Systematic Approach for the Prediction of Ground-Level Air Pollution (around an Industrial Port) Using an Artificial Neural Network

Abstract

The prediction of air pollution levels is critical to enable proper precautions to be taken before and during certain events. In this paper a rigorous method of preparing air quality data is proposed to achieve more accurate air pollution prediction models based on an artificial neural network (ANN). The models consider the prediction of daily concentrations of various ground-level air pollutants, namely CO, PM 10 , NO, NO 2 , NO x , SO 2 , H 2 S, and O 3 , which were measured by an ambient air quality monitoring station in Ghadafan village, located 700 m downwind of the emissions of Sohar Industrial Port on the Al-Batinah coast of Oman. The training of the models is based on the multi-layer perceptron (MLP) method with the Back-Propagation (BP) algorithm. The results show very good agreement between the actual and predicted concentrations, as the values of the coefficient of multiple determinations (R 2 ) for all ANN models exceeded 0.70. The results also show the importance of temperature in the daily variations of O 3 , SO 2 , and NO x , whilst the wind speed and wind direction play significant roles in the daily variations of NO, CO, NO 2 , and H 2 S. PM 10 concentrations are influenced by almost all the measured meteorological parameters.

Indoor air pollution and exposure assessment of the gulf cooperation council countries: A critical review

“…Oman has similar weather conditions as other GCC countries (Table 5). Therefore, infiltrations of outdoor air pollutants from both natural and anthropogenic sources are important factors in determining the IAQ (Baawain and Al-Serihi, 2014). Abdul-Wahab et al (2005) reported the presence of high-level earth metals (Zn, Mg, Fe, and Cu) in homes due to natural dust storms, while limestone borne-aerosols were attributed to nearby cement industries.…”

Temporal Evolution of Air Pollution Levels in the Wider Industrial Zone of Kavala, East Macedonia and Thrace, Greece

“…Several studies have been conducted around the world that investigate the air quality in industrial areas in terms of various pollutants such as volatile organic compounds [2] , trace elements [3] , air pollution indices (including SO 2 , NO 2 , PM 10 ) [4] and others. Some of these studies have attempted to predict future air pollution levels through detailed monitoring [5] .…”

THE COMPARISON OF LINEAR MODELS FOR PM10 AND PM2.5 FORECASTING

“…One solution is to apply Fuzzy Logic techniques [24], [25]. Another is to apply a variety of neural network procedures [11], [12]; among the most useful being Radial Basis Function and Elman Networks [13], as well as the latest recurrent types [14]- [16]. In article [17], the accuracy of prediction of PM10 pollution by wavelet transformation and an ensemble of neural predictors is considered.…”