Model-based geostatistical interpolation of the annual number of ozone exceedance days in the Netherlands

  • J. van de Kassteele
  • A. L. M. Dekkers
  • A. Stein
  • G. J. M. Velders
Original Paper
First Online:

Abstract

This paper discusses two model-based geostatistical methods for spatial interpolation of the number of days that ground level ozone exceeds a threshold level. The first method assumes counts to approximately follow a Poisson distribution, while the second method assumes a log-Normal distribution. First, these methods were compared using an extensive data set covering the Netherlands, Belgium and Germany. Second, the focus was placed on only the Netherlands, where only a small data set was used. Bayesian techniques were used for parameter estimation and interpolation. Parameter estimates are comparable due to the log-link in both models. Incorporating data from adjacent countries improves parameter estimation. The Poisson model predicts more accurately (maximum kriging standard deviation of 2.16 compared to 2.69) but shows smoother surfaces than the log-Normal model. The log-Normal approach ensures a better representation of the observations and gives more realistic patterns (an RMSE of 2.26 compared to 2.44). Model-based geostatistical procedures are useful to interpolate limited data sets of counts of ozone exceedance days. Spatial risk estimates using existing prior information can be made relating health effects to environmental thresholds.

Keywords

Model-based geostatistics Bayesian inference Count data Ozone Exceedance days 

Abbreviations

MCMC

Markov chain Monte Carlo

This is a preview of subscription content, log in to check access.

References

  1. Besag JE (1994) Discussion on the paper by Grenander and Miller. J R Stat Soc B 56:591–592Google Scholar
  2. Borowiak A, Lagler F, Gerboles M, DeSaeger E (2000) EC harmonization programme for air quality measurements. Intercomparison exercises 1999/2000 for SO2, CO, NO2 and O3. EC report EUR 19629. Joint Research Centre, Ispra ItalyGoogle Scholar
  3. Breslow NE, Clayton DG (1993) Approximate inference in generalized linear mixed models. J Am Stat Ass 88:9–25Google Scholar
  4. Christakos G (1992) Random field models in earth sciences. Academic, New YorkGoogle Scholar
  5. Christensen OF, Ribeiro PJ Jr.(2002) GeoRglm—a package for generalised linear spatial models. R News 2(2):26–28Google Scholar
  6. Christensen OF, Waagepetersen RP (2002) Bayesian prediction of spatial count data using generalised linear mixed models. Biometrics 58:280–286Google Scholar
  7. Cressie NAC (1993) Statistics for spatial data, revised edition. Wiley, New YorkGoogle Scholar
  8. Diggle PJ, Tawn JA, Moyeed RA (1998) Model-based geostatistics (with discussion). J R Stat Soc C 47:299–350Google Scholar
  9. EC (2002) Directive 2002/3/EC of the European Parliament and of the Council of 12 February 2002 relating to ozone in ambient air. Official Journal L 067, 09/03/2002Google Scholar
  10. EEA (1998) Europe’s environment, The second assessment. European Environment Agency. ISBN 92-828-3351-8, Office for Official Publications of the European Communities, Luxembourg. Elsevier Science Ltd. Kidlington, UK, pp 94–108Google Scholar
  11. Elzakker BG van (2001) Monitoring activities in the Dutch national air quality monitoring network in 2000 and 2001. Internal report. RIVM report 723101055, Bilthoven, The NetherlandsGoogle Scholar
  12. ETC/ACC (2003) Airbase air quality information system. European topic centre on air and climate change, Bilthoven, The NetherlandsGoogle Scholar
  13. Feister U, Balzer K (1991) Surface ozone and meteorological predictors on a sub-regional scale. Atmos Environ 25A:1781–1790Google Scholar
  14. Gelman A, Carlin JC, Stern H, Rubin DB (1995) Bayesian data analysis. Chapman & Hall, New YorkGoogle Scholar
  15. Gilks WR, Richardson S, Spiegelhalter DJ (1996) Markov chain Monte Carlo in practice. Chapman & Hall, LondonGoogle Scholar
  16. Gregg JW, Jones CG, Dawson E (2003) Urbanization effects on tree growth in the vicinity of New York city. Nature 424:183–187Google Scholar
  17. Guttorp P, Meiring W, Sampson P (1994) A space–time analysis of ground-level ozone data. Environmetrics 5:241–254Google Scholar
  18. Ihaka R, Gentleman R (1996) R: a language for data analysis and graphics. J Comp Graph Stat 5:299–314Google Scholar
  19. McCullagh P, Nelder JA (1989) Generalized linear models, 2nd edn. Chapman & Hall, LondonGoogle Scholar
  20. Papaspilliopoulus O, Roberts GO, Skold M (2003) Non-centered parameterizations for hierarchical models and data augmentation. In: Bernardo JM, Bayarri S, Dawid JO, Heckerman D, Smith AFM, West M (eds) Bayesian statistics 7. Oxford University Press, OxfordGoogle Scholar
  21. Pinheiro JC, Bates DM (2000) Mixed-effects models in S and S-PLUS. Springer, New YorkGoogle Scholar
  22. Ribeiro PJ Jr, Diggle PJ (1999) Bayesian inference in Gaussian model-based geostatistics. Technical report ST-99-08. Department of Maths and Statistics, Lancaster University, Lancaster UKGoogle Scholar
  23. Ribeiro PJ, Jr Diggle PJ (2001) GeoR: a package for geostatistical analysis. R N EWS 1(2):15–18Google Scholar
  24. Shively TS (1991) An analysis of the trend in ground-level ozone using non-homogeneous Poisson processes. Atmos Environ 25B:387–395Google Scholar
  25. Smith RL (1989) Extreme value analysis of environmental time series: an application to trend detection in ground-level ozone. Stat Sci 4:367–393Google Scholar
  26. UNECE (1996) Critical levels for ozone in Europe: test and finalising the concept. In: Kärenlampi L, Skärby L (eds) UN-ECE workshop report. University of Kuopio, FinlandGoogle Scholar
  27. WHO (1996) Update and revision of the WHO air quality guidelines for Europe. Classical air pollutants; ozone and other photochemical oxidants. European Centre for Environment and Health, Bilthoven, The NetherlandsGoogle Scholar

Copyright information

© Springer-Verlag 2005

Authors and Affiliations

  • J. van de Kassteele
    • 1
    • 2
  • A. L. M. Dekkers
    • 2
  • A. Stein
    • 1
  • G. J. M. Velders
    • 2
  1. 1.Mathematical and Statistical Methods Group, BiometrisWageningen UniversityWageningenThe Netherlands
  2. 2.Netherlands Environmental Assessment Agency - RIVMBilthovenThe Netherlands

Personalised recommendations