Abstract Latin American cities have witnessed rapid and unplanned growth causing social, economic and environmental problems. To solve these problems, urban planners require information and indicators that normally are not available. In this study, the applicability of remote sensing data to extract environmental data was examined. A Landsat Enhanced Thematic Mapper (ETM+) image was used to gather information about land surface temperature (Ts) and its relationship with the Normalized Difference Vegetation Index (NDVI) and the Leaf Water Content Index (LWC). A strong negative relationship between Ts and NDVI and between Ts and LWC was observed. Analysis of variance points out statistically significant differences in the averages of Ts, NDVI, and LWC among neighbourhoods. Areas with high density housing, with a deficient urban design and those with commercial establishments had the lowest means of NDVI and LWC, and higher means of Ts. On the other hand, neighbourhoods with a higher proportion of trees and green zones had higher NDVI and LWC, and lower Ts. Finally, all neighbourhoods were classified into those that have lower to higher Ts. Therefore, the greening campaigns and new landscape design of the city should be directed specifically at neighbourhoods with the lowest level of NDVI or LWC. Acknowledgments The author thanks the University of Maryland (Global Land Cover Facility server) for distributing the Landsat images. Furthermore, the author would also like to thank the three anonymous referees for their useful comments and suggestions.