Skip to main content

Hybrid Model for Urban Air Pollution Forecasting: A Stochastic Spatio-Temporal Approach

Abstract

Air pollution is usually driven by a complex combination of factors in which meteorology, physical obstacles, and interactions between pollutants play significant roles. Considering the characteristics of urban atmospheric pollution and its consequent impacts on human health and quality of life, forecasting models have emerged as an effective tool to identify and forecast air pollution episodes. The overall objective of the present work is to produce forecasts of pollutant concentrations with high spatio-temporal resolution and to quantify the uncertainty in those forecasts. Therefore, a new approach was developed based on a two-step methodology. Firstly, neural network models were used to generate short-term temporal forecasts based on air pollution and meteorology data. The accuracy of those forecasts was then evaluated against an independent set of historical data. Secondly, local conditional distributions of the observed values with respect to the predicted values were used to perform spatial stochastic simulations for the entire geographic area of interest. With this approach the spatio-temporal dispersion of a pollutant can be predicted, while accounting for both the temporal uncertainty in the forecast (reflecting the neural networks efficiency at each monitoring station) and the spatial uncertainty as revealed by the spatial variograms. Based on an analysis of the results, our proposed method offers a highly promising alternative for the characterization of urban air quality.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

References

  • Agirre-Basurko E, Ibarra-Berastegi G, Madariaga I (2006) Regression and multilayer perceptron-based models to forecast hourly O3 and NO2 levels in the Bilbao area. Environ Model Softw 21:430–446

    Article  Google Scholar 

  • APA—Agência Portuguesa do Ambiente (2008) Evolução da qualidade do ar em Portugal entre 2001 e 2005. Report

  • Atkinson PM, Lloyd CD (2001) Ordinary and indicator kriging of monthly mean nitrogen dioxide concentrations in the United Kingdom. In: Monestiez P et al (eds) GeoENV VIII-geostatistics for environmental applications. Kluwer Academic, Norwell, pp 33–44

    Chapter  Google Scholar 

  • Bilonick RA (1983) Risk qualified maps of hydrogen ion concentration for the New York state area for 1966–1978. Atmos Environ 17:2513–2524

    Article  Google Scholar 

  • Bilonick RA (1985) The space–time distribution of sulfate deposition in the northeastern united states. Atmos Environ 19:1829–1845

    Article  Google Scholar 

  • Cobourn W, Dolcine L, French M, Hubbard M (2000) A comparison of nonlinear regression and neural network models for ground-level ozone forecasting. J Air Waste Manage Assoc 50:1999–2009

    Article  Google Scholar 

  • Cressie N, Kaiser MS, Daniels MJ, Aldworth J, Lee J, Lahiri SN, Cox LH (1999) Spatial analysis of particulate matter in an urban environment. In: Gomez-Hernandez J, Soares A, Froidevaux R (eds) GeoENV II—geostatistics for environmental applications. Kluwer Academic, Dordrecht, pp 41–52

    Chapter  Google Scholar 

  • Demuzere M, Trigo R, Arellano V, van Lipzig N (2009) The impact of weather and atmospheric circulation on O3 and PM10 levels at a rural mid-latitude site. Atmos Chem Phys 9:2695–2714

    Article  Google Scholar 

  • Dutot AL, Rynkiewicz J, Steiner FE, Rude J (2007) A 24-h forecast of ozone peaks and exceedance levels using neural classifiers and weather predictions. Environ Model Softw 22:1261–1269

    Article  Google Scholar 

  • EC—European Community (2006) Development of a methodology to assess population exposed to high levels of noise and air pollution close to major transport infrastructure. Final report. Entec UK limited

  • EEA—European Environment Agency (2011) Air quality in Europe. Technical report No 12/2011

  • EEA—European Environment Agency (2010) The European environment–state and outlook 2010: synthesis. European Environment Agency, Copenhagen

  • Franco C, Soares A, Delgado J (2006) Geostatistical modelling of heavy metal contamination in the topsoil of Guadiamar river margins (Spain) using a stochastic simulation technique. Geoderma 136(3–4):852–864

    Article  Google Scholar 

  • Gardner M, Dorling S (2000) Statistical surface ozone models: an improved methodology to account for non-linear behaviour. Atmos Environ 34:21–34

    Article  Google Scholar 

  • Gardner M, Dorling S (1999) Neural network modelling and prediction of hourly NO x and NO2 concentrations in urban air in London. Atmos Environ 33:709–719

    Article  Google Scholar 

  • Gomez-Hernandez J, Journel AG (1993) Joint sequential simulation of multi-Gaussian fields. In: Soares A (ed) Geostatistics TROIA’92. Kluwer Academic, Dordrecht, pp 85–94

    Google Scholar 

  • Goovaerts P (1997) Geostatistics for natural resources evaluation. Oxford Univ. Press, New York

    Google Scholar 

  • Hooyberghs J, Mensink C, Dumont G, Fierens F, Brasseur O (2005) A neural network forecast for daily average PM10 concentrations in Belgium. Atmos Environ 39:3279–3289

    Article  Google Scholar 

  • Horta A, Soares A (2010) Direct sequential co-simulation with joint probability distributions. Math Geosci 42:269–292

    Article  Google Scholar 

  • INE—Instituto Nacional de Estatística. www.ine.pt. Accessed 17 July 2012

  • Kolehmainen M, Martikainen H, Ruuskanen J (2001) Neural networks and periodic components used in air quality forecasting. Atmos Environ 35:815–825

    Article  Google Scholar 

  • Kyriakidis P, Journel A (1999) Geostatistical space–time models: a review. Math Geol 31(6):651–685

    Article  Google Scholar 

  • Lal B, Tripathy SS (2012) Prediction of dust concentration in open cast coal mine using artificial neural network. Atmos Pollut Res 3:211–218

    Article  Google Scholar 

  • Lamb RG (1983) A regional scale (1000 km) model of photochemical air pollution, part I: theoretical formulation. EPA 600/3-83-035. US Environmental Protection Agency, Research Triangle Park, NC

  • Luecken DJ, Hutzell WT, Gipson GL (2006) Development and analysis of air quality modeling simulations for hazardous air pollutants. Atmos Environ 40:5087–5096

    Article  Google Scholar 

  • Monestiez P, Meiring W, Sampson PD, Guttorp P (1997) Modelling non-stationary spatial covariance structure from space–time monitoring data. Ciba Foundation symposium. 01/1997; 210:38-48; discussion 48-51, 68-78.

  • Monteiro A, Vautard R, Borrego C, Miranda A (2005) Long-term simulations of photo oxidant pollution over Portugal using the CHIMERE model. Atmos Environ 39(17):3089–3101

    Article  Google Scholar 

  • Morris RE, Meyers TC (1990) User’s guide for the Urban Airshed Model. In: User’s manual for UAM (CB-IV). EPA-450/4-90-007A, vol. I. US Environmental Protection Agency, Research Triangle Park

    Google Scholar 

  • Nunes C, Soares A (2005) Geostatistical space–time simulation model. Environmetrics 16:393–404

    Article  Google Scholar 

  • Pereira MJ (1999) Air quality modelling and simulation. PhD Dissertation, Instituto Superior Técnico, Lisbon, Portugal

  • Perez P, Reyes J (2002) Prediction of maximum of 24-h average of PM10 concentrations 30h in advance in Santiago. Chile Atmos Environ 36:4555–4561

    Article  Google Scholar 

  • Perez P, Trier A, Reyes J (2000) Prediction of PM2.5 concentrations several hours in advance using neural networks in Santiago, Chile. Atmos Environ 34:1189–1196

    Article  Google Scholar 

  • Russo A, Trigo R, Soares A (2008) Stochastic modelling applied to air quality space–time characterization. In: Soares A, Pereira MJ, Dimitrakopoulos R (eds) GeoENV VI-geostatistics for environmental applications. Springer, Berlin, pp 83–93

    Chapter  Google Scholar 

  • Soares A (2001) Sequential direct simulation and co-simulation. Math Geol 33(8):911–926

    Article  Google Scholar 

  • Soares A, Pereira MJ (2007) Space–time modelling of air quality for environmental-risk maps: a case study in South Portugal. Comput Geosci 33(10):1327–1336

    Article  Google Scholar 

  • Sokhi RS, San José R, Kitwiroon N, Fragkou E, Pérez JL, Middleton DR (2006) Prediction of ozone levels in London using the MM5–CMAQ modelling system. Environ Model Softw 21:566–576

    Article  Google Scholar 

  • Srivastava RM (1992) Reservoir characterization with probability field simulation. SPE Paper 24753

  • Trigo R, DaCamara C (2000) Circulation weather types and their impact on the precipitation regime in Portugal. Int J Climatol 20:1559–1581

    Article  Google Scholar 

  • Trigo R, Palutikof J (1999) Simulation of daily temperatures for climate change scenarios over Portugal: a neural network model approach. Clim Res 13:45–59

    Article  Google Scholar 

  • Turias I, González F, Martin M, Galindo P (2007) Prediction models of CO, SPM and SO2 concentrations in the Campo de Gibraltar region, Spain: a multiple comparison strategy. Environ Monit Assess 143:131–146

    Article  Google Scholar 

Download references

Acknowledgements

The authors acknowledge the Instituto de Meteorologia and Agência Portuguesa do Ambiente for the meteorological and environmental data, respectively. The authors also acknowledge the Fundação para a Ciência e Tecnologia from the Science, Technology and Superior Education Ministry, for supporting this research through grant SFRH/BD/27765/2006.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Ana Russo.

Appendix Local Conditional Distributions of Observed Values Given the Predicted Value of a Contaminant

Appendix Local Conditional Distributions of Observed Values Given the Predicted Value of a Contaminant

Bivariate distributions between predicted and equivalent real values [Z (x α ,t 0−i ),Z(x α ,t 0−i )] (x α =1, N m , i=1,N T ) are calculated at each monitoring station using a independent set of historical data not used in the training step of the NN model. These local bi-distributions measure the local accuracy of the temporal predictions at each monitoring station. Experimental bi-plots of two monitoring stations with different prediction accuracies are associated with different uncertainties. For example, a bi-plot with a significant cloud spread of high values has a high level of uncertainty regarding the real observed values for a certain predicted high value. A bi-plot with a less uncertain cloud of low and high values has less uncertainty regarding the real observed values. Based on the bi-plots, the local conditional distribution is determined for each day and for each location.

For a certain predicted value z (x α ,t 0) at instant t 0, the local conditional distribution: F[Z(x α ,t 0)|Z (x α ,t 0)=z ] can be calculated from the bi-distributions [Z (x α ,t 0−i ),Z (x α ,t 0−i )]. A practical implementation of the local conditional distributions evaluation is presented in Horta and Soares (2010) and can be summarized as follows: First, the user must define the minimum number of data N c of each class of the conditional histogram F[Z(x α ,t 0−i )|Z (x α ,t 0)=z ]. By ranking the pairs of values [Z(x i ),Z (x i )] by increasing the order of Z , then for one certain conditioning value m=Z (x j ) we have the corresponding Z(x j ), at the jth position of the ordered [Z(x i ),Z (x i )]. Hence, F[Z(x)|Z (x)=m] comprises the closest N c values of Z(x j ) in the rank-ordered list.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Russo, A., Soares, A.O. Hybrid Model for Urban Air Pollution Forecasting: A Stochastic Spatio-Temporal Approach. Math Geosci 46, 75–93 (2014). https://doi.org/10.1007/s11004-013-9483-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11004-013-9483-0

Keywords

  • Air quality
  • Neural networks
  • Stochastic simulation
  • PM10
  • Uncertainty