Investigation of Performance of Tropospheric Ozone Estimations in the Industrial Region Using Differential Artificial Neural Networks Methods

Abstract

The method of Levenberg-Marquardt learning algorithm was investigated for estimating tropospheric ozone concentration. The Levenberg-Marquardt learning algorithm has 12 input neurons (6 pollutants and 6 meteorological variables), 28 neurons in the hidden layer, and 1 output neuron for the Ozone (O<inf>3</inf>) estimate. The Multilayer Perceptron Model (MLP) performance was found to make good predictions with the mean square error (MSE) less than 1 μg/m3 (0.002 μg/m3). In addition, the correlation coefficient ranges from 0.74 to 0.95 in The Levenberg-Marquardt learning. The Levenberg-Marquardt learning algorithm that a multilayer perception method of Artificial Neural Network (ANN) has performed well and an effective approach for predicting tropospheric ozone. Ozone concentration was influenced predominantly by the nitrogen oxide (NO<inf>x</inf>, NO<inf>2</inf>, NO), SO<inf>2</inf> and temperature. The model did not predict solar radiation to ozone with sufficient accuracy. © 2018 Global NEST Printed in Greece. All rights reserved.