Title :
Application of Artificial Neural Networks (ANNs) to Predict Air Quality Classes in Big Cities
Author :
Kaminski, W. ; Skrzypski, W. Kaminski J ; Jach-Szakiel, E.
Author_Institution :
Fac. of Process & Environ. Eng., Lodz Tech. Univ., Lodz
Abstract :
The aim of the study was to examine the possibilities of the development of a prognostic instrument for the air quality management in big cities. The models ANNs were tested (MLP and RBF type). The study was focused on the development of the neural network models for prediction of the classes of the air quality state in relation to mean daily PM10 concentration. The air quality class was predicted for the next day in relation to mean daily concentrations. The tests were carried out in the city of Lodz in central Poland. The results of the modelling were very satisfactory. In the optimally constructed models, false prognosis were only 1.9% in testing series and 1.4% in training series. A low level of error prediction confirmed the fact that the neural network models are an effective instrument of the air quality management in big cities.
Keywords :
air pollution; environmental science computing; learning (artificial intelligence); multilayer perceptrons; neural nets; radial basis function networks; RBF type; air quality class; air quality classes; air quality management; artificial neural networks; error prediction; neural network models; prognostic instrument; training series; Air pollution; Artificial neural networks; Cities and towns; Instruments; Neural networks; Organisms; Quality management; Surface topography; Testing; Thermal pollution;
Conference_Titel :
Systems Engineering, 2008. ICSENG '08. 19th International Conference on
Conference_Location :
Las Vegas, NV
Print_ISBN :
978-0-7695-3331-5
DOI :
10.1109/ICSEng.2008.14