Monitoring and controlling air quality parameters form an important subject of atmospheric and environmental research today due to the health impacts caused by the different pollutants present in the urban areas. The support vector machine (SVM), as a supervised learning analysis method, is considered an effective statistical tool for the prediction and analysis of air quality. The work presented here examines the feasibility of applying the SVM to predict the ozone and particle concentrations in two Tunisian cities, namely Tunis and Sfax. We used the SVM with the linear kernel, SVM with the polynomial kernel and SVM with the RBF kernel to predict the ozone and particle concentrations in Tunisia for one year. The RBF kernel produced good results for the two pollutants with 0% error rate. Polynomial and linear kernels produced sufficiently low errors for the pollutants, at 9.09% and 18.18%, respectively. Discriminant Analysis (DA) was selected to analyze the datasets of two air quality parameters, namely ozone O3 and Suspended Particles SP. The DA results show that the spatial characterization allows for the successful discrimination between the two cities with an error rate of 4.35% in the case of the linear DA and 0% in the case of the quadratic DA. A thematic map of Tunisia was created using the MapInfo software.

In the present study, air quality analyses for ozone (O3) were conducted in Shiraz, a city in the south of Iran. The measurements were taken from 2011 through 2012 in two different locations to prepare average data in the city. The average concentrations were calculated for every 24 hours, each month and each season. Results showed that the highest concentration of ozone occurs generally in the afternoon while the least concentration was found in the morning and at midnight. Monthly concentrations of ozone showed the highest value in August and June while the least value was in December. The seasonal concentrations showed the least amounts in autumn while the highest amounts were in spring. Relations between the air pollutant and some meteorological parameters were calculated statistically using the daily average data. The wind data (velocity, direction), relative humidity, temperature, sunshine periods, evaporation, dew point, and rainfall were considered as independent variables. The relationships between concentration of pollutant and meteorological parameters were expressed by multiple linear regression equations for both annual and seasonal conditions using SPSS software. Root mean square error (RMSE) test showed that among different prediction models, stepwise model is the best option.