Moving window kriging with geographically weighted variograms

  • Paul Harris
  • Martin Charlton
  • A. Stewart Fotheringham
Original Paper


This study adds to our ability to predict the unknown by empirically assessing the performance of a novel geostatistical-nonparametric hybrid technique to provide accurate predictions of the value of an attribute together with locally-relevant measures of prediction confidence, at point locations for a single realisation spatial process. The nonstationary variogram technique employed generalises a moving window kriging (MWK) model where classic variogram (CV) estimators are replaced with information-rich, geographically weighted variogram (GWV) estimators. The GWVs are constructed using kernel smoothing. The resultant and novel MWK–GWV model is compared with a standard MWK model (MWK–CV), a standard nonlinear model (Box–Cox kriging, BCK) and a standard linear model (simple kriging, SK), using four example datasets. Exploratory local analyses suggest that each dataset may benefit from a MWK application. This expectation was broadly confirmed once the models were applied. Model performance results indicate much promise in the MWK–GWV model. Situations where a MWK model is preferred to a BCK model and where a MWK–GWV model is preferred to a MWK–CV model are discussed with respect to model performance, parameterisation and complexity; and with respect to sample scale, information and heterogeneity.


Geostatistics Kriging Nonstationary Nonparametric Variogram 



Research presented in this paper was funded by a Strategic Research Cluster grant (07/SRC/I1168) by the Science Foundation Ireland under the National Development Plan. The authors gratefully acknowledge this support. Thanks are also due to the first author’s PhD studentship at Newcastle University and to Professor Chris Brunsdon for kindly providing the R code for the comap. We also thank the anonymous referees whose comments and insights helped improve the paper.


  1. Anderes EB, Stein ML (2005) Estimating deformations of isotropic Gaussian random fields on the plane. Technical report no. 27, Centre for Integrating Statistics and Environmental Sciences, University of ChicagoGoogle Scholar
  2. Banerjee S, Gelfand AE, Finley AO, Sang H (2008) Gaussian predictive processes for large spatial datasets. J R Stat Soc B Stat Methodol 70:825–848CrossRefGoogle Scholar
  3. Brunsdon C (2001) The Comap: exploring spatial pattern via conditional distributions. Comput Environ Urban Syst 25:53–68CrossRefGoogle Scholar
  4. Cattle JA, McBratney AB, Minasny B (2002) Kriging methods evaluation for assessing the spatial distribution of urban soil lead contamination. J Environ Qual 31:1576–1588CrossRefGoogle Scholar
  5. Chilès J-P, Delfiner P (1999) Geostatistics—modelling spatial uncertainty. Wiley Interscience, New YorkGoogle Scholar
  6. CLAG-Freshwaters (1995) Critical loads of acid deposition for United Kingdom freshwaters. Critical Loads Advisory Group, Sub-report on Freshwaters, ITE, PenicuikGoogle Scholar
  7. Cressie N (1993) Statistics for spatial data. Wiley, New JerseyGoogle Scholar
  8. Dubois G (2008) Editorial. Advances in automatic interpolation for real-time mapping. Stoch Environ Res Risk Assess 22:597–599CrossRefGoogle Scholar
  9. Fotheringham AS, Brunsdon C, Charlton M (2002) Geographically weighted regression—the analysis of spatially varying relationships. Wiley, ChichesterGoogle Scholar
  10. Fuentes M (2001) A new high frequency kriging approach for nonstationary environmental processes. Environmetrics 12:469–483CrossRefGoogle Scholar
  11. Fuentes M (2005) A formal test for nonstationarity of spatial stochastic processes. J Multivar Anal 96:30–54CrossRefGoogle Scholar
  12. Fuentes M, Guttorp P, Challenor P (2003) Statistical assessment of numerical models. Int Stat Rev 71:201–221CrossRefGoogle Scholar
  13. Goovaerts P (2001) Geostatistical modelling of uncertainty in soil science. Geoderma 103:3–26CrossRefGoogle Scholar
  14. Goovaerts P, Jacquez GM, Greiling D (2005) Exploring scale-dependent correlations between cancer mortality rates using factorial kriging and population-weighted semivariograms. Geogr Anal 37:152–182CrossRefGoogle Scholar
  15. Haas TC (1990) Lognormal and moving window methods of estimating acid deposition. J Am Stat Assoc 85:950–963CrossRefGoogle Scholar
  16. Haas TC (1996) Multivariate spatial prediction in the presence of non-linear trend and covariance non-stationarity. Environmetrics 7:145–165CrossRefGoogle Scholar
  17. Haas TC (1998) Statistical assessment of spatio-temporal pollutant trends and meteorological transport models. Atmos Environ 32:1865–1879CrossRefGoogle Scholar
  18. Haas TC (2002) New systems for modelling, estimating, and predicting a multivariate spatio-temporal process. Environmetrics 13:311–332CrossRefGoogle Scholar
  19. Harris P, Brunsdon C (2010) Exploring spatial variation and spatial relationships in a freshwater acidification critical load data set for Great Britain using geographically weighted summary statistics. Comput Geosci 36:54–70CrossRefGoogle Scholar
  20. Higdon D, Swall J, Kern J (1999) Nonstationary spatial modelling. In: Berardo JM, Berger JO, Dawid AP, Smith AFM (eds) Bayesian statistics 6. Oxford University Press, Oxford, pp 761–768Google Scholar
  21. Isaaks EH, Srivastava RM (1989) An introduction to applied geostatistics. Oxford University Press, New YorkGoogle Scholar
  22. Johannesson G, Cressie N (2004) Finding large-scale spatial trends in massive, global, environmental datasets. Environmetrics 15:1–44CrossRefGoogle Scholar
  23. Journel AG (1983) Nonparametric estimation of spatial distributions. Math Geol 15:445–468CrossRefGoogle Scholar
  24. Journel AG (1989) Fundamentals of geostatistics in five lessons. Short course in geology. American Geophysical Union Press, Washington, DCGoogle Scholar
  25. Journel AG, Huijbregts CJ (1978) Mining geostatistics. Academic Press, LondonGoogle Scholar
  26. Kitanidis PK, Shen K-F (1996) Geostatistical interpolation of chemical concentration. Adv Water Resour 19:369–378CrossRefGoogle Scholar
  27. Lahiri SN, Lee Y, Cressie N (2002) On asymptotic distribution and asymptotic efficiency of least squares estimators of spatial variogram parameters. J Stat Plan Inference 103:65–85CrossRefGoogle Scholar
  28. Lloyd CD (2010) Nonstationary models for exploring and mapping monthly precipitation in the United Kingdom. Int J Climatol 30:390–405Google Scholar
  29. Lloyd CD, Atkinson PM (2002) Nonstationary approaches for mapping terrain and assessing prediction uncertainty. Trans GIS 6:17–30CrossRefGoogle Scholar
  30. Matheron G (1976) A simple substitute for conditional expectation: the disjunctive kriging. In: Guarascio M, David M, Huijbrechts C (eds) Advanced geostatistics for the mining industry. Reidel, Dordrecht, pp 221–236Google Scholar
  31. Müller WG (1999) Least-squares fitting from the variogram cloud. Stat Probab Lett 43:93–98CrossRefGoogle Scholar
  32. Omre H (1984) The variogram and its estimation. In Verly G, David M, Journel AG, Marachal A (eds) Geostatistics for natural resources characterization. ASI. Reidel, Hingham, pp 107–125Google Scholar
  33. Paciorek CJ, Schervish MJ (2006) Spatial modelling using a new class of nonstationary covariance functions. Environmetrics 17:483–506CrossRefGoogle Scholar
  34. Pardo-Igúzquiza E, Dowd P, Grimes D (2005) An automatic moving window approach for mapping meteorological data. Int J Climatol 26:665–678CrossRefGoogle Scholar
  35. Parker HM (1991) Statistical treatment of outlier data in epithermal gold deposit reserve estimation. Math Geol 23:175–199CrossRefGoogle Scholar
  36. Pebesma EJ (2004) Multivariate geostatistics in S: the gstat package. Comput Geosci 30:683–691CrossRefGoogle Scholar
  37. Ploner A, Dutter R (2000) New directions in geostatistics. J Stat Plan Inference 91:499–509CrossRefGoogle Scholar
  38. Ribeiro PJ, Diggle PJ (2001) geoR: a package for geostatistical analysis. R News 1:15–18Google Scholar
  39. Richmond A (2002) Two-point declustering for weighting data pairs in experimental variogram calculations. Comput Geosci 28:231–241CrossRefGoogle Scholar
  40. Rivoirard J (2002) Weighted variograms. In Kleingold WJ, Krige DG (eds) Geostatistics 2000 Cape Town. Geostatistical Association of Southern Africa, South AfricaGoogle Scholar
  41. Sampson PD, Damian D, Guttorp P (2001) Advances in modeling and inference for environmental processes with nonstationary spatial covariance. NRCSE-TRS No 61, National Research Centre for Statistics and the Environment Technical Report Series, 2001Google Scholar
  42. Stein A, Hoogerwerf M, Bouma J (1988) Use of soil map delineations to improve (co)kriging of point data on moisture deficits. Geoderma 43:163–177CrossRefGoogle Scholar
  43. Van Tooren CF, Haas TC (1993) A site investigation strategy using moving window kriging and automated semivariogram modelling. In: Contaminated soil ‘93. Kluwer Academic Press, Dordrecht, pp 609–622Google Scholar
  44. Walter C, McBratney AB, Douaoui A, Minasny B (2001) Spatial prediction of topsoil salinity in the Chelif Valley, Algeria, using local ordinary kriging with local variograms versus whole-area variogram. Aust J Soil Res 39:259–272CrossRefGoogle Scholar
  45. Yamamoto JK (2000) An alternative measure of the reliability of ordinary kriging estimates. Math Geol 32:489–509CrossRefGoogle Scholar
  46. Zhang X, Eijkeren JC, Heemink AW (1995) On the weighted least-squares method for fitting a semivariogram model. Comput Geosci 21:605–608CrossRefGoogle Scholar

Copyright information

© Springer-Verlag 2010

Authors and Affiliations

  • Paul Harris
    • 1
  • Martin Charlton
    • 1
  • A. Stewart Fotheringham
    • 1
  1. 1.National Centre for GeocomputationNational University of Ireland MaynoothMaynoothIreland, UK

Personalised recommendations