摘要：Urban heat island (UHI), a phenomenon in which land surface temperatures (LSTs) in an urban area are notably higher than that in the surrounding rural area, has made the living environment thermally uncomfortable, endangered public health, and increased the energy consumption on indoor air cooling. To develop a liveable and sustainable city, it is crucial to provide an accurate estimation of the UHI effect for urban planners when an area is transformed from bare lands to a high density of buildings. With this objective, the study develops multivariate spatial regression models based on LSTs retrieved from Landsat-8 thermal images to estimate the distribution of urban heat magnitudes (i.e., UHMs, relative temperatures referenced to rural temperature), by considering four types of causative factors that include land use and land cover, urban morphology, heat source, and local climate zones. Partial correlation analysis is performed to determine explainable variables and R2 is used to evaluate the models. Based on the constructed models and a master plan of buildings in Kowloon East, Hong Kong, the future UHM distributions are forecasted on four representative days in different seasons. Results show that the UHI effect will be mitigated significantly when the new buildings are built, suggesting appropriate urban planning regarding the urban thermal environment. We found that the considered factors can largely explain the daytime UHIs in both the built-up areas and land-cover areas. The proposed method can also be used to optimize the urban design for creating a more thermo-friendly urban environment.
