Artificial Neural Network Prediction of Tropospheric Ozone Concentrations in Istanbul, Turkey

Abstract

Artificial Neural Network Prediction of Tropospheric Ozone Concentrations in Istanbul, TurkeyTropospheric (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, crossvalidation, 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 mg/m 3 , 11.15 mg/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. IntroductionOzone (O 3 ) is a secondary pollutant and formed in the lower atmosphere (troposphere) by the complex reactions of nitrogen oxides (NO x ) and volatile organic compounds (VOCs) in the presence of solar radiation. Ozone formation in the troposphere is a rapid photochemical cycle and a non-linear process depending on the concentrations of precursors, meteorological parameters, and the sunlight intensity and spectral distribution [1,2]. Briefly, it involves the photolysis of nitrogen dioxide (NO 2 ) by solar radiation to form nitric oxide (NO) and a ground-state oxygen atom (O).The major reaction forming O 3 in the troposphere includes the reaction of oxygen atom with oxygen molecule (O 2 ). Collision of recently formed O 3 with a third body (i.e., a molecule from the surrounding air) removes the excess energy of ozone and allows it to stabilize.O 3 is removed by the reaction with NO to reform NO 2 ;However, reactions between NO and reactive radical species that are formed by the oxidation of reactive VOCs can also oxidize NO to NO 2 without the involvement of ozone, NO ÀÀÀÀÀÀÀ!

Simulation of Climate Change Impact on Emergency Medical Services Clients Caused by Air Pollution

“…Several studies applied ANNs to predict the concentration or emission of one or more air pollutants in an area (9,27,28,(30)(31)(32)(33)(34). They applied various methodologies to forecast future air pollution conditions, as well as climate change impacts on air quality.…”

“…To simulate the climate change impacts on EMS clients caused due to air pollution, ANN was applied. Neural network is a powerful computational data-driven model that can capture and represent a linear and nonlinear complex input or output relationship (27)(28)(29)(30). Multilayer perceptron (MLP) known as a supervised learning network is the most commonly used neural network model.…”

Estimation of PM10-Bound As, Cd, Ni and Pb Levels by Means of Statistical Modelling: PLSR and ANN Approaches

“…For this reason, ANNs are particularly expected to produce good predictive results when modelling PM mass concentrations compared with common gaseous pollutants based on their ability to capture the highly non-linear character of the complex processes that control the formation, transportation and removal of aerosols in the atmosphere (Grivas and Chaloulakou 2006). Furthermore, ANNs have been extensively applied in the past in the atmospheric literature with successful results regarding forecasting major gaseous air pollutant concentrations, such as nitrogen oxides (Gardner and Dorling 1999;Kolehmainen et al 2001;Lu et al 2003), sulphur dioxide (Chelani et al 2002a) and (commonly) ozone (Abdul-Wahab and Al-Alawi 2002;Chaloulakou et al 2003;Comrie 1997;Inal 2010;Sousa et al 2007;Wang et al 2003;Yi and Prybutok 1996). Moreover, a number of studies have been conducted using ANN approaches to forecast airborne PM mass concentrations (Caselli et al 2009;Chelani 2005;Grivas and Chaloulakou 2006;Hoi et al 2009;Kim et al 2009;Papanastasiou et al 2007;Paschalidou et al 2011;Perez and Reyes 2002;Perez and Reyes 2006;Pérez et al 2000;Voukantsis et al 2011), predict PM mass concentrations and predict other gaseous pollutant concentrations (Brunelli et al 2007;Cai et al 2009;Hrust et al 2009;Jiang et al 2004;Kukkonen et al 2003;Kurt et al 2008;Lu et al 2004;Lu et al 2003;Niska et al 2005;Turias et al 2008).…”

HISYCOL a hybrid computational intelligence system for combined machine learning: the case of air pollution modeling in Athens

“…More specifically, they train ANN models with data related to a narrow area (e.g., city center), and they consider this data sample as representative of a wider area that covers locations varying from a topographic, microclimate or population density point of view. For example, paper [23] predicts particulate matter concentrations in India, using data from only two stations, paper [4] uses data from ten stations in order to figure out an air pollution picture for the whole country of Belgium, while paper [6] uses only four stations for the city of Istanbul. Also there are important seasonal studies in the literature that do not offer more generalized annual solutions.…”