A forecast of surface ozone using analytical models

Abstract

In this study, several analytical models were tested to forecast the surface ozone concentration using Artificial Neural Network (ANN), Multiple Linear Regression (MLR) and Time Series Regression (TSR). Four study areas were selected in this study, namely Seberang Jaya in Penang, Shah Alam in Selangor, Larkin in Johor and Kota Bharu in Kelantan. The main objective of this study is to determine the appropriate analytical models MLR and ANN for surface ozone forecasting in some zones of peninsular Malaysia, to forecast surface ozone concentration with TSR model in several zones of peninsular Malaysia and to compare the performance of each model by the performance index. The performance index that will be shown in this study for the model comparison are root mean square error (RMSE), mean square error (MSE) and determination of coefficient (R2). The ANN model showed better performance compared to the MLR and TSR models in the model comparison in each station. The station in Larkin, Johor provides high accuracy in forecasting surface ozone concentrations for each model with minimum MSE, 0.000009 ppm and RMSE, 0.0042 ppm compared to other stations. The value of R2 is 0.33 which is highest compared to station in Seberang Jaya and Kota Bharu.