|
|||||
|
|
Forecasting Ambient Air SO2 Concentrations Using Artificial Neural Networks |
|
| Authors: | Sait C. Sofuoglu Aysun Sofuoglu Savas Birgili Gokmen Tayfur |
| Affiliation: | 1. Izmir Institute of Technology, Department of Chemical Engineering , Gülbah?e K?yü, Urla, Izmir, Turkey;2. Izmir Institute of Technology, Environmental Engineering MS Program , Gülbah?e K?yü, Urla, Izmir, Turkey;3. Izmir Institute of Technology, Department of Civil Engineering , Gülbah?e K?yü, Urla, Izmir, Turkey |
| Abstract: | An Artificial Neural Networks (ANNs) model is constructed to forecast SO2 concentrations in Izmir air. The model uses meteorological variables (wind speed and temperature) and measured particulate matter concentrations as input variables. The correlation coefficient between observed and forecasted concentrations is 0.94 for the network that uses all three variables as input parameters. The root mean square error value of the model is 3.60 μg/mt3. Considering the limited number of available input variables, model performances show that ANNs are a promising method of modeling to forecast ambient air SO2 concentrations in Izmir. |
| Keywords: | air pollution SO2 forecasting artificial neural networks |