Examining the land surface temperature (LST) and its mechanism is very significant for urban planning.The purpose of this study is to determine the factors affecting the surface temperature of urban areas of Shiraz. The OLS and GWR were used o determine the effective factors. Also, satellite data of Landsat 8 for summer 2019 were used to obtain the surface temperature of Shiraz. To this end, the Landsat 8 satellite images of Shiraz urban districts during Summer 2019, were prepared. First, the LST and vegetation was extracted from the images. Before performing the regression model between the LST as the dependent variable and geographical variables such as slope, slope gradient, elevation, distance to rivers, direct and indirect solar radiation, sunshine duration, and Total Solar Irradiance (TSI) as independent variables, the component analysis method was employed to eliminate collinearity and dependence relations among independent variables and reducing variables. Four significant components that had eigenvalues above one and about 86.75% of the variance of the initial variables were selected, which included the significance of (direct, indirect, general) solar radiation, the direction of slope, distance to rivers, vegetation, and slope gradient, respectively. In the next step, the regression analysis was performed between the components and the LST via the Ordinary Least Square (OLS) and Geographically Weighted Regression (GWR). The results showed that GWR has better performance in showing the spatial distribution of LSTs in Shiraz. Shiraz UHIs correspond to the airport and the dirt and barren districts around the city, which are often non-residential.

研究地表温度（LST）及其机理对城市规划具有十分重要的意义。本研究的目的是确定影响设拉子市区温度的因素。使用OLS和GWR确定有效因素。此外，2019年夏季的Landsat 8卫星数据被用于获取设拉子的地表温度。为此，准备了2019年夏季设拉子市区的Landsat 8卫星图像。首先，从图像中提取LST和植被。在执行LST作为因变量与地理变量（例如坡度，坡度，海拔，河流距离，直接和间接太阳辐射，日照时长和总太阳辐照度（TSI））作为自变量之间的回归模型之前，采用成分分析法消除自变量与归约变量之间的共线性和依赖关系。选择特征值大于初始变量方差的1且约为86.75％的四个重要成分，包括（直接，间接，一般）太阳辐射的重要性，坡度的方向，与河流的距离，植被和坡度梯度分别。下一步，通过普通最小二乘（OLS）和地理加权回归（GWR）在组件和LST之间执行回归分析。结果表明，GWR在显示设拉子地区LST的空间分布方面具有更好的性能。西拉子UHI对应于机场以及城市周围的尘土和贫瘠地区，这些地区通常是非住宅的。