PM10 forecasting for Thessaloniki, Greece

The present research aims at developing an efficient and reliable module, for operational concentration levels of particulate matter with aerodynamic diameter up to 10@mm (PM"1"0) for the city of Thessaloniki. The Thessaloniki urban area is very densely built, with a high degree of motorisation and industrial activities concentration. The increase of emissions mainly from traffic and industry are responsible for the increase in atmospheric pollution levels during the last years. The air quality data sets examined in the current study are collected by a network of monitoring stations operated by the Municipality of Thessaloniki and correspond to PM"1"0 concentrations for the years 1994-2000. In order to provide with an operational air quality forecasting module for PM"1"0, statistical methods are investigated and applied. The presented results demonstrate that CART and Neural Network (NN) methods are capable of capturing PM"1"0 concentration trends, while CART may have a better performance concerning the index of agreement. Methods studied (including linear regression and principal component analysis) demonstrate promising operational forecasting capabilities.

[1]  A. Leung,et al.  Prediction of maximum daily ozone level using combined neural network and statistical characteristics. , 2003, Environment international.

[2]  L. Janssen,et al.  Analysis of spatial and temporal variations of PM 10 concentrations in the Netherlands using Kalman filtering , 2000 .

[3]  P. Misaelides,et al.  Toxic element concentrations in airborne particulate matter in the area of Thessaloniki, Greece , 1993 .

[4]  J. Schwartz,et al.  Is Daily Mortality Associated Specifically with Fine Particles? , 1996, Journal of the Air & Waste Management Association.

[5]  A. Comrie.  Comparing Neural Networks and Regression Models for Ozone Forecasting , 1997 .

[6]  Costas A. Varotsos,et al.  Thessaloniki '91 field measurement campaign—II. Ozone formation in the greater Thessaloniki area , 1997 .

[7]  Roy M. Harrison,et al.  Regression modelling of hourly NOx and NO2 concentrations in urban air in London , 1997 .

[8]  Constantini Samara,et al.  Elemental composition of airborne particulate matter in the multi-impacted urban area of Thessaloniki, Greece , 2002 .

[9]  E. Manoli,et al.  Chemical characterization and source identification/apportionment of fine and coarse air particles in Thessaloniki, Greece , 2002 .

[10]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[11]  Hsin-Chung Lu,et al.  Estimating the frequency distributions of PM10 and PM2.5 by the statistics of wind speed at Sha-Lu, Taiwan. , 2002, The Science of the total environment.

[12]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[13]  D G Gajghate,et al.  Prediction of Ambient PM10 and Toxic Metals Using Artificial Neural Networks , 2002, Journal of the Air & Waste Management Association.

[14]  C. Pope,et al.  What do epidemiologic findings tell us about health effects of environmental aerosols? , 2000, Journal of aerosol medicine : the official journal of the International Society for Aerosols in Medicine.

[15]  Isidro A. Pérez,et al.  Forecasting particulate pollutant concentrations in a city from meteorological variables and regional weather patterns , 1990 .

[16]  Constantini Samara,et al.  Heavy Metal Distribution In The Area OfThessaloniki, Greece , 1970 .

[17]  Robert E. Davis,et al.  Statistics for the evaluation and comparison of models , 1985 .

[18]  Hsin-Chung Lu,et al.  The statistical characters of PM10 concentration in Taiwan area , 2002 .

[19]  Roy M. Harrison,et al.  Sources and processes affecting concentrations of PM10 and PM2.5 particulate matter in Birmingham (U.K.) , 1997 .

[20]  C.-C. Yu,et al.  Fractal analysis of temporal variation of air pollutant concentration by box counting , 2003, Environ. Model. Softw..

[21]  Scott M. Robeson,et al.  Evaluation and comparison of statistical forecast models for daily maximum ozone concentrations , 1990 .

[22]  M. C. Hubbard,et al.  A Comparison of Nonlinear Regression and Neural Network Models for Ground-Level Ozone Forecasting , 2000, Journal of the Air & Waste Management Association.

[23]  D V Bates,et al.  Air pollution and health. , 1988, The American review of respiratory disease.

[24]  M. Kolehmainen,et al.  Neural networks and periodic components used in air quality forecasting , 2001 .

[25]  D. Dockery,et al.  Epidemiology of Particle Effects , 1999 .

[26]  Vasil Simeonov,et al.  Chemical mass balance source apportionment of PM10 in an industrialized urban area of Northern Greece , 2003 .

[27]  C. Willmott.  Some Comments on the Evaluation of Model Performance , 1982 .

[28]  Constantini Samara,et al.  Labile and bioaccessible fractions of heavy metals in the airborne particulate matter from urban and industrial areas , 2002 .

[29]  Trevor D. Davies,et al.  Regression and stochastic models for air pollution—I. Review, comments and suggestions , 1994 .

[30]  Constantini Samara,et al.  Fine and Coarse Ionic Aerosol Components in Relation to Wet and Dry Deposition , 2000 .

[31]  Zissis Samaras,et al.  Spatial and temporal characteristics of air pollutant emissions in Thessaloniki, Greece: investigation of emission abatement measures. , 2002, The Science of the total environment.

[32]  Aldo Cipriano,et al.  Forecasting ozone daily maximum levels at santiago, chile , 1998 .

[33]  Patricio Perez,et al.  Prediction of NO and NO2 concentrations near a street with heavy traffic in Santiago, Chile , 2001 .

[34]  William F. Ryan,et al.  Forecasting severe ozone episodes in the Baltimore metropolitan area , 1995 .