Prediction of PM10 and SO2 exceedances to control air pollution in the Bay of Algeciras, Spain

In this paper, the authors apply different classification techniques in order to provide 24 h advance forecasts of the daily peaks of SO2 and PM10 concentrations in the Bay of Algeciras. K-nearest-neighbours, multilayer neural network with backpropagation and support vector machines (SVMs) are the classification methods used. The aim of this research is to obtain a suitable prediction model that would enable us to predict the peaks of pollutant concentrations in critical meteorological situations caused by the widespread existing industry and population in the area. A resampling strategy with twofold crossvalidation has been applied, using different quality indexes to evaluate the performance of the prediction models. SVM models achieved better true positive rate and accuracy (ACC) quality indexes. Results of ACC index value of 0.795 for PM10 and 0.755 for SO2 showed the ability of the model to predict peaks and non-peaks correctly.

[1]  Gavin C. Cawley,et al.  Modelling SO2 concentration at a point with statistical approaches , 2004, Environ. Model. Softw..

[2]  A. Atiya,et al.  Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2005, IEEE Transactions on Neural Networks.

[3]  D. Dockery,et al.  Health Effects of Fine Particulate Air Pollution: Lines that Connect , 2006, Journal of the Air & Waste Management Association.

[4]  X. Querol,et al.  Source apportionment of PM10 and PM2.5 at multiple sites in the strait of Gibraltar by PMF: impact of shipping emissions , 2011, Environmental science and pollution research international.

[5]  Jorge Reyes,et al.  An integrated neural network model for PM10 forecasting , 2006 .

[6]  Ignacio Turias Domínguez,et al.  Prediction of Peak Concentrations of PM10 in the Area of Campo de Gibraltar (Spain) Using Classification Models , 2011, SOCO.

[7]  W. Wilson,et al.  Fine particles and coarse particles: concentration relationships relevant to epidemiologic studies. , 1997, Journal of the Air & Waste Management Association.

[8]  J. Sjöberg.  Neural networks for modelling and control of dynamic systems: M. Nørgaard, O. Ravn, N. K. Poulsen and L. K. Hansen. Springer-Verlag, London Berlin Heidelberg, 2000, pp. xiv+246 , 2004 .

[9]  W. González-Manteiga,et al.  Support vector machines and gradient boosting for graphical estimation of a slate deposit , 2004 .

[10]  Niels Kjølstad Poulsen,et al.  Neural Networks for Modelling and Control of Dynamic Systems: A Practitioner’s Handbook , 2000 .

[11]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[12]  Yao Zhu,et al.  Assessment for surface water quality in Lake Taihu Tiaoxi River Basin China based on support vector machine , 2013, Stochastic Environmental Research and Risk Assessment.

[13]  Anastasia K Paschalidou,et al.  Forecasting hourly PM10 concentration in Cyprus through artificial neural networks and multiple regression models: implications to local environmental management , 2011, Environmental science and pollution research international.

[14]  Ujjwal Kumar,et al.  ARIMA forecasting of ambient air pollutants (O3, NO, NO2 and CO) , 2010 .

[15]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[16]  David G. Stork,et al.  Pattern Classification , 1973 .

[17]  J C Bailar,et al.  The association between daily mortality and ambient air particle pollution in Montreal, Quebec. 1. Nonaccidental mortality. , 2001, Environmental research.

[18]  David G. Stork,et al.  Pattern Classification (2nd ed.) , 1999 .

[19]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[20]  J Schwartz,et al.  Is daily mortality associated specifically with fine particles? , 1996, Journal of the Air & Waste Management Association.

[21]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[22]  Alexander J. Smola,et al.  Support Vector Method for Function Approximation, Regression Estimation and Signal Processing , 1996, NIPS.

[23]  J M Gorriz,et al.  Prediction of CO maximum ground level concentrations in the Bay of Algeciras, Spain using artificial neural networks. , 2008, Chemosphere.

[24]  Boosting for real and functional samples: an application to an environmental problem , 2008 .

[25]  Giorgio Corani,et al.  Air quality prediction in Milan: feed-forward neural networks, pruned neural networks and lazy learning , 2005 .

[26]  Gavin C. Cawley,et al.  A rigorous inter-comparison of ground-level ozone predictions , 2003 .

[27]  J. L. Carrasco-Rodriguez,et al.  Effective 1-day ahead prediction of hourly surface ozone concentrations in eastern Spain using linear models and neural networks , 2002 .

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

[29]  M. Zunckel,et al.  A novel air pollution index based on the relative risk of daily mortality associated with short-term exposure to common air pollutants , 2007 .

[30]  Georgios Grivas,et al.  Artificial neural network models for prediction of PM10 hourly concentrations, in the Greater Area of Athens, Greece , 2006 .

[31]  N. Seaman.  Meteorological modeling for air-quality assessments q , 2000 .

[32]  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..

[33]  Ignacio J. Turias,et al.  Pitting corrosion behaviour of austenitic stainless steel using artificial intelligence techniques , 2012, J. Appl. Log..

[34]  Pavlos Kassomenos,et al.  Assessing air quality with regards to its effect on human health in the European Union through air quality indices , 2013 .

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

[36]  Joel Schwartz,et al.  The association of daily sulfur dioxide air pollution levels with hospital admissions for cardiovascular diseases in Europe (The Aphea-II study). , 2003, European heart journal.

[37]  F. Nejadkoorki,et al.  Forecasting Extreme PM 10 Concentrations Using Artificial Neural Networks , 2012 .

[38]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[39]  Saeid Baroutian,et al.  Forecasting Extreme PM10 Concentrations Using Artificial Neural Networks , 2012 .

[40]  Marija Zlata Boznar,et al.  A neural network-based method for short-term predictions of ambient SO2 concentrations in highly polluted industrial areas of complex terrain , 1993 .

[41]  Shenglian Guo,et al.  Comparative study of monthly inflow prediction methods for the Three Gorges Reservoir , 2014, Stochastic Environmental Research and Risk Assessment.

[42]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[43]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[44]  I. Turias,et al.  Prediction models of CO, SPM and SO2 concentrations in the Campo de Gibraltar Region, Spain: a multiple comparison strategy , 2008, Environmental monitoring and assessment.

[45]  Snezhana Georgieva Gocheva-Ilieva,et al.  Time series analysis and forecasting for air pollution in small urban area: an SARIMA and factor analysis approach , 2014, Stochastic Environmental Research and Risk Assessment.