Ozone prediction based on meteorological variables: a fuzzy inductive reasoning approach

Abstract. MILAGRO project was conducted in Mexico City during March 2006 with the main objective of study the local and global impact of pollution generated by megacities. The research presented in this paper is framed in MILAGRO project and is focused on the study and development of modeling methodologies that allow the forecasting of daily ozone concentrations. The present work aims to develop Fuzzy Inductive Reasoning (FIR) models using the Visual-FIR platform. FIR offers a model-based approach to modeling and predicting either univariate or multivariate time series. Visual-FIR offers an easy-friendly environment to perform this task. In this research, long term prediction of maximum ozone concentration in the downtown of Mexico City Metropolitan Area is performed. The data were registered every hour and include missing values. Two modeling perspectives are analyzed, i.e. monthly and seasonal models. The results show that the developed models are able to predict the diurnal variation of ozone, including its maximum daily value in an accurate manner.

[1]  J. Chenevez,et al.  Operational ozone forecasts for the region of Copenhagen by the Danish Meteorological Institute , 2001 .

[2]  Kasım Koçak,et al.  Nonlinear time series prediction of O3 concentration in Istanbul , 2000 .

[3]  Mahmut Bayramoglu,et al.  Adaptive neuro-fuzzy based modelling for prediction of air pollution daily levels in city of Zonguldak. , 2006, Chemosphere.

[4]  Wei-Zhen Lu,et al.  Forecasting Ozone Levels and Analyzing Their Dynamics by a Bayesian Multilayer Perceptron Model for Two Air-Monitoring Sites in Hong Kong , 2006 .

[5]  M. Mesbah,et al.  Modelling and analysis of ozone episodes , 2000, Environ. Model. Softw..

[6]  G. Önkal-Engin,et al.  Assessment of urban air quality in Istanbul using fuzzy synthetic evaluation , 2004 .

[7]  Bush Jones,et al.  Architecture of systems problem solving , 1986, Journal of the American Society for Information Science.

[8]  Àngela Nebot,et al.  Local Maximum Ozone Concentration Prediction Using Soft Computing Methodologies , 2003 .

[9]  W. Geoffrey Cobourn,et al.  Fuzzy system models combined with nonlinear regression for daily ground-level ozone predictions , 2007 .

[10]  Wei-Zhen Lu,et al.  Potential assessment of a neural network model with PCA/RBF approach for forecasting pollutant trends in Mong Kok urban air, Hong Kong. , 2004, Environmental research.

[11]  Charles S. Wasson.  The Architecture of Systems , 2005 .

[12]  Franz Wotawa,et al.  Deriving qualitative rules from neural networks - a case study for ozone forecasting , 2001, AI Commun..

[13]  Short-Range Prediction of Tropospheric Ozone Concentrations and Exceedances for Baton Rouge, Louisiana , 2003 .

[14]  Àngela Nebot,et al.  Modeling and Simulation of the Central Nervous System Control with Generic Fuzzy Models , 2003, Simul..

[15]  K Héberger,et al.  Prediction of ozone concentration in ambient air using multivariate methods. , 2004, Chemosphere.

[16]  Àngela Nebot,et al.  COMBINED QUALITATIVE/QUANTITATIVE SIMULATION MODELS OF CONTINUOUS-TIME PROCESSES USING FUZZY INDUCTIVE REASONING TECHNIQUES , 1996 .

[17]  M. Alvim-Ferraz,et al.  Prediction of ozone concentrations in Oporto city with statistical approaches. , 2006, Chemosphere.

[18]  D. Assimacopoulos,et al.  Forecasting Daily Maximum Ozone Concentrations in the Athens Basin , 1999 .

[19]  Àngela Nebot,et al.  Growth model for white shrimp in semi-intensive farming using inductive reasoning methodology , 1998 .

[20]  Saleh M. Al-Alawi,et al.  Assessment and prediction of tropospheric ozone concentration levels using artificial neural networks , 2002, Environ. Model. Softw..

[21]  Dong-Sool Kim,et al.  A new method of ozone forecasting using fuzzy expert and neural network systems. , 2004, The Science of the total environment.

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

[23]  Àngela Nebot,et al.  Visual-FIR: A tool for model identification and prediction of dynamical complex systems , 2008, Simul. Model. Pract. Theory.

[24]  José David Martín-Guerrero,et al.  Neural networks for analysing the relevance of input variables in the prediction of tropospheric ozone concentration , 2006 .

[25]  N Moussiopoulos,et al.  Statistical analysis of environmental data as the basis of forecasting: an air quality application. , 2002, The Science of the total environment.

[26]  Christian Ghiaus,et al.  Linear fuzzy-discriminant analysis applied to forecast ozone concentration classes in sea-breeze regime , 2003 .

[27]  Wei-Zhen Lu,et al.  Interval estimation of urban ozone level and selection of influential factors by employing automatic relevance determination model. , 2006, Chemosphere.

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

[29]  Francesco Carlo Morabito,et al.  Fuzzy neural identification and forecasting techniques to process experimental urban air pollution data , 2003, Neural Networks.

[30]  G. Soja,et al.  Ozone indices based on simple meteorological parameters: potentials and limitations of regression and neural network models , 1999 .

[31]  Franz Wotawa,et al.  Local Maximum Ozone Concentration Prediction Using Neural Networks , 1999 .

[32]  Brent R. Young,et al.  Fuzzy logic modeling of surface ozone concentrations , 2005, Comput. Chem. Eng..