This paper describes the ability of artificial neural network (ANN) models to simulate the pollutant dispersion characteristics in varying urban atmospheres at different regions. ANN models are developed based on twelve meteorological (including rainfall/precipitation) and six traffic parameters/variables that have significant influence on emission/pollutant dispersion. The models are trained to predict concentration of carbon monoxide and particulate matters in urban atmospheres using field meteorological and traffic data. Training, validation, and testing of ANN models are conducted using data from the Dhaka city of Bangladesh. The models are used to simulate concentration of pollutants as well as the effect of rainfall on emission dispersion throughout the year and inversion condition during the night. The predicting ability and robustness of the models are then determined by using data of the coastal cities of Chittagong and Dhaka. ANN models based on both meteorological and traffic variables exhibit the best performance and are capable of resolving patterns of pollutant dispersion to the atmosphere for different cities. 1. Introduction Air pollution is a major environmental concern in major cities around the world. The major causes of air pollution include rapid industrialization and urbanization and increased non-environment-friendly energy production. The emission of pollutants such as carbon monoxide (CO), nitrogen oxides (NOx/NO2), and particulate matter (PM) due to high traffic volumes, congestion, and poor vehicle maintenance has resulted in the transport sector being a major contributor to air pollution in major cities around the world [1]. Inefficient land use and overall poor traffic management further add to traffic congestion and air pollution besides old, overloaded, and poorly maintained motor vehicles [2, 3]. Although the concentration of particulate matter with an aerodynamic diameter of less than 10？μm (PM10) is usually used as standard measure of air pollution, the particles with a diameter of less than 2.5？μm (PM2.5) have been associated with the increase of health related problems [4]. Air quality data are complex and nonlinear in nature because of their dependencies on emission sources, especially those related to vehicular emissions and meteorological parameters. One approach to predict pollutant concentrations is to use a detailed atmospheric diffusion model that requires detailed emissions and metrological data [5]. Another approach is the regression modeling based on a statistical approach that has been applied to air
References
[1]
Y. Yin, T. Zhang, Y. Luo, and D. Lu, “Spatial and diurnal variations in concentration of atmospheric NOx along urban-rural roadways in Nanjing, Southeastern China,” International Journal of Environment and Pollution, vol. 32, no. 3, pp. 332–340, 2008.
[2]
A. K. Azad and T. Kitada, “Characteristics of the air pollution in the city of Dhaka, Bangladesh in winter,” Atmospheric Environment, vol. 32, no. 11, pp. 1991–2005, 1998.
[3]
S. K. Biswas, S. A. Tarafdar, A. Islam, M. Khaliquzzaman, H. Tervahattu, and K. Kupiainen, “Impact of unleaded Gasoline introduction on the concentration of lead in the air of Dhaka, Bangladesh,” Journal of the Air and Waste Management Association, vol. 53, no. 11, pp. 1355–1362, 2003.
[4]
R. T. Burnett, M. Smith-Doiron, D. Stieb, S. Cakmak, and J. R. Brook, “Effects of particulate and gaseous air pollution on cardiorespiratory hospitalizations,” Archives of Environmental Health, vol. 54, no. 2, pp. 130–139, 1999.
[5]
R. S. Collett and K. Oduyemi, “Air quality modelling: a technical review of mathematical approaches,” Meteorological Applications, vol. 4, no. 3, pp. 235–246, 1997.
[6]
M. W. Gardner and S. R. Dorling, “Statistical surface ozone models: an improved methodology to account for non-linear behaviour,” Atmospheric Environment, vol. 34, no. 1, pp. 21–34, 2000.
[7]
M. W. Gardner and S. R. Dorling, “Neural network modelling and prediction of hourly NOx and NO2 concentrations in urban air in London,” Atmospheric Environment, vol. 33, no. 5, pp. 709–719, 1999.
[8]
R. Pérez-Roa, J. Castro, H. Jorquera, J. R. Pérez-Correa, and V. Vesovic, “Air-pollution modelling in an urban area: correlating turbulent diffusion coefficients by means of an artificial neural network approach,” Atmospheric Environment, vol. 40, no. 1, pp. 109–125, 2006.
[9]
S. S. M. Nagendra and M. Khare, “Artificial neural network based line source models for vehicular exhaust emission predictions of an urban roadway,” Transportation Research D: Transport and Environment, vol. 9, no. 3, pp. 199–208, 2004.
[10]
W. Z. Lu, W. J. Wang, H. Y. Fan et al., “Prediction of pollutant levels in Causeway Bay area of Hong Kong using an improved neural network model,” Journal of Environmental Engineering, vol. 128, no. 12, pp. 1146–1157, 2002.
[11]
P. Pérez, A. Trier, and J. Reyes, “Prediction of PM2.5 concentrations several hours in advance using neural networks in Santiago, Chile,” Atmospheric Environment, vol. 34, no. 8, pp. 1189–1196, 2000.
[12]
D. Melas, I. Kioutsioukis, and I. C. Ziomas, “Neural network model for predicting peak photochemical pollutant levels,” Journal of the Air and Waste Management Association, vol. 50, no. 4, pp. 495–501, 2000.
[13]
X. Wu, J. Ghaboussi, and J. H. Garrett Jr., “Use of neural networks in detection of structural damage,” Computers & Structures, vol. 42, no. 4, pp. 649–659, 1992.
[14]
M. Nehdi, Y. Djebbar, and A. Khan, “Neural network model for preformed-foam cellular concrete,” ACI Materials Journal, vol. 98, no. 5, pp. 402–409, 2001.
[15]
K. M. A. Hossain, M. Lachemi, and S. M. Easa, “Artificial neural network model for the strength prediction of fully restrained RC slabs subjected to membrane action,” Computers and Concrete, vol. 3, no. 6, pp. 439–454, 2006.
[16]
M. Khare and P. Sharma, “Performance evaluation of general finite line source model for Delhi traffic conditions,” Transportation Research D, vol. 4, no. 1, pp. 65–70, 1999.
[17]
D. E. Rumelhart, G. E. Hinton, and R. J. William, “Learning internal representations by error propagation,” in Parallel Distributed Processing, Vol. 1: Foundations, D. E. Rumelhart and J. L. McClelland, Eds., pp. 318–362, MIT Press, Cambridge, Mass, USA, 1986.
[18]
K. M. A. Hossain and S. M. Easa, “Neural network models of pollutant dispersion,” International Journal of Engineering Simulation, vol. 15, no. 1, pp. 3–11, 2014.
[19]
B. A. Begum, S. K. Biswas, and P. K. Hopke, “Temporal variations and spatial distribution of ambient PM2.2 and PM10 concentrations in Dhaka, Bangladesh,” Science of the Total Environment, vol. 358, no. 1–3, pp. 36–45, 2006.
[20]
K. M. A. Hossain and S. M. Easa, “Pollutant dispersion characteristics in Dhaka city, Bangladesh,” Asia-Pacific Journal of Atmospheric Sciences, vol. 48, no. 1, pp. 35–41, 2012.
[21]
B. A. Begum, S. K. Biswas, E. Kim, P. K. Hopke, and M. Khaliquzzaman, “Investigation of sources of atmospheric aerosol at a hot spot area in Dhaka, Bangladesh,” Journal of the Air and Waste Management Association, vol. 55, no. 2, pp. 227–240, 2005.
[22]
DOE, Dhaka City State of Environment Report 2005, Department of Environment, Ministry of Agriculture and Environment, Dhaka, Bangladesh, 2005.
[23]
J. P. Shi and R. M. Harrison, “Regression modelling of hourly NOxand NO2 concentrations in urban air in London,” Atmospheric Environment, vol. 31, no. 24, pp. 4081–4094, 1997.
[24]
F. Pasquill, “The estimation of the dispersion of windborne material,” The Meteorological Magazine, vol. 90, no. 1063, pp. 33–49, 1961.
[25]
C. J. Willmott, “Some comments on the evaluation of model performance,” Bulletin of American Meteorological Society, vol. 63, no. 11, pp. 1309–1313, 1982.
[26]
S. T. Rao, L. Sedefian, and U. H. Czapski, “Characteristics of turbulence and dispersion of pollutants near major highways,” Journal of Applied Meteorology, vol. 18, no. 3, pp. 283–290, 1979.
[27]
L. Sedefian, S. T. Rao, and U. Czapski, “Effects of traffic-generated turbulence on near-field dispersion,” Atmospheric Environment A, vol. 15, no. 4, pp. 527–536, 1981.
