Forecasting Concentrations of Gaseous Air Pollutants Using Artificial Neural Networks in Tabriz

Today, air pollution is considered as an important and challenging problem in the megacities all over the world. It is usually caused due to industrialization, urbanization, rapid development in traffic and increasing amounts of anthropogenic emissions. Urban air pollution in developing countries has been represented as a growing problem for communities. Reliable forecasting of air pollution would allow taking more efficient countermeasures to prevent air pollution crisis and protect public health. The artificial Neural Network (ANN) has emerged out to be more flexible, less assumption dependent and adaptive methodology to obtain reliable prediction values of air pollutants. ANNs have been shown to be quite powerful in capturing the complex and usually nonlinear relationships between meteorological variables and air pollutant concentrations [1-3].