Abstract
Urban growth and its related environmental problems call for sustainable urban management policies to safeguard the quality of urban environments. Vegetation plays an important part in this as it provides ecological, social, health and economic benefits to a city's inhabitants. Remotely sensed data are of great value to monitor urban green and despite the clear advantages of contemporary high resolution images, the benefits of medium resolution data should not be discarded. The objective of this research was to estimate fractional vegetation cover from a Landsat ETM+ image with sub-pixel classification, and to compare accuracies obtained with multiple stepwise regression analysis, linear spectral unmixing and multi-layer perceptrons (MLP) at the level of meaningful urban spatial entities. Despite the small, but nevertheless statistically significant differences at pixel level between the alternative approaches, the spatial pattern of vegetation cover and estimation errors is clearly distinctive at neighbourhood level. At this spatially aggregated level, a simple regression model appears to attain sufficient accuracy. For mapping at a spatially more detailed level, the MLP seems to be the most appropriate choice. Brightness normalisation only appeared to affect the linear models, especially the linear spectral unmixing.
Highlights
Urbanisation has reached an important milestone in 2008: more than half of the earth’s population lives in urban areas [1]
The relatively low spatial resolution of a medium resolution satellite sensor may lead to low mapping accuracies because the instantaneous field of view (IFOV) often contains different types of land cover, especially in urban areas [6]
Van de Voorde et al [29] compared linear spectral unmixing to a multi-layer perceptrons (MLP) for impervious surface mapping and found that the MLP was more accurate, and that this could be explained by a better representation of the mixture space by the MLP
Summary
Urbanisation has reached an important milestone in 2008: more than half of the earth’s population lives in urban areas [1]. Vegetation elements, which would call for high resolution data, is not required for many applications related to sustainable urban management at strategic or higher levels of planning Despite all these advantages, the relatively low spatial resolution of a medium resolution satellite sensor may lead to low mapping accuracies because the instantaneous field of view (IFOV) often contains different types of land cover, especially in urban areas [6]. For this purpose, we compared three unmixing approaches: linear regression analysis (LR), linear spectral unmixing (LSMA) and multi-layer perceptrons (MLP). To a quantitative validation on a per-pixel basis, fraction estimates were aggregated to meaningful urban spatial units, i.e. neighbourhoods to make the comparison between the models more relevant in an urban planning context
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
