Spatial regression analysis of NOx and O3 concentrations in Madrid urban area using Radial Basis Function networks

Abstract This paper discusses the performance of Radial Basis Function networks (RBF) in a problem of spatial regression of pollutants in Madrid. Specifically, the spatial regression of NO x and O 3 is considered, in such a way that, starting from a set of measuring points provided by the air quality monitoring network of Madrid, the complete surface of the pollutants in the city is obtained. This pollutant surface can be used as an initial step for modeling intra-urban pollution using land-use regression techniques for example. Also, different works has used a pollutant surface to study the patterns of pollution in different cities in the world and also to establish their air monitoring networks under mathematical criteria. The paper is focussed in analyzing the performance of RBF networks to obtain this first pollutant surface, so different RBF training algorithms are tested in this paper. Specifically, evolutionary-based RBF training algorithms are described, and compared with classical training algorithms for RBF networks with Gaussian kernels. The inclusion of meteorological variables in the RBF networks are also discussed in the paper. The experimental part of the article studies real results of the application of RBF networks to obtain a first pollutant surface of NO x and O 3 , using the data of the air pollution monitoring network of Madrid and the meteorological network of the city.

[1]  Michael Brauer,et al.  Application of land use regression to estimate long-term concentrations of traffic-related nitrogen oxides and fine particulate matter. , 2007, Environmental science & technology.

[2]  Juan Julián Merelo Guervós,et al.  Evolving RBF neural networks for time-series forecasting with EvRBF , 2004, Inf. Sci..

[3]  Panagiotis Patrinos,et al.  A two-stage evolutionary algorithm for variable selection in the development of RBF neural network models , 2005 .

[4]  Romà Tauler,et al.  Investigation of geographical and temporal distribution of tropospheric ozone in Catalonia (North-East Spain) during the period 2000–2004 using multivariate data analysis methods , 2006 .

[5]  Eric Mayer,et al.  Analytical determination and classification of pollutant concentration fields using air pollution monitoring network data: Methodology and application in the Paris area, during episodes with peak nitrogen dioxide levels , 2000, Environ. Model. Softw..

[6]  Yves Candau,et al.  Hourly ozone prediction for a 24-h horizon using neural networks , 2008, Environ. Model. Softw..

[7]  Claudio Silva,et al.  Optimization of the atmospheric pollution monitoring network at Santiago de Chile , 2003 .

[8]  Mingchao Zhu,et al.  Radial basis function networks combined with genetic algorithm applied to nondestructive determination of compound erythromycin ethylsuccinate powder , 2008 .

[9]  Gabriel Ibarra-Berastegi,et al.  From diagnosis to prognosis for forecasting air pollution using neural networks: Air pollution monitoring in Bilbao , 2008, Environ. Model. Softw..

[10]  Bernhard Sick,et al.  Architecture optimization of radial basis function networks with a combination of hard- and soft-computing techniques , 2003, SMC'03 Conference Proceedings. 2003 IEEE International Conference on Systems, Man and Cybernetics. Conference Theme - System Security and Assurance (Cat. No.03CH37483).

[11]  Xin Yao,et al.  Evolutionary programming using mutations based on the Levy probability distribution , 2004, IEEE Transactions on Evolutionary Computation.

[12]  Pentti Minkkinen,et al.  Estimation of the variance of sampling of process analytical and environmental emissions measurements , 2007 .

[13]  Kazuhiko Ito,et al.  A land use regression for predicting fine particulate matter concentrations in the New York City region , 2007 .

[14]  D. E. Goldberg,et al.  Genetic Algorithms in Search , 1989 .

[15]  M. Kubat,et al.  Decision trees can initialize radial-basis function networks , 1998, IEEE Trans. Neural Networks.

[16]  Joan O. Grimalt,et al.  Prediction of daily ozone concentration maxima in the urban atmosphere , 2006 .

[17]  Thomas Bäck,et al.  An Overview of Evolutionary Algorithms for Parameter Optimization , 1993, Evolutionary Computation.

[18]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[19]  Xin Yao,et al.  Evolutionary programming made faster , 1999, IEEE Trans. Evol. Comput..

[20]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[21]  Olav M. Kvalheim,et al.  OZONE FORECASTING FROM METEOROLOGICAL VARIABLES. PART II. DAILY MAXIMUM GROUND-LEVEL OZONE CONCENTRATION FROM LOCAL WEATHER FORECASTS , 1998 .

[22]  Marco Pintore,et al.  Automatic design of growing radial basis function neural networks based on neighboorhood concepts , 2007 .

[23]  Olav M. Kvalheim,et al.  Ozone forecasting from meteorological variables , 1998 .

[24]  Pavlos S. Kanaroglou,et al.  Establishing an air pollution monitoring network for intra-urban population exposure assessment: A location-allocation approach , 2005 .

[25]  Marco Pintore,et al.  Automatical initialization of RBF neural networks , 2007 .

[26]  David B. Fogel,et al.  An introduction to simulated evolutionary optimization , 1994, IEEE Trans. Neural Networks.

[27]  Gabriel Ibarra-Berastegi,et al.  Regression and multilayer perceptron-based models to forecast hourly O3 and NO2 levels in the Bilbao area , 2006, Environ. Model. Softw..

[28]  S. M. Lo,et al.  Application of evolutionary neural network method in predicting pollutant levels in downtown area of Hong Kong , 2003, Neurocomputing.

[29]  Bert Brunekreef,et al.  Estimated long-term outdoor air pollution concentrations in a cohort study , 2007 .

[30]  J. Mark.  Introduction to radial basis function networks , 1996 .

[31]  A. Clappier,et al.  Summer ozone episodes in the Greater Madrid area. Analyzing the ozone response to abatement strategies by modelling , 2002 .

[32]  V. Alexandrov,et al.  A comprehensive sensitivity analysis of the WRF model for air quality applications over the Iberian Peninsula , 2008 .

[33]  Simon Kingham,et al.  Mapping Urban Air Pollution Using GIS: A Regression-Based Approach , 1997, Int. J. Geogr. Inf. Sci..

[34]  X. Yao.  Evolving Artificial Neural Networks , 1999 .

[35]  N Künzli,et al.  A land use regression model for predicting ambient fine particulate matter across Los Angeles, CA. , 2007, Journal of environmental monitoring : JEM.

[36]  J. Gulliver,et al.  A review of land-use regression models to assess spatial variation of outdoor air pollution , 2008 .

[37]  M. Pujadas,et al.  Estimates of atmospheric particle emissions from bulk handling of dusty materials in Spanish Harbours , 2007 .

[38]  R. Tauler,et al.  Variation patterns of nitric oxide in Catalonia during the period from 2001 to 2006 using multivariate data analysis methods. , 2009, Analytica chimica acta.

[39]  Bruce A. Whitehead,et al.  Cooperative-competitive genetic evolution of radial basis function centers and widths for time series prediction , 1996, IEEE Trans. Neural Networks.

[40]  Xin Yao,et al.  Self-adaptive differential evolution with neighborhood search , 2008, 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence).

[41]  Toshihide Tsuda,et al.  Application of land use regression to regulatory air quality data in Japan. , 2009, The Science of the total environment.

[42]  R. Storn,et al.  Differential Evolution: A Practical Approach to Global Optimization (Natural Computing Series) , 2005 .

[43]  A. Kai Qin,et al.  Self-adaptive differential evolution algorithm for numerical optimization , 2005, 2005 IEEE Congress on Evolutionary Computation.