Prediction of Air Quality Indices by Neural Networks and Fuzzy Inference Systems - The Case of Pardubice Microregion

Abstract

This paper presents a design of models for air quality prediction using feed-forward neural networks of perceptron and Takagi-Sugeno fuzzy inference systems. In addition, the sets of input variables are optimized for each air pollutant prediction by genetic algorithms. Based on data measured by the monitoring station of the Pardubice city, the Czech Republic, models are designed to predict air quality indices for each air pollutant separately and consequently, to predict the common air quality index. Considering the root mean squared error, the results show that the compositions of individual prediction models outperform single predictions of common air quality index. Therefore, these models can be applied to obtain more accurate one day ahead predictions of air quality indices. © Springer-Verlag Berlin Heidelberg 2013.