Land use and land cover (LUCC) research has long focused on rural areas, but as the world continues to urbanize, much research is focusing on ecological and land cover dynamics within cities, with attention to vegetative cover therein. The ecosystem services and social benefits that urban vegetation provides have the potential to ameliorate many of the problems common to urban environments and to improve the quality of life of urban residents. While much of the research in urban ecologies has focused on urban regions in the global north, less attention has been paid to rapidly urbanizing areas in the global south, and in particular to mid sized cities which are home to a significant number of urban dwellers. The objective of this research is to investigate the spatial patterns and socio-economic determinants of urban vegetation in Altamira City, Pará State, Brazil. High resolution, space based optical imagery from 2008 was classified to derive maps of urban vegetative cover and time series remotely sensed imagery was digitized to create urban expansion maps from 1970 to 2008. Land cover information was spatially linked to socio-economic data from the 2000 Brazilian census in order to investigate geographic associations between urban vegetative cover and social indicators at the census sector level. Contrary to studies that report greener urban landscapes prevailing in more affluent neighborhoods, our analysis reveals lower vegetative cover in higher-income sectors of Altamira. Lower levels of vegetative cover are also observed in sectors of higher-housing density and age of urbanization, while higher vegetative cover is found on sectors with increased connection to the city's main water system (a proxy for urban infrastructure). Housing tenure appears to be related to patterns of vegetated cover, though the relationship is not statistically significant in multivariate analysis. These results indicate that studies of vegetative outcomes in similar urban environments of the global south should investigate socioeconomic and demographic contexts while also integrating recent infrastructure development and density-dependent growth patterns.

High spatial resolution images have been increasingly used for urban land use/cover classification, but the high spectral variation within the same land cover, the spectral confusion among different land covers, and the shadow problem often lead to poor classification performance based on the traditional per-pixel spectral-based classification methods. This paper explores approaches to improve urban land cover classification with QuickBird imagery. Traditional per-pixel spectral-based supervised classification, incorporation of textural images and multispectral images, spectral-spatial classifier, and segmentation-based classification are examined in a relatively new developing urban landscape, Lucas do Rio Verde in Mato Grosso State, Brazil. This research shows that use of spatial information during the image classification procedure, either through the integrated use of textural and spectral images or through the use of segmentation-based classification method, can significantly improve land cover classification performance.