The urban thermal environment is closely related to landscape patterns and land surface characteristics. Several studies have investigated the relationship between land surface characteristics and land surface temperature (LST). To explore the effects of the urban landscape on urban thermal environments, multiple land-use/land-cover (LULC) remote sensing-based indices have emerged. However, the function of the indices in better explaining LST in the heterogeneous urban landscape has not been fully addressed. This study aims to investigate the effect of remote-sensing-based LULC indices on LST, and to quantify the impact magnitude of green spaces on LST in the city built-up blocks. We used a random forest classifier algorithm to map LULC from the Gaofen 2 (GF-2) satellite and retrieved LST from Landsat-8 ETM data through the split-window algorithm. The pixel values of the LULC types and indices were extracted using the line transect approach. The multicollinearity effect was excluded before regression analysis. The vegetation index was found to have a strong negative relationship with LST, but a positive relationship with built-up indices was found in univariate analysis. The preferred indices, such as normalized difference impervious index (NDISI), dry built-up index (DBI), and bare soil index (BSI), predicted the LST (R2
= 0.41) in the multivariate analysis. The stepwise regression analysis adequately explained the LST (R2
= 0.44) due to the combined effect of the indices. The study results indicated that the LULC indices can be used to explain the LST of LULC types and provides useful information for urban managers and planners for the design of smart green cities.
This is an open access article distributed under the Creative Commons Attribution License
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited