Remotely sensed thermal infrared (TIR) data have been widely used to retrieve land surface temperature (LST). The
LST is an important parameter in the studies of urban thermal environment and dynamics. Specific objectives are to
evaluate land cover change detection in Isfahan and to analyze the impact of these changes on surface temperature
using TM and ETM+ thermal bands for 1990 and 2001. Hybrid method classification was used for producing land cover
maps and post-classification comparison was applied for change detection. The single channel algorithm was used for
calculating LST. For investigation the relationship between the kinds of land cover and land surface temperature, the
land cover change map for 1990 and 2001 was overlaid with LST map. The technique of image differencing is
employed to produce a radiant temperature change image after the surface radiant temperature of each year has been
normalized. The results indicate that bare land exhibits the highest surface radiant temperature (44.9°C in 1990 &
48.9°C in 2001), followed by stony body (42.6°C in 1990 & 45.3°C in 2001). After that urban and built up area have
temperature less than bare land and stony body. The lowest radiant temperature in 1990and 2001are observed in
green cover and river classes.