Estimation of Population Density of Census Sectors Using Remote Sensing Data and Spatial Regression

  • Tessio Novack
  • Hermann Kux
  • Corina Freitas
Part of the Studies in Computational Intelligence book series (SCI, volume 348)


Assuming that urban planning aims the optimization of urban functioning and the well-being of citizens, questions like “how many people are living in the city?” and “where do they live?” become key issues. In this work we utilized landscape metrics generated by the FragStats software for the estimation of population density out of census sectors in the mega city of São Paulo, Brazil. The metrics were calculated over an image from the QuickBird II sensor classified by the Maximum Likelihood algorithm. The accuracy of the classified image was analyzed qualitatively. Ordinary linear regression models were generated and formal statistical tests applied. The residuals from each model had its spatial dependency analyzed by visualizing its LISA Maps and by the Global Moran index. Afterwards, spatial regression models were tried and a significant improvement was obtained in terms of spatial dependency reduction and increase of the prediction power of the models. For the sake of comparison, the use of dummy variables was also tried and it became a suitable option for eliminating spatial dependency of the residuals as well. The results proved that some landscape metrics obtained over high resolution images, classified by simple supervised methods, can predict well the population density at the area under study when using it as independent variable in spatial regression models.


Population density Spatial regression High resolution remote sensing 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Anselin, L.: The Moran scatterplot as an ESDA tool to assess local instability in spatial association. In: Fischer, M., Scholten, H., Unwin, D. (eds.) Spatial analytical perspectives on GIS in environmental and socio-economic sciences. Taylor and Francis, London (1996)Google Scholar
  2. Anselin, L.: GeoDa 0.95i Release Notes. Spatial Analysis Laboratory (SAL). Department of Agricultural and Consumer Economics, University of Illinois, Urbana-Champaign (2004)Google Scholar
  3. Anselin, L., Bera, A.: Spatial dependence in linear regression models with an introduction to spatial econometrics. In: Ullah, A., Giles, D.E. (eds.) Handbook of applied economic statistics. Marcel Dekker, New York (1998)Google Scholar
  4. Anselin, L., Florax, R.J.: Small sample properties of tests for spatial dependence in regression models: some further results. In: Anselin, L., Florax, R.J. (eds.) New directions in spatial econometrics. Springer, Berlin (1995)Google Scholar
  5. Bailey, T.C., Gatrell, A.C.: Interactive Spatial Data Analysis. John Wiley and Sons, New York (1995)Google Scholar
  6. Balk, D., Pozzi, F., et al.: The distribution of people and the dimension of place: methodologies to improve the global estimation of urban extent. In: Proceedings of the Urban Remote Sensing Conference, Tempe, AZ (2005)Google Scholar
  7. Harvey, J.T.: Estimating census district populations from satellite imagery: some approaches and limitations. Int. J. Remote Sens. 23(10), 2071–2095 (2002)CrossRefGoogle Scholar
  8. IBGE – Fundação Instituto Brasileiro de Geografia e Estatística. In: Censo demográfico de 2000 (2002), (access June 23, 2008)
  9. Jannuzzi, P. M.: Projeções populacionais para pequenas áreas: métodos e aplicações (2004), (access August 18, 2008)
  10. Liu, X.H., Clarke, K.: Estimation of residential population using high resolution satellite imagery. In: Proceedings of International Symposium on Remote Sensing of Urban Areas, Istanbul, Turkey (2002)Google Scholar
  11. Li, G., Weng, Q.: Integration of remote sensing and census data for assessing urban quality of life: model development and validation. In: Weng, Q., Quattrochi, D. (eds.) Urban remote sensing. Taylor and Francis, Boca Raton (2007)Google Scholar
  12. Liu, X., Herold, M.: Population estimation and interpolation using remote sensing. In: Weng, Q., Quattrochi, D. (eds.) Urban remote sensing, Taylor and Francis, Boca Raton (2007)Google Scholar
  13. Lo, D., Weng, Q., et al.: Residential population estimation using a remote sensing derived impervious surface approach. Int. J. Remote Sens. 27(16), 3553–3570 (2006)CrossRefGoogle Scholar
  14. Mather, P.M.: Computer processing of remotely-sensed images: an introduction, 3rd edn. John Wiley & Sons, Chichester (2004)Google Scholar
  15. Netter, J., Wasserman, W.: Applied linear statistical models. Irwin, Homewood (1974)Google Scholar
  16. Reis, I. A.: Estimação da população dos setores censitários de Belo Horizonte usando imagens de satélite (2005), (access December 18, 2007)
  17. Ribeiro, S. R. A,. Centeno, J .S.: Classificação do uso do solo utilizando redes neurais e o algoritmo MAXVER (2001), (access December 18, 2007)
  18. Sutton, P.C., Elvidge, C.D., et al.: Building and evaluating models to estimate ambient population density. Photogramm Eng. Remote Sens. 69(5), 545–553 (2003)Google Scholar
  19. UN-HABITAT (2006), (access February 28, 2008)

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Tessio Novack
    • 1
  • Hermann Kux
    • 1
  • Corina Freitas
    • 1
  1. 1.Department of Remote SensingNational Institute for Space Research (INPE)Brazil

Personalised recommendations