Abstract
Suspended particulate matter is significantly related to the degradation of air quality in urban agglomerations, generating adverse health effects. Therefore, the ability to make accurate predictions of particulate ambient concentrations is important in order to improve public awareness and air quality management. This study aims at developing models using multiple regression and neural network (NN) methods that might produce accurate 24-h predictions of daily average (DA) value of PM10 concentration and at comparatively assessing the above mentioned techniques. Pollution and meteorological data were collected in the urban area of Volos, a medium-sized coastal city in central Greece, whose population and industrialization is continuously increasing. Both models utilize five variables as inputs, which incorporate meteorology (difference between daily maximum and minimum hourly value of ground temperature and DA value of wind speed), persistency in PM10 levels and weekly and annual variation of PM10 concentration. The validation of the models revealed that NN model showed slightly better skills in forecasting PM10 concentrations, as the regression and the NN model can forecast 55 and 61% of the variance of the data, respectively. In addition, several statistical indexes were calculated in order to verify the quality and reliability of the developed models. The results showed that their skill scores are satisfying, presenting minor differences. It was also found that both are capable of predicting the exceedances of the limit value of 50 μg/m3 at a satisfactory level.
Similar content being viewed by others
References
Beale, R., & Jackson, T. (1992). Neural computing: An introduction. Bristol, England: IOP Publishing.
Berlyand, M. E. (1991). Prediction and regulation of air pollution. Dordecht, The Netherlands: Atmospheric Sciences Library, Kluwer.
Boy, M., & Kulmala, M. (2002). Influence of spectral solar irradiance on the formation of new particles in the continental boundary layer. Atmos. Chem. Phys. Discuss., 2, 1317–1350.
Boznar, M., Lesjak, M., & Mlakar, P. (1993). A neural network based method from short term predictions of ambient SO2 concentrations in highly polluted industrial areas of complex terrain. Atmospheric Environment, 27B, 221–230.
Chaloulakou, A., Grivas, G., & Spyrellis, N. (2003a). Neural network and multiple regression models for PM10 prediction in Athens: A comparative assessment. Journal of Air & Waste Management, 53, 1183–1190.
Chaloulakou, A., Kassomenos, P., Spyrellis, N., Demokritou, P., & Koutrakis, P. (2003b). Measurements of PM10 and PM2.5 particle concentrations in Athens, Greece. Atmospheric Environment, 37, 649–660.
Chaloulakou, A., Saisana, M., & Spyrellis, N. (2003c). Comparative assessment of neural network and regression models for forecasting summertime ozone in Athens. Science of the Total Environment, 313, 1–13.
Colbeck, I., Chung, M.-C., & Eleftheriadis, K. (2002). Formation and transport of atmospheric aerosol over Athens, Greece. Water, Air, & Soil Pollution: Focus, 2, 223–235.
Comrie, A. (1997). Comparing neural networks and regression models for ozone forecasting. Journal of Air & Waste Management, 47, 653–663.
Dockery, D. W., Schwartz, J., & Spengler, J. D. (1992). Air pollution and daily mortality: Association with particulates and acid aerosols. Environmental Research, 59, 362–373.
Fuller, G. W., Carslaw, D. C., & Lodge, H. W. (2002). An empirical approach for the prediction of daily mean PM10 concentrations. Atmospheric Environment, 36, 1431–1441.
Gardner, M., & Dorling, S. (1998). Artificial neural networks (the multilayer perceptron) – A review of applications in the atmospheric sciences. Atmospheric Environment, 32, 2627–2636.
Hubbard, M. C., & Cobourn, W. G. (1998). Development of a regression model to forecast ground-level ozone concentration in Louisville, KY. Atmospheric Environment, 32, 2637–2647.
Joliffe, I. T., & Stephenson, D. B. (2002). Forecast verification. New York: Wiley.
Kassomenos, P. A., Flocas, H. A., Lykoudis, S., & Skouloudis, A. (1998). Spatial and temporal characteristics of the relationship between air quality status and mesoscale circulation over an urban Mediterranean basin. Science of the Total Environment, 217, 37–57.
Kassomenos, P., Kotroni, V., & Kallos, G. (1995). Analysis of climatological and air quality observations from greater Athens area. Atmospheric Environment, 29, 3671–3688.
Katsouyianni, K., Touloumi, G., Spix, C., Scwartz, J., Balducci, F., Medina, S., et al. (1997). Short term effects of ambient SO2 and particulate matter on mortality in 12 European cities: results from time series data from the APHEA project. BMJ, 314, 1658–1663.
Massart, B. G. J., Kvalheim, O. M., Stige, L., & Aasheim, R. (1998). Ozone forecasting from meteorological variables. Part II. Daily maximum ground-level O3 concentration from local weather forecasts. Chemometrics and Intelligent Laboratory, 42, 191–197.
Melas, D., Kioutsioukis, I., & Ziomas, I. C. (2000). Neural network model for predicting peak photochemical pollutant levels. Journal of Air & Waste Management, 50, 495–501.
Ostro, B. D., Chestnut, L., Vichit-Vadakan, N., & Laixuthai, A. (1999a). The impact of particulate matter on daily mortality in Bangkok, Thailand. Journal of Air & Waste Management, 49, 100–107.
Ostro, B. D., Eskeland, G. S., Sanchez, J. M., & Feyzioglou, T. (1999b). Air pollution and health effects: A study of medical visits among children in Santiago, Chile. Environmental Health Perspectives, 107, 69–73.
Papanastasiou, D. K., & Melas, D. (2007a). Daily ozone forecasting in an urban area, using meteorological & pollution data. Fresenius Environmental Bulletin, (in press).
Papanastasiou, D. K., & Melas, D. (2007b). Statistical characteristics of ozone and PM10 levels in a medium sized Mediterranean city. Special Issue on Air Pollution, International Journal of Environment and Pollution, (in press).
Perez, P., & Reyes, J. (2002). Prediction of maximum of 24-h average of PM10 concentrations 30 h in advance in Santiago, Chile. Atmospheric Environment, 36, 4555–4561.
Potukuchi, S., & Wexler, A. S. (1997). Predicting vapor pressures using neural networks. Atmospheric Environment, 31, 741–753.
Prybutok, V. R., Yi, J., & Mitchell, D. (2000). Comparison of neural network models with ARIMA and regression models for prediction of Houston’s daily maximum ozone concentrations. European Journal of Operational Research, 122, 31–40.
Schwartz, J., & Dockery, D. W. (1992). Increased mortality in Philadelphia associated with daily air pollution concentrations. American Review of Respiratory Disease, 145, 600–604.
Touloumi, G., Pocock, S. J., Katsouyianni, K., & Trichopoulos, D. (1994). Short term effects of air pollution on daily mortality in Athens. A time series analysis. International Journal of Epidemiology, 23, 957–967.
Van der Wal, J. T., & Janssen, L. H. (2000). Analysis of spatial and temporal variations of PM10 concentrations in The Netherlands using Kalman filtering. Atmospheric Environment, 34, 3675–3687.
Wilks, D. (1995). Statistical methods in the atmospheric sciences: An introduction. Academic Press.
Yi, J., & Prybutok, V. R. (1996). A neural network model forecasting for prediction of daily maximum ozone concentration in an industrialized urban area. Environmental Pollution, 92, 349–357.
Zannetti, P. (1990). Air pollution modelling. New York: Computational Mechanics.
Ziomas, I. C., Melas, D., Zerefos, C. S., & Bais, A. F. (1995a). On the relationship between peak ozone levels and meteorological variables. Fresenius Environmental Bulletin, 4, 53–58.
Ziomas, I. C., Melas, D., Zerefos, C. S., Paliatsos, A., & Bais, A. F. (1995b). Forecasting peak pollutant levels using meteorological variables and Indexes. Atmospheric Environment, 29, 3703–3711.
Acknowledgements
The authors would like to thank Mr. Stefanos Tzavelas who is the head of the pollution and the meteorological station, Department of Environment, Prefecture of Magnessia in Greece.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Papanastasiou, D.K., Melas, D. & Kioutsioukis, I. Development and Assessment of Neural Network and Multiple Regression Models in Order to Predict PM10 Levels in a Medium-sized Mediterranean City. Water Air Soil Pollut 182, 325–334 (2007). https://doi.org/10.1007/s11270-007-9341-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11270-007-9341-0