Authors: J. Neto, Francisco Ferreira, Pedro M. Torres, F. Boavida
Addresses: Meteorology Institute, Department of Meteorological Observation and Weather Watch, Rua C do Aeroporto, 1749-077 Lisboa, Portugal. ' Faculty of Sciences and Technology, Department of Sciences and Environmental Engineering, New University of Lisbon, Campus da Caparica, Quinta da Torre 2829-516 Caparica, Portugal. ' Faculty of Sciences and Technology, Department of Sciences and Environmental Engineering, New University of Lisbon, Campus da Caparica, Quinta da Torre 2829-516 Caparica, Portugal. ' Environment Institute, Ministry of the Environment, Rua da Murgueira N.o 9/9A, 2610-124 Amadora, Portugal
Abstract: Ozone and particulate matter levels in Southern European countries are particularly high, exceeding the established limit values, and the information and alert thresholds (in the case of ozone). Therefore, it is relevant to develop a good prediction methodology for the concentrations of these pollutants. Statistical models based on Multiple Regression (MR) analysis and classification and regression trees analysis were developed successfully. The models were applied in forecasting the average daily concentrations for particulate matter and average maximum hourly ozone levels, for next day, for the group of existing air quality monitoring stations in the Metropolitan Area of North Lisbon in Portugal.
Keywords: statistical forecasting; particles; ozone levels; air pollution; air quality; environmental pollution; Portugal; particulate matter; PM10; Lisbon.
International Journal of Environment and Pollution, 2009 Vol.39 No.3/4, pp.333 - 339
Available online: 23 Sep 2009Full-text access for editors Access for subscribers Purchase this article Comment on this article