MILAGRO project was conducted in Mexico City during March 2006 with the mainobjective of study the local and global impact of pollution generated bymegacities. The research presented in this paper is framed in MILAGROproject and is focused on the study and development of modelingmethodologies that allow the forecasting of daily ozone concentrations. Thepresent work aims to develop Fuzzy Inductive Reasoning (FIR) models usingthe Visual-FIR platform. FIR offers a model-based approach to modeling andpredicting either univariate or multivariate time series. Visual-FIR offersan easy-friendly environment to perform this task. In this research, longterm prediction of maximum ozone concentration in the downtown of MexicoCity Metropolitan Area is performed. The data were registered every hour andinclude missing values. Two modeling perspectives are analyzed, i.e. monthlyand seasonal models. The results show that the developed models are able topredict the diurnal variation of ozone, including its maximum daily value inan accurate manner.
展开▼