Abstract:Under the background of global warming and rapid urbanization, the urban heat island effect is the most obvious feature of urban thermal environment, so it is of great significance to study the temporal and spatial evolution of urban thermal environment change for disaster prevention and mitigation. In this study, we use the random forest model to estimate the spatial distribution of population in the Yangtze River Delta by taking the latest generation of night light satellite NPP/VIIRS data, the normalized vegetation index, the digital elevation model and topographic slope data as independent variables. Then we combine the surface temperature data retrieved by MODIS satellite remote sensing, taking the summer of 2016 as an example, to study the risk of surface thermal environment exposure and its special distribution in the Yangtze River Delta at 1 km resolution. The results show: (1) The explanatory degree of 1000 m grid spatialization variables for the population of the Yangtze River Delta in 2016 is 81.61% by using the random forest model. The simulated population can truly reflect the regional difference of population distribution in the Yangtze River Delta, closer to those of actual population. (2) The highvalue area of population density has a good correspondence with the hightemperature areas in the surface, the high populaton exposure areas and the highrisk areas exposed in most months of the summer, while in June, the area of hightemperature zone in the northwestern part of the Yangtze River Delta increased, which is asymmetrical to the area of highdensity population, and thus the exposure risks of surface temperature from low to high levels are higher than those in other months. (3) On monthly and seasonal scales, the high risks for population exposure to the land surface thermal environment are mainly located in the coastal areas, along the lower reaches of the Yangtze River and in the central urban areas of the counties. The middle risks for population exposure to LST is mainly distributed in the surrounding areas of the eastern and central cities; the lowexposure risk areas are distributed in the inland areas of the northeast and the relatively small population areas of the northeast Yangtze River Delta.