Feedforward Neural Networks for Spatial Interaction: Are They Trustworthy Forecasting Tools?

  • Jean-Claude Thill
  • Mikhail Mozolin
Part of the Advances in Spatial Science book series (ADVSPATIAL)


Though it has often been criticized for providing too crude a rendition of processes underpinning revealed patterns of interaction between geo-referenced entities, spatial interaction modelling has persisted as one of the methodological pillars of several spatial sciences, including regional science, geography and transportation (Fotheringham and O’Kelly 1989; Ortuzar and Willumsen 1994; Sen and Smith 1995; Isard et al. 1998). Traditionally, the spatial interaction model is calibrated by one of several well known fitting and optimization techniques, including leastsquares regression, maximum likelihood, or by numerical heuristics.


Neural Network Neural Network Model Hide Node Feedforward Neural Network Spatial Interaction 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Ayeni B. 1982. The testing of hypothesis on interaction data matrices, Geographical Analysis, 14: 79–84.CrossRefGoogle Scholar
  2. BacharachM. 1970. Biproportional Matrices and Input-Output Change, Cambridge University Press,Cambridge, UK.Google Scholar
  3. Batty M. 1976. Urban Modeling: Algorithms, Calibrations, Predictions, Cambridge University Press, Cambridge, UK.Google Scholar
  4. Batty M. and Mackie S. 1972. The calibration of gravity, entropy, and related models of spatial interaction, Environment and Planning A, 4: 205–33.CrossRefGoogle Scholar
  5. Beale R. and Jackson T. 1990. Neural Computing. An Introduction, Adam Hilger, Bristol, UK.CrossRefGoogle Scholar
  6. Bishop C.M. 1995. Neural Networks for Pattern Recognition, Oxford University Press, Oxford, UK.Google Scholar
  7. Black W.R. 1995. Spatial interaction modeling using artificial neural networks, Journal of Transport Geography 3, 3:159–66.CrossRefGoogle Scholar
  8. Boots B.N. and Kanaroglou P.S. 1988. Incorporating the effects of spatial structure in discrete choice models of migration, Journal of Regional Science, 28, 4: 495–507.CrossRefGoogle Scholar
  9. Broomhead D.S. and Lowe D. 1988. Multi-Variable Functional Interpolation and Adaptive Networks, Complex Systems, 2: 749–61.Google Scholar
  10. Bryson A.E. and Ho Y.-C. 1969. Applied Optimal Control, Blaisdell, New York.Google Scholar
  11. Carpenter G.A. and Grossberg S. 1987a. Invariant pattern recognition and recall by an attentive self-organizing ART architecture in a non-stationary world, Proceedings of IEEE First Int. Conference on Neural Networks, Vol. II, IEEE, San Diego, 737-6.Google Scholar
  12. Carpenter G.A. and Grossberg S. 1987b. ART2: Self-organization of stable category recognition codes for analog input patterns, Applied Optics, 26: 4919–30.CrossRefGoogle Scholar
  13. Carpenter G.A., Grossberg S. and Reynolds J.H. 1991. A self-organizing ARTMAP neural architecture of supervised learning and pattern recognition, In R.J. Mammone, and Zevi Y. (eds.) Neural Networks, Theory and Applications, Academic Press, Boston, 43–80.Google Scholar
  14. Cichocki A. and Unbehauen R. 1993. Neural Networks for Optimization and Signal Processing, John Wiley and Sons, Chichester.Google Scholar
  15. Dougherty, M. 1995. A review of neural networks applied to transport, Transportation Research C, 3, 4: 247–60.CrossRefGoogle Scholar
  16. Evans A.W. 1971. The calibration of trip distribution models with exponential or similar cost functions, Transportation Research, 5, 1: 15–38.CrossRefGoogle Scholar
  17. Fahlman S.E. 1989. Faster-learning variations on back-propagation: an empirical study, in Touretzky D., Hinton G. and Sejnowski T. (eds.) Proceedings of the 1988 Connectionist Models Summer School, Morgan Kaufmann Publishers, San Mateo, CA, 38–51.Google Scholar
  18. Fischer M.M. and Gopal S. 1994. Artificial neural networks: a new approach to modeling interregional telecommunication flows, Journal of Regional Science, 34, 4: 503–27.CrossRefGoogle Scholar
  19. Fotheringham A.S. 1981. Spatial structure and distance-decay parameters, Annals of the Association of American Geographers, 71, 3: 425–36.Google Scholar
  20. Fotheringham S. and Knudsen D.C. 1987. Goodness-of-fit statistics. CATMOG series, Geo Abstracts, Norwich, UK.Google Scholar
  21. Fotheringham A.S. and O’Kelly M.E. 1989. Spatial Interaction Models: Formulations and Applications, Kluwer Academic Publishers, London.Google Scholar
  22. Freeman T.A., and Skapura D.M. 1991. Neural Networks: Algorithms, Applications and Programming Techniques, Addison-Wesley, Reading.Google Scholar
  23. Ghosh A. 1984. Parameter nonstationarity in retail choice models, Journal of Business Research, 12: 425–36.CrossRefGoogle Scholar
  24. Goodman P.H. 1996. NevProp Software, Version 3, University of Nevada, Reno NV, URL: Scholar
  25. Gopal S. and Fischer M.M. 1996. Learning in single hidden-layer feedforward network: backpropagation in a spatial interaction modeling context, Geographical Analysis, 28, 1: 38–55.CrossRefGoogle Scholar
  26. Griffith D.A. and Jones K.G. 1980. Explorations into the relationship between spatial structure and spatial interaction, Environment and Planning A, 12: 187–202. ]CrossRefGoogle Scholar
  27. Haykin S.S. 1998. Neural Networks: A Comprehensive Foundation, Prentice Hall, Upper Saddle River, NJ.Google Scholar
  28. Hua J. and Faghri A. 1994. Applications of artificial neural networks to intelligent vehicle-highway systems, Transportation Research Record, 1453: 83–90.Google Scholar
  29. Isard W, Aziz I.J., Drennan M.P., Miler R.E., Saltzman S. and Throbercke E. 1998. Methods of Interregional and Regional Analysis, Ashgate, Aldershot.Google Scholar
  30. Kohonen T. 1997. Self-organizing Maps, Springer-Verlag, Berlin.Google Scholar
  31. Kreinovich V. and Sirisaengtaskin O. 1993. Universal approximators for functions and for control strategies, Neural, Parallel, and Scientific Computations, 1, 3: 325–46.Google Scholar
  32. Lee S. and Kil R.M. 1988. Multilayer feedforward potential function network, IEEE International Conference on Neural Networks, IEEE, Piscataway, NJ, 161–72.Google Scholar
  33. Masters T. 1995. Advanced Algorithms for Neural Networks :A C+ + Sourcebook, John Wiley and Sons, New York.Google Scholar
  34. Mozolin M.V. 1997. Spatial interaction modeling with an artificial neural network, Discussion Paper Series 97-1, Department of Geography, University of Georgia, Athens, GA.Google Scholar
  35. Openshaw S. 1993. Modeling spatial interaction using a neural net, in Fischer M.M. and Nijkamp P. (eds.) Geographic Information Systems, Spatial Modeling and Policy Evaluation, Springer-Verlag, Berlin, 147–64.Google Scholar
  36. Openshaw S. and Openshaw C. 1997. Artificial Intelligence in Geography, John Wiley and Sons, Chichester.Google Scholar
  37. Ortuzar J. deDios and Willumsen L.G. 1994. Modelling Transport, John Wiley, Chichester.Google Scholar
  38. Penfold R., Dufournaud C. and Thill J.-C. 2000. Spatial interaction modeling with Jaynes’ quadratic criterion: II. Spatial structure, Working paper, Department of Geography, University at Buffalo, Buffalo, NY.Google Scholar
  39. Ripley B.D. 1996. Pattern Recognition and Neural Networks, Cambridge University Press, Cambridge, UK.Google Scholar
  40. Rojas P. 1996. Neural Networks: A Systematic Introduction, Springer-Verlag, New York.Google Scholar
  41. Rumelhart D.E., Hinton G.E., and Williams R.J. 1986. Learning representations by back-propagating errors, Nature, 323 (9 October): 533–36.CrossRefGoogle Scholar
  42. Sarle W.S. (ed.) 1997. Neural Network FAQ, part 1 of 7: Introduction, periodic posting to the Usenet newsgroup URL: Scholar
  43. Sen A.K. and Smith T.E. 1995. Gravity Models of Spatial Interaction Behavior, Springer-Verlag, Berlin.Google Scholar
  44. Sheppard E.S. 1976. Entropy, theory construction and spatial analysis, Environment and Planning A, 8: 741–52.CrossRefGoogle Scholar
  45. Slater P.B. 1976. Hierarchical internal migration regions of France, IEEE Transactions on Systems, Man, and Cybernetics, 6,4: 321–24.Google Scholar
  46. Smetanin Y.G. 1995. Neural networks as systems for pattern recognition: a review, Pattern Recognition and Image Analysis 5,2: 254–93.Google Scholar
  47. Smith M. 1993. Neural Networks for Statistical Modeling, Van Nostrand Reinhold, New York.Google Scholar
  48. Snickars F. and Weibull J.W. 1977. A minimum information principle: theory and practice, Regional Science and Urban Economics 7: 137–68.CrossRefGoogle Scholar
  49. Thomas R.W. and Hugget R.J. 1980. Modeling in Geography: A Mathematical Approach, Barnes and Noble, Totowa, NJ.Google Scholar
  50. U.S. Department of Commerce. 1983. 1980 Census of Population and Housing, Census Tracts, Atlanta, GA. PHC80-2-77, Washington, DC,Google Scholar
  51. U.S. Department of Commerce, Bureau of the Census. U.S. Department of Transportation. Bureau of Transportation Statistics. 1993. 1990 Census Transportation Planning Package, Washington, DC, U.S. Department of Transportation, Bureau of Transportation Statistics, CD.Google Scholar
  52. Williams P.A. and Fotheringham A.S. 1984. The Calibration of Spatial Interaction Models by Maximum Likelihood Estimation with Program SIMODEL, Geographic Monograph Series, Volume 7, Department of Geography, Indiana University, Bloomington, IN.Google Scholar
  53. Wilson A.G. 1970. Entropy in Urban and Regional Modeling, Pion, London.Google Scholar
  54. Yun S.-Y., Namkoong S., Rho J.-H., Shin S.-W. and Choi J.-U. 1998. A performance evaluation of neural network models in traffic volume forecasting, Mathematical Computing and Modelling, 27, 9-11: 293–310.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Jean-Claude Thill
    • 1
  • Mikhail Mozolin
    • 2
  1. 1.Department of Geography and National Center for Geographic Information AnalysisState University of New York at BuffaloAmherstUSA
  2. 2.ESRI, Inc.RedlandsUSA

Personalised recommendations