atmospheric Administration)-AVHRR (Advanced Very High Resolution Radiometer) data using mixels. The proposed algorithm uses the properties of the NOAA-AVHRR multispectral bands, the mixels, and the NDVI (normalized difference vegetation index) to estimate the actual conditions. This study suggests that the proposed approach provides reasonable results as compared to those of maximum likelihood estimation and k-means clustering.