Simulation of the urban heat island phenomenon in Mediterranean climates

An intelligent "data-driven" method is used in the present study for investigating, analyzing and quantifying the urban heat island phenomenon in the major Athens region where hourly ambient air-temperature data are recorded at twenty-three stations. The heat island phenomenon has a serious impact on the energy consumption of buildings, increases smog production, while contributing to an increasing emission of pollutants from power plants, including sulfur dioxide, carbon monoxide, nitrous oxides and suspended particulates. The intelligent method is an artificial neural network approach in which the urban heat island intensity at day and nighttime are estimated using as inputs several climatic parameters. Various neural network architectures are designed and trained for the output estimation, which is the daytime and nighttime urban heat island intensity at each station for a two-year time period. The results are tested with extensive sets of non-training measurements and it is found that they correspond well with the actual values. Furthermore, the influence of several input climatic parameters measured at each station, such as solar radiation, daytime and nighttime air temperature, and maximum daily air temperature, on the urban heat island intensity fluctuations is investigated and analyzed separately for the day and nighttime period. From this investigation it is shown that heat island intensity is mainly influenced by urbanization factors. A sensitivity investigation has been performed, based on neural network techniques, in order to adequately quantify the impact of the above input parameters on the urban heat island phenomenon.