Martin, Edouard Philippe
Comparative Performance of Different Statistical Models for Predicting Ground-Level Ozone (O3) and Fine Particulate Matter (PM2.5) Concentrations in Montréal, Canada.
Masters thesis, Concordia University.
- Accepted Version
Ground-level ozone (O3) and fine particulate matter (PM2.5) are two air pollutants known to reduce visibility, to have damaging effects on building materials and adverse impacts on human health. O3 is the result of a series of complex chemical reactions between nitrogen oxides (NOx) and volatile organic compounds (VOCs) in the presence of solar radiation. PM is a class of airborne contaminants composed of sulphate, nitrate, ammonium, crustal components and trace amounts of microorganisms. PM2.5 is the respirable subgroup of PM having an aerodynamic diameter of less than 2.5 μm. Development of effective forecasting models for ground-level O3 and PM2.5 is important to warn the public about potentially harmful or unhealthy concentration levels.
The objectives of this study is to investigate the applicability of Multiple Linear Regression (MLR), Principle Component Regression (PCR), Multivariate Adaptive Regression Splines (MARS), feed-forward Artificial Neural Networks (ANN) and hybrid Principal Component – Artificial Neural Networks (PC-ANN) models to predict concentrations of O3 and PM2.5 in Montréal (Canada). Air quality and meteorological data is obtained from the Réseau de surveillance de la qualité de l’air (RSQA) for the Airport Station (45°28′N, 73°44′W) and the Maisonneuve Station (45°30′N, 73°34′W) for the period January 2004 to December 2007. Air pollution data include concentration values for nitrogen monoxide (NO), nitrogen dioxide (NO2), carbon monoxide (CO) and 142 different volatile organic compounds. Meteorological data include solar irradiation (SR), temperature (Temp), pressure (Press), dew point (DP), precipitation (Precip), wind speed (WS) and wind direction (WD).
Analysis of the available volatile organic compound data expressed on a propylene-equivalent concentration indicated that m/p-xylene, toluene, propylene and (1,2,4)-trimethylbenzene were species with the most significant ozone forming potential in the study area.
Different models and architectures have been investigated through five case studies. Predictive performances of each model have been measured by means of performance metrics and forecast success rates. Overall, MARS models allowing second order interaction of independent basis functions yielded lower error, higher correlation and higher forecast success rates. This study indicates that models based on statistical methods can be cost-effective tools to forecast ground-level O3 and PM2.5 in Montréal and to provide support for decision makers in protecting human health.
References:Agirre-Basurko, E., Ibarra-Berastegi, G. and Madariaga, G., 2006. Regression and multilayer perceptron-based models to forecast hourly O3 and NO2 levels in the Bilbao area.
Environmental Modelling & Software, 21 (4): 430-446.
Akyuz, M. and Cabuk, H., 2009. Meteorological variations of PM2.5/PM10 concentrations and particle-associated polycyclic aromatic hydrocarbons in the atmospheric environment of Zonguldak, Turkey. Journal of Hazardous Materials, 170 (1): 13-21.
Al-Alawi, S.M., Abdul-Wahab, S.A. and Bakheit, C.S., 2008. Combining principal component regression and artificial neural networks for more accurate predictions of ground-level ozone. Environmental Modelling & Software. 23: 396 – 403.
Altshuller, A.P., 1984. Assessment of the Contribution of Stratospheic Ozone to Ground-Level Ozone Concentrations. Environmental Research Brief, U.S. Environmental Protection Agency, Washington (United States).
Atkinson, R., 1990. Gas-phase Tropospheric Chemistry of Organic Compounds: A Review. Atmospheric Environment, 24 (1): 1–41.
Bailey, R.A. Clark, H.M., Ferris, J.P. and Krause, S., 2002. Chemistry of the Environment. Academic Press, New York (United States).
Barnard, W.R. and Hodan, W.M., 2004. Evaluating the Contribution of PM2.5 Precursor Gases and Re-entrained Road Emissions to Mobile Source PM2.5 Particulate Matter Emission. Proceedings of the13th International Emission Inventory Conference, United States Environmental Protection Agency, Washington (United States).
Barry, R.G. and Chorley, R.J., 2003. Atmosphere, Weather and Climate. Routledge, London (England).
Basheer, I.A. and Hajmeer, M., 2000. Artificial neural networks: fundamentals, computing, design, and application. Journal of Microbiological Methods, 43: 3–31.
Ben-Gal. I., 2007. Bayesian Networks, Encyclopaedia of Statistics in Quality & Reliability, Wiley & Sons, New York (United States).
Bernstein, J.A., Alexis, N., Barnes, C., Bernstein, L.I., Nel, A., Peden, D., Diaz-Sanches, D., Tarlo, M.S. and Williams, P.B., 2004. Health effects of air pollution. Journal of Allergy and Clinical Immunology, 114: 1116–1123.
Bordignon, S., Gaetan, C. and Lisi, F., 2002. Nonlinear models for ground-level ozone forecasting. Statistical Methods & Applications, 11 (2) : 227-245.
Brook, J. and Dann, T., 2002. Major Sources of Air Pollution in Eastern Canada and Transboundary Pollution. Proceedings of the Symposium on Air Pollution and Public Health, Québec National Institute of Public Health, Québec (Canada).
Brunelli, U., Piazza, V., Pignato, L., Sorbello, F. and 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.
Bruno, F., Cocchi, D. and Trivisano, C., 2004. Forecasting daily high ozone concentrations by classification trees. Environmetrics, 15(2) : 141-153.
Caya, D., Laprise, R., Gigure, M., Bergeron, G., Blanchet, J., Stocks, B.,Boer, G. and McFarlane, N., 1995. Description of the Canadian regional climate model. Water, Air and Soil Pollution 82: 477-482.
Chaloulakou, A., Saisanaa, M. and Spyrellisa, N., 2003. Comparative assessment of neural networks and regression models for forecasting summertime ozone in Athens. The Science of the Total Environment, 313: 1–13.
Chameides, W. L., Fehsenfeld, F., Rodgers, M.O, Cardelino, C., Martinez, J., Parrish, D., Lonneman, W., Lawson, D.R., Rasmussen, R.A., Zimmerman, P., Greenberg, J., Middleton, P. and Wang, T. 1992. Ozone Precursor Relationships in the Ambient Atmosphere. Journal of Geophysical Research, 97 (5): 6037-6055.
Cobourn, W.G., 2010. An enhanced PM2.5 air quality forecast model based on nonlinear regression and back-trajectory concentrations. Atmospheric Environment, 44(25): 3015-3023.
Corani, G., 2005. Air quality prediction in Milan: neural networks, pruned neural networks and lazy learning. Ecological Modelling, 185: 513-529.
Crouse, D., Goldberg, M.S. and Ross, N., 2009. A Prediction-based Approach to Modelling Temporal and Spatial Variability of Traffic-related Air Pollution in Montreal, Canada. Atmospheic Environment, 43 (32): 5075-5084.
Cuhadaroğlu, B. and Demirci, E., 1997. Influence of some meteorological factors on air pollution in Trabzon city. Energy and Buildings, 25: 179-184.
Dalrymple, G.B., 2004. The age of Earth and Its Cosmic Surroundings. Stanford University Press, Palo Alto (United States).
Delfino, R.J., Murphy-Moulton, A.M. and Becklake, M.R., 1998. Emergency Room Visits for Respiratory Illnesses among the Elderly in Montreal: Association with Low Level Ozone Exposure. Environmental Research, 76: 67 – 77.
Deschamps, K.M., 2003. Associations between Asthma Hospital Admissions and Ambient Air Pollutants in Montréal, 1992 to 1999. M.A. dissertation, Concordia University, Montréal (Canada).
Diaz-Robles, L.A. Ortega, J.C, Fub, J.S., Reed, G.D., Chow, J.C., Watson, J.G. and Moncada-Herrera, J.A., 2008. A hybrid ARIMA and artificial neural networks model to forecast particulate matter in urban areas: The case of Temuco, Chile. Atmospheric Environment, 42 (35): 8331-8340.
Donaldson, K. and MacNee, W., 1998. The mechanism of lung injury caused by PM10 in issues in environmental science and technology. Ed. R.E. Hester & R.M. Harisson, The Royal Society of Chemistry, London.
Egmont-Petersen M., Talmon J. L., Brender J., and NcNair, P., 1994. On the quality of neural net classifiers. Artificial Intelligence in Medicine, 6 (5): 359–381.
Evtyugina, M.G., Nunes, T., Alves, C. and Marques, M.C., 2009. Photochemical pollution in a rural mountainous area in the northeast of Portugal. Atmospheric Research, 92 (2): 151-158.
Fonseca, D.J., Navaresse, D.O. and Moynihan, G.P., 2003. Simulation metamodeling through artificial neural networks. Engineering Applications of Artificial Intelligence, 16: 177–183.
Garner, J., Lewis, T., Hogsett, W. and Andersen, C., 2005. Air quality criteria for ozone and related photochemical oxidants (second external review draft) volume iii. Technical report, U.S. Environmental Protection Agency, Washington (United States).
Ghio, A.J. and Huang, Y.C., 2004. Exposure to concentrated ambient particles (CAPs): a review. Inhalation Toxicology, 16: 53 – 59.
Gilbert, N.L., Goldberg, M.S., Beckerman, B., Brook, J.R and Jerrett, M., 2005. Assessing Spatial Variability of Ambient Nitrogen Dioxide in Montreal, Canada, with a Land-Use Regression Model. Journal of the Air & Waste Management Association, 55: 1059 – 1063.
Goldberg, M.S., Burnett, R.T., Bailar, J.C., Brook, J.R., Bonvalot, Y., Tamblyn, R., Singh, R. and Valois, M.-F. , 2001a. The Association between Daily Mortality and Ambient Air Particle Pollution in Montreal, Quebec: 1. Nonaccidental Mortality. Environmental Research, 86: 12 – 25.
Goldberg, M.S., Burnett, R.T., Bailar, J.C., Brook, J., Bonvalot, Y., Tamblyn, R., Singh, R., Valois, M.-F. and Vincent, R., 2001b. The Association between Daily Mortality and Ambient Air Particle Pollution in Montreal, Quebec: 2. Cause-Specific Mortality. Environmental Research, 86: 26 – 36.
Goldberg, M.S., Burnett, R.T., Valois, M.-F., Flegel, K., Bailar, J.C., Brook, J., Vincent, R. and Radon, K., 2003. Associations between ambient air pollution and daily mortality among persons with congestive heart failure. Environmental Research, 91: 8 – 20.
Goldberg, M.S., Burnett, R.T., Yale, J.-F, Valois, M.-F. and Brook, J.R., 2006. Associations between ambient air pollution and daily mortality among persons with diabetes and cardiovascular disease. Environmental Research, 100: 255 – 267.
Griffin, R.J. Cocker, D.R. Flagan, R.C. and Seinfeld, J.H., 1999. Organic aerosol formation from oxidation of biogenic hydrocarbons. Journal of Geophysical Research, 104: 3555-3567.
Hao, L. and Naiman, D. Q., 2007. Quantile Regression. Sage Publications, Thousand Oaks (United States).
Hastie, T., Tibshirani, R. and Friedman, J., 2001. The Elements of Statistical Learning: Data Mining, Inference and Prediction. Springer, New York (United States).
HCEC, 1998. National Ambient Air Quality Objectives for Particular Matter: A report by the CEPA/FPAC on Air Quality Objectives and Guidelines. Health Canada & Environmental Canada (HCEC), Ottawa (Canada).
HCEC, 1999. National Ambient Air Quality Objectives for Ground-Level Ozone : A report by the CEPA/FPAC on Air Quality Objectives and Guidelines. Health Canada & Environmental Canada (HCEC), Ottawa (Canada).
He, Y., 2004. ANN Modeling of Ambient PM2.5 in Fort McKay, Alberta. M.Sc. Dissertation, University of Alberta, Edmonton (Canada).
HRSDC, 2004. Early Childhood Education and Care Policy. Human Resources and Skills Development Canada, Ottawa (Canada).
Hutcheon, N.B. and Handegord, G.O.P., 1995. Building Science for a Cold Climate. National Research Council Canada, Ottawa (Canada).
Jensen, F. V. and Nielsen, T.D., 2007. Bayesian Networks and Decision Graphs. Springer, New York (United States).
Johnson. D., Mignacca, D., Herod, D., Jutzi, D. and Miller, H., 2007. Characterization and identification of trends in average ambient ozone and fine particulate matter levels through trajectory cluster analysis in eastern Canada. Journal of the Air & Waste Management Association, 57 (8): 907-18.
Jolliffe, I.T., 1989. Principal Component Analysis. Springer-Verlag, New York (United States).
Kampa, M. and Castanas, E., 2008. Human health effects of air pollution, Environmental Pollution, 151: 362–367.
Karatzas, K and Kaltsatos, S., 2007. Air pollution modeling with aid of computational intelligence methods in Thessaloniki, Greece. Simulation Modelling Practice and Theory, 15: 1310–1319.
Kim, S.E., 2010. Tree-based threshold modeling for short-term forecast of daily maximum ozone level. Stochastic Environmental Research and Risk Assessment, 24 (1): 19-28.
Kovac-Andric, E., Branab, J. and Gvozdica V., 2009. Impact of meteorological factors on ozone concentrations modelled by time series analysis and multivariate statistical methods. Ecological Informatics, 4 (2): 117-122.
Kuo, C.-Y., Chen, P.-T., Lin, Y.-C., Lin C.Y., Chen, H.H. and Shih, J.F, 2008. Factors affecting the concentrations of PM10 in central Taiwan, Chemosphere 70: 1273–1279.
Lin, Y., 2007. Development of fuzzy system and nonlinear regression models for ozone and PM2.5 air quality forecasts. Ph.D. dissertation, University of Louisville, Louisville (United States).
Liu, Z., 2007. Combing Measurements With Deterministic Model Outputs: Predicting Ground-Level Ozone. Ph.D. dissertation. University Of British Columbia, Vancouver (Canada).
Lu, W.Z. and Wang, X.K., 2004. Interaction patterns of major air pollutants in Hong Kong territory. Science of Total Environment, 324: 247–259.
Lykoudis, S., Psounis, N., Mavrakis, A. and Christides, A., 2008. Predicting photochemical pollution in an industrial area. Environmental Monitoring and Assessment, 142: 279 -288.
Malinowski, E.R. and Howery, D.G., 1980. Factor analysis in chemistry. John Wiley & Sons, New York (United States).
Mayer, H., 1999. Air pollution in cities. Atmospheric Environment, 33: 4029–4037.
Maynard, R., 2004. Key airborne pollutants—the impact on health. Science of Total Environment, 335: 9–13.
Mintz, R., Young, B.R. and Svrcek, W.Y., 2005. Fuzzy logic modeling of surface ozone concentrations. Computers & Chemical Engineering, 29 (10): 2049-2059.
MTL, 2003. Atlas démographique et socio-économique de Montréal. Ville de Montréal, Montréal (Canada).
Nazaroff, W. and Alvarez-Cohen, L., 2001. Environmental Engineering Science. John Wiley & Sons, New York (United States).
Nedjah, N. and Mourelle, L.M., 2005. Fuzzy Systems Engineering: Theory and Practice, Springer, New York (United States).
Nedjah, N. and Mourelle, L.M., 2006. Genetic Systems Programming Theory and Experiences. Springer, New York (United States).
Nightingale, J.A., Rogers, D.F. and Barnes, P.J., 1999. Effect of inhaled ozone on exhaled nitric oxide, pulmonary function, and induced sputum in normal and asthmatic subjects. Thorax, 54: 1061 – 1069.
Nooria, R., Hoshyaripoura, G., Ashrafia, K. and Araabib, B. N., 2010. Uncertainty analysis of developed ANN and ANFIS models in prediction of carbon monoxide daily concentration. Atmospheric Environment, 44(4): 476-482.
Novara, C., Volta, M. and Finzi, G., 2007. Nonlinear Models to Forecast Ozone Peaks. Air Pollution Modeling and Its Application XVII, 11: 721-723.
NRTEE, 2008. Developing ambient air quality objectives for Canada : advice to the Minister of Environment. National Round Table on the Environment and the Economy, Ottawa (Canada).
Odman, M. and Ingram, C., 1996. Multiscale air quality simulation plat-form (maqsip) source code documentation and validation. Technical report, Environmental Programs, MCNC-North Carolina Supercomputing Center, Raleigh (United States).
Ordieres, J. B., Vergara, E. P., Capuz, R. S., and Salazar, R. E., 2005. Neural network prediction model for fine particulate matter (PM2.5) on the US–Mexico border in El Paso (Texas) and Ciudad Juárez (Chihuahua). Environmental Modelling & Software, 20 (5) : 547-559.
Patel, P., 2004. Neural Network Analysis of 8-hr Ozone and Particulate Matter in the Texas Upper Gulf Coast Region. M.Eng. dissertation, Lamar University, Beaumont (United States).
Pires, J.C.M., Sousa, S.I.V., Pereira, M.C., Alvim-Ferraz, M.C.M. and Martins, F.G., 2008a. Management of air quality monitoring using principal component and cluster analysis—Part II: CO, NO2 and O3. Atmospheric Environment, 42: 1261-1274.
Pires, J.C.M., Sousa, S.I.V., Pereira, M.C., Alvim-Ferraz, M.C.M. and Martins, F.G., 2008b. Management of air quality monitoring using principal component and cluster analysis—Part I: SO2 and PM10. Atmospheric Environment, 42: 1249-1260.
Prybutok, B., Yi, J. and 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.
Rohli, R.V. and Vega, A.J., 2008. Climatology. Jones and Bartlett Publishers, Sudbury.
RSQA, 2004. Rapport environnemental annuel de la Qualité de l’air à Montréal (2004). Réseau de Surveillance de la Qualité de l’air (RSQA), Montréal (Canada).
RSQA, 2005. Rapport environnemental annuel de la Qualité de l’air à Montréal (2005). Réseau de Surveillance de la Qualité de l’air (RSQA), Montréal (Canada).
RSQA, 2006. Rapport environnemental annuel de la Qualité de l’air à Montréal (2006). Réseau de Surveillance de la Qualité de l’air (RSQA), Montréal (Canada).
RSQA, 2007. Rapport environnemental annuel de la Qualité de l’air à Montréal (2007). Réseau de Surveillance de la Qualité de l’air (RSQA), Montréal (Canada).
Salazar-Ruiz, E., Ordieres, J.B., Vergara, E.P. and Capuz-Rizo, S.F., 2008. Development and comparative analysis of tropospheric ozone prediction models using linear and artificial intelligence-based models in Mexicali, Baja California (Mexico) and Calexico, California (US). Environmental Modelling and Software 23: 1056–1069.
Setiono, R., 2006. Feedforward Neural Network Construction Using Cross Validation. Neural Computation, 13 (12): 2865-2877.
Seinfeld, J.H. and Pandis, S.N., 1998. Atmospheric Chemistry and Physics. John Wiley & Sons, New York (United States).
Slini, T., Karatzas, K. and Moussiopoulos, N., 2002. Statistical analysis of environmental data as the basis of forecasting: an air quality application. Science of Total Environment, 288: 227 – 237.
Slini, T., Kaprara, A., Karatzas, K. and Moussiopoulos, N., 2006. PM10 forecasting for Thessaloniki, Greece. Environmental Modelling & Software, 21: 559 – 565.
Sofuoglu, S.C., Sofuoglu, A., Birgili, S. and Tayfur, G., 2006. Forecasting ambient air SO2 concentrations using artificial neural networks. Energy Source, 1: 127–136.
Solaiman, T.A, Coulibaly, P. and Kanaroglou, P., 2008. Ground-level ozone forecasting using data-driven methods. Air quality, Atmosphere and Health, 1: 179-193.
Sousa, S., Martins, F., Alvim-Ferraz, M. and Pereira, M., 2007. Multiple linear regression and artificial neural networks based on principal components to predict ozone concen
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access
Repository Staff Only: item control page