• Fatemeh Kardel Department of Environmental Science, Faculty of Science, University of Mazandaran, Babolsar, Mazandaran, Iran
  • Amirreza Lashkari Department of Statistics and Actuarial Science, University of Waterloo, Waterloo, Ontario, Canada
  • Manoochehr Babanezhad Mail Department of Statistics, Faculty of Science, Golestan University, Gorgan, Golestan, Iran
PM10 concentration, air pollutants, meteorological factors, AR-GMDH neural network, time series


Introduction: Predicting PM10 concentration as a significant risk factor for anumber of pollution related diseases has been recently inevitable task for areas with high population density particularly for areas with no updating monitoring systems. This study aims to illustrate how PM10 concentration level can be predicted by the prior information of the air pollutants and the meteorologicalfactors in urban areas.

Materials and methods: The data we used are measured from four monitoringstations in the city of Tehran between January 2012 and December 2014. We use the Auto-regressive group method of data handling (AR - GMDH) neuralnetwork approach which employees the prior stationary time series data setting.

Results: Our results demonstrate that PM10 concentration level for a specific dayis more likely to be predictable by sulfur dioxide (SO2) and nitrogen dioxide (NO2) than the carbon monoxide (CO) concentrations, and also show thatPM10 concentration is positively associated with precipitation and wind speedand with high temperature. The accuracy of the predicted values of the PM10 concentration is evaluated by inspecting the coefficient of determination, meansquared error, the square root of mean squared error, mean absolute deviation, and index of agreement.

Conclusions: The AR - GMDH algorithm can be proposedin comparison with the chemical and physical approaches due to its accuracyand simplicity, and its cost efficiency.


World Health Organization (WHO). Burden of disease

from the joint effects of household and ambient air pollution

for 2012. www. topics/outdoor

air/data bases.

Zhang H, Wang Y, Hu J, Ying Q, Hu X-M. Relationships

between meteorological parameters and criteria

air pollutants in there megacities in China. Environmental

Research. 2015; 140:242–54.

Chelani AB, Devotta S. Nonlinear analysis and prediction

of coarse particulate matter concentration in ambient

air. Journal of the Air and Waste Management Association.

; 56:78- 84.

de Kok TM, Driece HA, Hogervorst JG, Briedé JJ.

Toxicological assessment of ambient and traffic-related

particulate matter: a review of recent studies.

Mutation Research/Reviews in Mutation Research.


Elangasinghe MA, Singhal N, Dirks KN, Salmond JA,

Samarasinghe S. Complex time series analysis of PM10

and PM2.5 for a coastal site using artificial neural network

modeling and k- means clustering. Atmospheric

Environment. 2014; 94:106–16.

Kelly FJ, Fussell JC. Size, source and chemical composition

as determinants oftoxicity attributable to ambient

particulate matter. Atmospheric environment. 2012.


Todorovic MN, Perisic MD, Kuzmanoski MM, Stojic

AM, Sostarić AI, Mijic ZR, et al. Assessment of PM10

pollution level and required source emission reduction

in Belgrade area. Journal of Environmental Science and

Health, Part A. 2015;50(13):1351-9.

Hassanzadeh S, Hosseinibalam F, Alizadeh R. Statistical

models and time series forecasting of sulfur dioxide:

a case study Tehran. Environmental Monitoring and Assessment.

; 155: 149–55.

Saniei R, Zangiabadi A, Sharifikia M, Ghavidel Y. Air

quality classificationand its temporal trend in Tehran,

Iran, 2002–2012. Geospatial Health. 2016; 11:213–20.

Taheri Shahraiyni H, Sodoudi S. Statistical modeling

approaches for PM10 prediction in urban areas; a review

of 21st-century studies. Atmosphere. 2016;7(2):15.

Perez P, Reyes J. An integrated neural network model

for PM10 forecasting. Atmospheric Environment.

; 40:2845–51.

Dayan U, Levy I. The influence of meteorological conditions

and atmosphericcirculation types on PM10 and

visibility in Tel Aviv. Journal of Applied Meteorology.

; 44: 606–19.

Russo A, Trigo RM, Martins H, Mendes MT. NO2,

PM10 and O3 urban concentrations and its association

with circulation weather types in Portugal. Atmospheric Environment. 2014; 89: 768–85.

Russo A, Lind RG, Raischel F, Trigo R, Mendes M.

Neural network forecast of dailypollution concentration

using optimal meteorological data at synoptic and

local scales. Atmospheric Pollution Research. 2015;


Choi W, Paulson SE, Casmassi J, Winer A. Evaluating

meteorological comparability in air quality studies:

Classification and regression trees for primary pollutants

in California’s South Coast Air Basin. Atmospheric

Environment. 2013; 64:150–9.

Eichler M. Graphical modelling of multivariate time

series. Probability Theory and Related Fields. 2012;


Goyal P, Chan AT, Jaiswal N. Statistical models for

the prediction of respirable suspended particulate matter

in urban cities. Atmospheric Environment. 2006; 40:


Hosseinpoor AR, Forouzanfar MH, Yunesian M,

Asghari F, Naieni KH, Farhood D. Air pollution and

hospitalization due to angina pectoris in Tehran,

Iran: a time-series study. Environmental Research.


Hu F, Lu Z, Wong H, Yuen TP. Analysis of air quality

time series of Hong Kong with graphical modeling.

Environmetrics. 2016;27(3):169-81.

Liu PWG. Simulation of the daily average PM10

concentrations at Ta-Liao withBox-Jenkins time series

models and multivariate analysis. Atmospheric Environment.

; 43: 2104-13.

Stadlober E, Hormann S, Pfeiler B. Quality and performance

of a PM10 daily forecasting model. Atmospheric

Environment. 2008; 42:1098-109.

Hrust L, Klaic ZB, Krizan J, Antonic O, Hercog P.

Neural network forecastingof air pollutants hourly

concentrations using optimised temporal averages of

meteorological variables and pollutant concentrations.

Atmospheric Environment. 2009; 43: 5588–96.

Voukantsis D, Karatzas K, Kukkonen J, Rsnen T,

Karppinen A, Kolehmainen M. Intercomparison of air

quality data using principal component analysis, and

forecasting of PM10 and PM2.5 concentrations using

artificial neural networks, in Thessalonikiand Helsinki.

Science of the Total Environment. 2011; 409:1266–76.

Grivas G, Chaloulakou A. Artificial neural network

models for prediction of PM10 hourly concentrations,

in the Greater Area of Athens, Greece. Atmospheric Environment.

; 40: 1216–29.

Hooyberghs J, Mensink C, Dumont G, Fierens F,

Brasseur O. A neural network forecast for daily average

PM10 concentrations in Belgium. Atmospheric Environment.

; 39:3279–89.

Sylvia Y, Santoso D. Transformation Box-Cox for stabilization

of diversity in group random design. Journal

of Computer Science. 2016; 11:18-29.

Ian McLeod A, Gweon H. Optimal deseasonalization

for monthly and daily geophysical time series. Journal of Environmental statistics. 2012;4:1-11.

Atashrouz S, Pazuki G, Alimoradi Y. Estimation of the

viscosity of nine nanofluids using a hybrid GMDH- type

neural network system. Fluid Phase Equilib. 2014;372:


Ebtehaj I, Bonakdari H, Zaji AH, Azimi H, Khoshbin

F. GMDH-type neural network approach for modeling

the discharge coefficient of rectangular sharp crested

side weirs. Engineering Science and Technology, an International

Journal. 2015; 18 (4):746-57.

Acharya N, Shrivastava NA, Panigrahi B, Mohanty

U. Development of an artificial neural network based

multi-model ensemble to estimate the northeast monsoon

rainfall over south peninsular India: an application

of extreme learning machine. Climate Dynamics. 2014;

( 5-6):1303–10.

How to Cite
Original Research