Short-run prediction of suspended particles’ pollution; a neural network application: Case study: Ahvaz city, Iran

Paper Details

Research Paper 01/03/2014
Views (164) Download (6)

Short-run prediction of suspended particles’ pollution; a neural network application: Case study: Ahvaz city, Iran

Dr Hossein Sadeghi, Samaneh Khaksar Astaneh, Mohammadhadi Hajian
J. Bio. Env. Sci.4( 3), 25-31, March 2014.
Certificate: JBES 2014 [Generate Certificate]


In order to take proper policies for pollution alleviation, it is necessary to forecast the trend of air pollution. Based on reports of World Health Organization, Ahvaz, a city located in south of Iran, is the most polluted city in the world. In this study, we employ daily time series data of maximum suspended PM10, a 10-micron suspended particle causing intensive air pollution, in order to predict pollution volume of PM10 in the air of Ahvaz city. For which, we used LMS learning algorithm to design a lag network by which concentration of PM10 is predicted for October of 2011. The results indicate that the average amount of the pollutant in this month is 482 microgram per square meter, and the maximum and minimum concentrations are respectively 722 and 319 microgram per square meter which are many times more than the maximum amount, 20 microgram per square meter, which is recognized by WHO. To control this phenomenon undoubtedly demands attention and cooperation of neighboring countries.


Aliyari Houredeli M, Teshnehlab M, Khaki A. 2008. Short term prediction using multilayer Perception neural system, Delay memory line, Gama, and ANFIS with combined instruction based on PSO, Control journal 2(2), 1-19 (in Farsi).

Berastegi G. Elias A, Barona A, Saenz J. Ezcurra A, Argandona D. 2008. From diagnosis to prognosis for forecasting air pollution using neural networks: Air pollution monitoring in Bilbao. Environmental Modeling & Software 23, 662-637.

Bodagpour S, Charkhestani A. 2011. Prediction of the concentration of pollutants in Tehran using an artificial neural network, Environmental science and technology 13(1), Tehran, Iran (in Farsi).

Brunelli U, Piazza V, Pignato L, Sorbello F. Vitabile S. 2007. Two-days ahead prediction of daily maximum concentrations of So2, O3, Pm10, No2, Co in the urban area of Palermo, Italy. Atmospheric Environment 41, 2967-2995.

Chatfield C. 1989. The analysis of time series: An Introduction, Champan & Hall.

Comrie A. 1997. Comparing neural networks and regression models for ozone forecasting, Journal of the Air and Waste Management Association 47, 653-663.

Dorffner G. 1996. Neural Networks for Time Series Processing, Report.

Gardner M, Dorling S. 1998. Artificial neural networks (the multilayer perceptron). A review of Applications in the atmospheric sciences, Atmospheric Environment 32, 2627-2636.

Gilat Amos. 2005. MATLAB: an introduction with applications, John Wiley publication.

Harrison P. 1998. Health effects of indoor air pollutants, Air Pollution and Health, The royal society of chemistry.

Lippmann M. 1998. The 1997 US EPA Standards for Particulate Matter and Ozone, Air Pollution and Health, The royal society of chemistry.

Natick MA. 2005. Learning simulink 6, The Mathworks publication.

Nelles O. 2001. Nonlinear system identification, Springer-Velag.

Perez P, Reyes J. 2006. An integrated neural network model for PM10 forecasting. Atmospheric Environment 40, 2845-2851.

Sivanandam SN. 2006. Introduction to neural networks using MATLAB 6.0, Tata McGraw Hill publication.

United Nation Environment Program. 2005. Environmental news Emergencies, Available from: URL: http//

Vemuri V. 1994. Artificial neural networks: forecasting time series, IEEE Computer Society publication.

World Health Organization. 1992. United Nation Environmental Program, Urban Air pollution in Mega Cities of the world. Oxford: Blackwell, 6-14.

World Health Organization. 2005. Particulate matter air pollution: how it harms health. Berlin, Copenhagen, Rome [Online]. [cited 2005 Apr 14]; Available from: URL: ParticulateMatter.pdf/

Yegnanarayana B. 2010. Artificial neural networks, PHI Learning Private Limited.