Premium
Artificial Neural Network Prediction of Tropospheric Ozone Concentrations in Istanbul, Turkey
Author(s) -
Inal Fikret
Publication year - 2010
Publication title -
clean – soil, air, water
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.444
H-Index - 66
eISSN - 1863-0669
pISSN - 1863-0650
DOI - 10.1002/clen.201000138
Subject(s) - mean squared error , linear regression , tropospheric ozone , multilayer perceptron , artificial neural network , environmental science , correlation coefficient , mathematics , coefficient of determination , statistics , regression analysis , perceptron , meteorology , ozone , geography , machine learning , computer science
Tropospheric (ground‐level) ozone has adverse effects on human health and environment. In this study, next day's maximum 1‐h average ozone concentrations in Istanbul were predicted using multi‐layer perceptron (MLP) type artificial neural networks (ANNs). Nine meteorological parameters and nine air pollutant concentrations were utilized as inputs. The total 578 datasets were divided into three groups: training, cross‐validation, and testing. When all the 18 inputs were used, the best performance was obtained with a network containing one hidden layer with 24 neurons. The transfer function was hyperbolic tangent. The correlation coefficient ( R ), mean absolute error (MAE), root mean squared error (RMSE), and index of agreement or Willmott's Index ( d 2 ) for the testing data were 0.90, 8.78 µg/m 3 , 11.15 µg/m 3 , and 0.95, respectively. Sensitivity analysis has indicated that the persistence information (current day's maximum and average ozone concentrations), NO concentration, average temperature, PM 10 , maximum temperature, sunshine time, wind direction, and solar radiation were the most important input parameters. The values of R , MAE, RMSE, and d 2 did not change considerably for the MLP model using only these nine inputs. The performances of the MLP models were compared with those of regression models (i.e., multiple linear regression and multiple non‐linear regression). It has been found that there was no significant difference between the ANN and regression modeling techniques for the forecasting of ozone concentrations in Istanbul.