Unsupervised system to classify SO2 pollutant concentrations in Salamanca, Mexico

Salamanca is cataloged as one of the most polluted cities in Mexico. In order to observe the behavior and clarify the influence of wind parameters on the Sulphur Dioxide (SO"2) concentrations a Self-Organizing Maps (SOM) Neural Network have been implemented at three monitoring locations for the period from January 1 to December 31, 2006. The maximum and minimum daily values of SO"2 concentrations measured during the year of 2006 were correlated with the wind parameters of the same period. The main advantages of the SOM Neural Network is that it allows to integrate data from different sensors and provide readily interpretation results. Especially, it is powerful mapping and classification tool, which others information in an easier way and facilitates the task of establishing an order of priority between the distinguished groups of concentrations depending on their need for further research or remediation actions in subsequent management steps. For each monitoring location, SOM classifications were evaluated with respect to pollution levels established by Health Authorities. The classification system can help to establish a better air quality monitoring methodology that is essential for assessing the effectiveness of imposed pollution controls, strategies, and facilitate the pollutants reduction.

[1]  Ferhat Karaca,et al.  An online air pollution forecasting system using neural networks. , 2008, Environment international.

[2]  Klaus Obermayer,et al.  Self-organizing maps and clustering methods for matrix data , 2004, Neural Networks.

[3]  Hanefi Bayraktar,et al.  Impacts of some meteorological parameters on SO2 and TSP concentrations in Erzurum, Turkey. , 2005, Chemosphere.

[4]  Tai-Yi Yu,et al.  Delineation of air-quality basins utilizing multivariate statistical methods in Taiwan , 2001 .

[5]  C. Dolea,et al.  World Health Organization , 1949, International Organization.

[6]  H. Christopher Frey,et al.  Uncertainties in predicted ozone concentrations due to input uncertainties for the UAM-V photochemical grid model applied to the July 1995 OTAG domain , 2001 .

[7]  Michael Jerrett,et al.  The use of wind fields in a land use regression model to predict air pollution concentrations for health exposure studies , 2007 .

[8]  Esa Alhoniemi,et al.  Clustering of the self-organizing map , 2000, IEEE Trans. Neural Networks Learn. Syst..

[9]  Raktim Pal,et al.  The pollution status of atmospheric carbonyls in a highly industrialized area. , 2008, Journal of hazardous materials.

[10]  Paolo Vestrucci,et al.  Using meteorological data to model pollutant dispersion in the atmosphere , 2009, Environ. Model. Softw..

[11]  N. Ilten,et al.  Investigating the impacts of some meteorological parameters on air pollution in Balikesir, Turkey , 2008, Environmental monitoring and assessment.

[12]  Erkan Aydar,et al.  Clustering of volcanic ash arising from different fragmentation mechanisms using Kohonen self-organizing maps , 2007, Comput. Geosci..

[13]  Jehng-Jung Kao,et al.  Utilizing multiobjective analysis to determine an air quality monitoring network in an industrial district , 2006 .

[14]  T. Warren Liao,et al.  Clustering of time series data - a survey , 2005, Pattern Recognit..

[15]  R. Sivacoumar,et al.  Assessment of contribution of SO2 and NO2 from different sources in Jamshedpur region, India , 2005 .

[16]  Ke-Lin Du,et al.  Clustering: A neural network approach , 2010, Neural Networks.

[17]  J. Miguel Barrón-Adame,et al.  Error Weighting in Artificial Neural Networks Learning Interpreted as a Metaplasticity Model , 2007, IWINAC.

[18]  H. Elminir.  Dependence of urban air pollutants on meteorology. , 2005, The Science of the total environment.

[19]  Nelson L. Seaman,et al.  Meteorological modeling for air-quality assessments , 2000 .

[20]  C. Brémard,et al.  PM10 air quality variations in an urbanized and industrialized harbor , 2008 .

[21]  RobertInger.  National Institute of Ecology , 1970, The Bulletin of the Ecological Society of America.

[22]  O Ozden,et al.  Assessment of ambient air quality in Eskişehir, Turkey. , 2008, Environment international.

[23]  Mark Lawrence,et al.  Evaluation of emissions and air quality in megacities , 2008 .

[24]  Emrullah Demirci,et al.  Statistical analysis of wind circulation and air pollution in urban Trabzon , 2000 .

[25]  Hsin-Chung Lu,et al.  Estimating the frequency distributions of PM10 and PM2.5 by the statistics of wind speed at Sha-Lu, Taiwan. , 2002, The Science of the total environment.

[26]  M. W Gardner,et al.  Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences , 1998 .

[27]  A. Vega-Corona,et al.  Prevision of industrial SO2 pollutant concentration applying ANNs , 2009, 2009 7th IEEE International Conference on Industrial Informatics.

[28]  K. Bignal,et al.  Effects of air pollution from road transport on growth and physiology of six transplanted bryophyte species. , 2008, Environmental pollution.

[29]  Robert Joumard,et al.  Air quality and urban space management , 1996 .

[30]  Hanna J. Cortner,et al.  Making science relevant to environmental policy , 2000 .

[31]  Ignacio J. Turias,et al.  A competitive neural network approach for meteorological situation clustering , 2006 .

[32]  M. Valdés,et al.  Assessment of vehicle emissions projections in Madrid (Spain) from 2004 to 2012 considering several control strategies , 2008 .

[33]  C. Chan,et al.  Air pollution in mega cities in China , 2008 .

[34]  Anthony J. Richardson,et al.  Using self-organizing maps to identify patterns in satellite imagery , 2003 .

[35]  A. Dannenberg,et al.  The built environment, climate change, and health: opportunities for co-benefits. , 2008, American journal of preventive medicine.

[36]  Robert Joumard,et al.  Air pollution related to transport , 2009 .

[37]  Stephen Budiansky,et al.  US Environmental Protection Agency: Political pollution unabated , 1983, Nature.

[38]  Steven R. Hanna,et al.  Evaluation of a photochemical grid model using estimates of concentration probability density functions , 2002 .

[39]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[40]  Michael J. Watts,et al.  Estimating the risk of insect species invasion: Kohonen self-organising maps versus k-means clustering. , 2009 .

[41]  Helena Ribeiro,et al.  Influence of atmospheric ozone, PM10 and meteorological factors on the concentration of airborne pollen and fungal spores , 2008 .

[42]  A Riccio,et al.  The application of a trajectory classification procedure to interpret air pollution measurements in the urban area of Naples (Southern Italy). , 2007, The Science of the total environment.

[43]  Berta Galán,et al.  Assessment of Self-Organizing Map artificial neural networks for the classification of sediment quality. , 2008, Environment international.

[44]  N. T. Kim Oanh,et al.  Meteorological pattern classification and application for forecasting air pollution episode potential in a mountain-valley area , 2005 .

[45]  Soon-Hwan Lee,et al.  Influence of dense surface meteorological data assimilation on the prediction accuracy of ozone pollution in the southeastern coastal area of the Korean Peninsula , 2007 .

[46]  C Borrego,et al.  Air quality assessment for Portugal. , 2007, The Science of the total environment.