Urban landcover mapping using Multiple Endmember Spectral Mixture Analysis

The spatial and spectral variability of urban environments are fundamental challenges in deriving accurate remote sensing information for urban areas. Multiple Endmember Spectral Mixture Analysis (MESMA) technique was used to map the physical components of urban land cover for the city of Constantza, Romania, using Landsat Thematic Mapper (TM), Enhanced Thematic Mapper (ETM+) and IKONOS imagery during period of 1989 and 2006 years. Field spectra of vegetation, soil, and impervious surface areas collected with the use of a fine resolution and IKONOS image and pixel purity index tool in ENVI 4.3 software were modeled as reference endmembers in addition to photometric shade that was incorporated in every model. This study employs thirty endmembers and six hundred and sixty spectral models to identify soil, impervious, vegetation, and shade in the Constantza area. The mean RMS error for the selected land use land cover classes range from 0.0025 to 0.019. This paper demonstrates the potential of moderate-and high resolution, multispectral imagery to map and monitor the evolution of the physical urban environment.