Skip to main content

A Methodology for Neural Spatial Interaction Modelling

  • Chapter
Spatial Analysis and GeoComputation
  • 1632 Accesses

Abstract

This paper attempts to develop a mathematically rigid and unified framework for neural spatial interaction modelling. Families of classical neural network models, but also less classical ones such as product unit neural network ones are considered for the cases of unconstrained and singly constrained spatial interaction flows. Current practice appears to suffer from least squares and normality assumptions that ignore the true integer nature of the flows and approximate a discrete-valued process by an almost certainly misrepresentative continuous distribution. To overcome this deficiency we suggest a more suitable estimation approach, maximum likelihood estimation under more realistic distributional assumptions of Poisson processes, and utilise a global search procedure, called Alopex, to solve the maximum likelihood estimation problem. To identify the transition from underfitting to overfitting we split the data into training, internal validation and test sets. The bootstrapping pairs approach with replacement is adopted to combine the purity of data splitting with the power of a resampling procedure to overcome the generally neglected issue of fixed data splitting and the problem of scarce data. In addition, the approach has power to provide a better statistical picture of the prediction variability. Finally, a benchmark comparison against the classical gravity models illustrates the superiority of both, the unconstrained and the origin-constrained neural network model versions in terms of generalisation performance measured by Kullback and Leibler’s information criterion.

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

Access this chapter

eBook
USD 16.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 109.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  • Bergkvist E. (2000): Forecasting interregional freight flows by gravity models, Jahrbuch für Regionalwissenschaft 20, 133–148

    Google Scholar 

  • Bergkvist E. and Westin L. (1997): Estimation of gravity models by OLS estimation, NLS estimation, Poisson and neural network specifications, CERUM Regional Dimensions, Working Paper 6

    Google Scholar 

  • Bia A. (2000): A study of possible improvements to the Alopex training algorithm. In: Proceedings of the VIth Brazilian Symposium on Neural Networks, IEEE Computer Society Press, pp. 125–130

    Google Scholar 

  • Black W.R. (1995): Spatial interaction modelling using artificial neural networks, Journal of Transport Geography 3(3), 159–166

    Article  Google Scholar 

  • Cover T.M. (1965): Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition, IEEE Transactions on Electronic Computers 14(3), 326–334

    Article  MATH  Google Scholar 

  • Efron B. (1982): The Jackknife, the Bootstrap and Other Resampling Plans. Philadelphia: Society for Industrial and Applied Mathematics SIAM, Philadelphia

    Google Scholar 

  • Fischer M.M. and Gopal S. (1994): Artifical neural networks: A new approach to modelling interregional telecommunication flows, Journal of Regional Science 34(4), 503–527

    Article  Google Scholar 

  • Fischer M.M. and Leung Y. (eds.) (2001): GeoComputional Modelling: Techniques and Applications, Springer, Berlin, Heidelberg, New York

    Google Scholar 

  • Fischer M.M. and Leung Y. (1998): A genetic-algorithms based evolutionary computational neural network for modelling spatial interaction data, The Annals of Regional Science 32(3), 437–458

    Article  Google Scholar 

  • Fischer M.M. and Reismann M. (2002): Evaluating neural spatial interaction modelling by bootstrapping, Networks and Spatial Economics 2(3), 255–268

    Google Scholar 

  • Fischer M.M., Reismann M. and Hlavácková-Schindler K. (2001): Neural network modelling of constrained spatial interaction flows, Paper presented at the 41rst Congress of the European Regional Science Association, Zagreb, Croatia [accepted for puplication in the Journal of Regional Science]

    Google Scholar 

  • Fischer M.M., Reismann M. and Hlavácková-Schindler K. (1999): A global search procedure for parameter estimation in neural spatial interacting modelling, Papers in Regional Science 78, 119–134

    Article  Google Scholar 

  • Fotheringham A.S. and O’Kelly M.E. (1989): Spatial Interaction Models: Formulations and Applications, Kluwer Academic Publishers, Dordrecht, Boston, London

    Google Scholar 

  • Giles C. and Maxwell T. (1987): Learning, invariance and generalization in high-order neural networks, Applied Optics 26(23), 4972–4978

    Article  ADS  Google Scholar 

  • Gopal S. and Fischer M.M. (1996): Learning in single hidden layer feedforward network models: Backpropagation in a spatial interaction context, Geographical Analysis 28(1), 38–55

    Article  Google Scholar 

  • Gopal S. and Fischer M.M.(1993): Neural net based interregional telephone traffic models. In: Proceedings of the International Joint Conference on Neural Networks IJCNN 93 Nagoya, Japan, October 25–29, pp. 2041–2044

    Google Scholar 

  • Kullback S. and Leibler R.A. (1951): On information and sufficiency, Annals of Mathematical Statistics 22(1), 78–86

    Article  MathSciNet  Google Scholar 

  • Longley P.A., Brocks S.M., McDonnel R. and Macmillan B. (eds.) (1998): Geocomputation: A Primer, John Wiley, Chichester [UK], New York

    Google Scholar 

  • Mozolin M., Thill J.-C. and Usery E.L. (2000): Trip distribution forecasting with multiplayer perceptron neural networks: A critical evaluation, Transportation Research B 34, 53–73

    Article  Google Scholar 

  • Nijkamp P., Reggiani A. and Tritapepe T. (1996): Modelling intra-urban transport flows in Italy, TRACE Discussion Papers TI 96-60/5, Tinbergen Institute, The Netherlands

    Google Scholar 

  • Openshaw S. (1993): Modelling spatial interaction using a neural net. In: Fischer M.M. and Nijkamp P. (eds.) Geographic Information Systems, Spatial Modeling, and Policy Evaluation, Springer, Berlin, Heidelberg, New York, pp. 147–164

    Google Scholar 

  • Press W.H., Teukolsky S.A., Vetterling W.T. and Flannery B.P. (1992): Numerical Recipes in C: The Art of Scientific Computing, Cambridge University Press, Cambridge [MA]

    Google Scholar 

  • Reggiani A. and Tritapepe T. (2000): Neural networks and logit models applied to commuters mobility in the metropolitan area of Milan. In: Hilmanen V., Nijkamp P. and Reggiani A. (eds.) Neural Networks in Transport Applications, Ashgate, Aldershot, pp. 111–129

    Google Scholar 

  • Rumelhart D.E., Durbin R., Golden R. and Chauvin Y. (1995): Backpropagation: The basic theory. In: Chauvin Y. and Rumelhart D.E. (eds.) Backpropagation: Theory, Architectures and Applications, Lawrence Erlbaum Associates, Hillsdale [NJ], pp. 1–34

    Google Scholar 

  • Thill J.-C. and Mozoli M. (2000): Feedforward neural networks for spatial interaction: Are they trustworthy forecasting tools?” In: Reggiani A. (ed.) Spatial Economic Science: New Frontiers in Theory and Methodology, Springer, Berlin, Heidelberg, New York, pp. 355–381

    Google Scholar 

  • Young T.Y. and Calver T.W. (1974): Classification, Estimation and Pattern Recognition, Elsevier, Amsterdam

    MATH  Google Scholar 

Download references

Authors

Rights and permissions

Reprints and permissions

Copyright information

© 2006 Springer Berlin · Heidelberg

About this chapter

Cite this chapter

Reismann, M. (2006). A Methodology for Neural Spatial Interaction Modelling. In: Spatial Analysis and GeoComputation. Springer, Berlin, Heidelberg . https://doi.org/10.1007/3-540-35730-0_14

Download citation

Publish with us

Policies and ethics