In this paper, first the land surface brightness temperature was retrieved by single channel algorithm

based on multi-temporal Landsat TM/ETM+ data, then NDVI, MNDWI, NDBI and NDBaI indices were calculated to classify

the land use/cover types in the study area by the decision tree method and, finally, the spatial and temporal

changes of Urban Heat Island (UHI) and the relationship between UHI and land use/cover change in Changsha City

were studied. The results show that the extent of UHI increases with the expansion of the built-up area in

Changsha City, that the change of land use/cover types is likely to cause the variation of the spatial

distribution of Land Surface Temperature (LST), and that the built-up area and the barren land seem to be the

major factors responsible for UHI intension, while the water body and the forest land play an important role in

reducing LST. Regression analysis shows that there exists a significant correlation between LST and the four

indices, and there also exist remarkable LST differences in different land use/cover types.