The increasing urban population is expanding the impervious surface and this leads to a more intense urban heat island (UHI) effect. Therefore, most of the world’s cities experience higher temperatures in their urban core than in the surrounding sub-urban and rural areas. However, there are still shortcomings. First, the effect of UHI is not well recognized in arid and semi-arid regions. Second, the association of multi-dimensional information with surface temperature in urban areas must be examined. This study focuses on the height-related aspects of urban geometry in an arid region. A range of multispectral and spatial vector data were used to derive the surface temperature and two-dimensional (2D) and three-dimensional (3D) information of the study area. All 2D and 3D information was aggregated into a grid with common spatial resolution to create a homogeneous dataset. The machine learning statistical model of a boosted regression tree (BRT) was used to reflect the relative influence of 2D and 3D indicators with land surface temperature. Our results showed a cooler surface temperature in the city than in the surrounding area. This leads to the question of whether the established UHI definition encompasses all types of cities or not? The thermal band was able to distinguish different spatial structures in the study area in one hand. On the other hand, the BRT analysis demonstrated that both multi-dimensional 2D and 3D indicators affect the surface temperature. In particular, the 3D indicators play a more important role than 2D indicators in shaping the surface temperature at different urban geometries of the study area. This new method can help urban planners identify the most influential 2D and 3D indicators that affect the surface temperature in different districts of a city.
.Branea, A.-M., Danciu, I., Keller, I., Bădescu, Ș., Gaman, S., & Paşcu, G. (2016). Urban heat island - state of the art review. Risk Reduction for Resilient Cities conference, Bucharest, 3.11.2016.
Cheong, Y. L., Leitão, P. J., & Lakes, T. (2014). Assessment of land use factors associated with dengue cases in Malaysia using Boosted Regression Trees. Spatial and Spatio-temporal Epidemiology, 10, 75-84.
Elith, J., Leathwick, J. R., & Hastie, T. (2008). A working guide to boosted regression trees. Journal of Animal Ecology, 77(4), 802-813.
Friedman, J. (2002). Stochastic gradient boosting. Computational Statistics & Data Analysis, 38(4), 367-378.
Harlan, S. L., Brazel, A. J., Prashad, L., Stefanov, W.L., & Larsen, L. (2006). Neighborhood microclimates and vulnerability to heat stress. Social Science Medicine, 63, 2847-2863.
Hjort, J., Suomi, J., & Kayhko, J. (2011). Spatial prediction of urban-rural temperatures using statistical methods. Theoretical and Applied Climatology, 106(1-2), 139-152.
Lafortezza, R., Carrus, G., Sanesi, G., & Davies, C. (2009). Benefits and well-being perceived by people visiting green spaces in periods of heat stress. Urban Forestry & Urban Greening, 8(2), 97-108.
Oke, T.R. (1982). The energetic basis of the urban heat island.Quarterly Journal of the Royal Meteorological Society, 108, 1-24.
Stafoggia, M., Schwartz, J., Forastiere, F., & Perucci, C.A. (2008). Does temperature modify the association between air pollution and mortality? A multicity case-cross over analysis in Italy. American Journal of Epidemiology, 167, 1476-1485, doi:10.1093/aje/kwn074.
Teuling, A., Ciais, P., Luyssaert, S., Van den Hurk, B., Ammann, C., Bernhofer, C., Ebba, Dellwik, D., Gielen, Gielen, B., Grünwald, T., Klumpp, K., Montagnani, L., Moureaux, C., Sottocornola , M., Wohlfahrt , G., Seneviratne, S., Stöckli, R., Reichstein, M., & Moors, M., 2010. Contrasting response of European forest and grassland energy exchange to heatwaves. Nature Geoscience, 3, 722-727. doi: 10.1038/NGEO950.