Asian Science Citation Index is committed to provide an authoritative, trusted and significant information by the
coverage of the most important and influential journals
to meet the needs of the global scientific community.
In this study, a nonlinear model for forecasting the SO2 ground level concentrations is build by using a Radial Basis Function Network (RBFN) based on hybrid learning algorithm. Ground level concentrations of pollutants were analysed in the area under study, in particular the high levels of SO2 occuring during relatively rare episodes. These events are influenced by many factors, such as local meteorology aspects, topography and industrial emissions. The model structure is identified by using a fuzzy C-means clustering algorithm. The proposed RBFN is trained by hybrid learning algorithm to obtain the centre and width of each radial basis function and the least squares method to obtain the output weights. An improved learning scheme is used to avoid the local minima. The developed model concerns an urban area in the Annaba City (North-East Algeria), but it can be adapted to other locations.
