A SOM‐based methodology for classifying air quality monitoring stations

The application of mathematical tools can be necessary to provide an integrated analysis and interpretation of the abundant information that can be collected in air quality monitoring networks. This article develops a methodology based on the use of Self-Organizing Map (SOM) artificial neural networks for integrating data about multiple measured pollutants to group monitoring stations according to their similar air quality. The proposed method considers the subsequent geographical mapping of the clusters of stations observed with the SOM, which can make it possible to detect geographically different areas but that share similar air pollution problems. This methodology is illustrated with its application to a case study in which 517 stations of the Spanish air quality monitoring network were classified considering simultaneously their levels of regulated pollutants in 2005, highlighting some implications of data normalization in the process. In particular, the use of legal limit values to normalize the concentrations of pollutants proved to be especially advisable. Results obtained with the SOM-based methodology, when compared to classifications based directly on legislation, provided more useful classifications for further air quality management actions, and revealed that these types of tools can facilitate the design of air pollution reduction programs by discovering different areas with similar problems. © 2010 American Institute of Chemical Engineers Environ Prog, 2011.

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

[2]  Markus Leuenberger,et al.  Research at Jungfraujoch. , 2008, The Science of the total environment.

[3]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[4]  Marek Wesolowski,et al.  The analysis of seasonal air pollution pattern with application of neural networks , 2005, Analytical and bioanalytical chemistry.

[5]  J. Skrzypski,et al.  Optimizing the prediction models of the air quality state in cities , 2007 .

[6]  Gabriel Ibarra-Berastegi,et al.  Assessing spatial variability of SO2 field as detected by an air quality network using Self-Organizing Maps, cluster, and Principal Component Analysis , 2009 .

[7]  Chung-Liang Chang,et al.  Classification of PM10 distributions in Taiwan , 2006 .

[8]  Goutami Chattopadhyay,et al.  Autoregressive forecast of monthly total ozone concentration: A neurocomputing approach , 2009, Comput. Geosci..

[9]  Stefan Tsakovski,et al.  Chemical composition of water from roofs in Gdansk, Poland. , 2010, Environmental pollution.

[10]  Kimmo Kiviluoto,et al.  Topology preservation in self-organizing maps , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[11]  Juha Vesanto,et al.  SOM-based data visualization methods , 1999, Intell. Data Anal..

[12]  P. Viotti,et al.  Atmospheric urban pollution: applications of an artificial neural network (ANN) to the city of Perugia , 2002 .

[13]  Gavin C. Cawley,et al.  Extensive evaluation of neural network models for the prediction of NO2 and PM10 concentrations, compared with a deterministic modelling system and measurements in central Helsinki , 2003 .

[14]  Esa Alhoniemi,et al.  Self-organizing map in Matlab: the SOM Toolbox , 1999 .

[15]  M. Schuhmacher,et al.  Metal pollution of soils and vegetation in an area with petrochemical industry. , 2003, The Science of the total environment.

[16]  Bruce Dickson,et al.  Comparison of lead isotopes with source apportionment models, including SOM, for air particulates. , 2007, The Science of the total environment.

[17]  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..

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

[19]  Sovan Lek,et al.  Artificial neural networks as a tool in ecological modelling, an introduction , 1999 .

[20]  Miklas Scholz,et al.  A comparative study: Prediction of constructed treatment wetland performance with k-nearest neighbors and neural networks , 2006 .

[21]  J R Viguri,et al.  Toxicity bioassays in core sediments from the Bay of Santander, northern Spain. , 2008, Environmental research.

[22]  P. Brucker.  On the Complexity of Clustering Problems , 1978 .

[23]  Donald W. Bouldin,et al.  A Cluster Separation Measure , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[25]  Gérard Lacroix,et al.  Assessment of self-organizing maps to analyze sole-carbon source utilization profiles. , 2005, Journal of microbiological methods.