Fuzzy logic approach for description of meteorological impacts on urban air pollution species: A Hong Kong case study

Abstract

An alternative approach to the conventional dynamic and photochemical models is presented to forecast urban air pollutants operationally. It is well known that there are some practical difficulties, which prevent the necessary progress in the development of these models as a forecasting tool. A fuzzy logic based method has been developed here to study the impact of meteorological factors on the evolution of air pollutant levels and to describe them quantitatively. This method meets all requirements but needs substantial amount of observational data. The developed model is based on simulation of diurnal cycles of principal meteorological variables (wind speed and direction, solar irradiance and air temperature) and the corresponding duirnal patterns of various air pollutants (O3,NO2,NO,NOy). In addition, the spatial patterns of these parameters are also studied. Both temporal and spatial parameter distributions have been considered in order to investigate impacts of meteorological factors and they are incorporated into the models as state vectors in the multidimensional space. Here we suggest that most of the weather and air pollution phenomena could be simulated by sequences of its conservation inside some fuzzy sets and the transition from one fuzzy set to another. Therefore, the important key point here is the development of the transition rules. © 2002 Elsevier Science Ltd. All rights reserved.