Prediction of Tropospheric Ozone Concentration by Employing Artificial Neural Networks

Küçük Resim Yok

Tarih

2008

Dergi Başlığı

Dergi ISSN

Cilt Başlığı

Yayıncı

Mary Ann Liebert, Inc

Erişim Hakkı

info:eu-repo/semantics/closedAccess

Özet

Air pollution modeling and prediction have great importance in preventing the occurrence of air pollution episodes and provide sufficient time to take the necessary precautions. Recently various algorithms such as artificial neural networks (ANNs) is applied to air quality modeling. The present work aims to predict tropospheric ozone concentration by the ANN with three pollutant parameters and eight meteorological factors in selected areas. We have preferred three-layer perceptron type of ANNs, which consists of input, hidden, and output layers, respectively. To evaluate the performance of the ANN model, selected statistical performance parameters are used. The overall system finds correlation parameter, r between 0.8 and 0.9 for the test data sets. Therefore, results show the successful follow of estimated ozone concentrations by the model with the observed values. Finally, it was seen that the ANN is one of the compromising methods in estimation of environmental complex air pollution problems.

Açıklama

Anahtar Kelimeler

tropospheric ozone, artificial neural networks (ANN), Istanbul, prediction

Kaynak

Environmental Engineering Science

WoS Q Değeri

Q3

Scopus Q Değeri

Q3

Cilt

25

Sayı

9

Künye