Multi-temporal monitoring of cotton growth through the vegetation profile classification for Tashkent province, Uzbekistan

As satellite data of the Earth surface seems to be of vital importance for many applications, classification of land use and land cover has been found to vary dramatically in different approaches. In this paper, modified classification algorithm of remote sensing data is presented for processing medium and high spatial resolution satellite images like Landsat and Sentinel in Tashkent province of Uzbekistan. The results of NDVI (Normalized difference vegetation index) profile analysis via Spectral Correlation Mapper classification are shown for the period 1994-2017. It is implied, that combination of optical and radar data with application of Spectral Correlation Mapper classification improve the results of classification for a specific dataset by considering such factors as overall classification accuracy and time and labor involved.