Agricultural land monitoring using a linear mixture model

Abstract

Intensive and mixed land cover areas, the complexity of vegetation stand structure, abundant vegetation species, and the smooth transition between different vegetation covers are critical problems facing the classification process of satellite images when using traditional approaches such as the maximum likelihood classifier. Most of the time, classification distinguishes only between cultivated/non‐cultivated. It has been difficult to accurately distinguish the different types of vegetation covers in areas that are within one pixel of satellite images. In this study, a linear mixture model (LMM) approach is applied to classify land covers in the eastern Nile delta of Egypt. Four endmembers (desert land, urban, cultivated land, water bodies) were identified based on the image itself and a constrained least‐square solution was used to unmix the image. Same method was applied on other three endmembers representing the main vegetation covers in the study area. Relationship between fraction images and NDVI was determined and the fraction images were compared with ground truth data for validation. This study indicates that the LMM is a promising approach for distinguishing the different land cover types and to classify the different vegetation types using Landsat ETM+ data.