Advertisement

STIFF: A Forecasting Framework for SpatioTemporal Data

  • Zhigang Li
  • Margaret H. Dunham
  • Yongqiao Xiao
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2797)

Abstract

Nowadays spatiotemporal forecasting has been drawing more and more attention from academic researchers and industrial practitioners for its promising applicability to complex data containing both spatial and temporal characteristics. To meet this increasing demand we propose STIFF (SpatioTemporal Integrated Forecasting Framework) in this paper. Following a divide-and-conquer methodology, it 1) first constructs a stochastic time series model to capture the temporal characteristic of each spatially separated location, 2) then builds an artificial neural network to discover the hidden spatial correlation among all locations, 3) finally combines the previous individual temporal and spatial predictions based upon statistical regression to obtain the overall integrated forecasting. After the framework description a real-world case study in a river catchment, which bears abrupt water flow rate fluctuation, obtained from a British catchment with complicated hydrological situations, is presented for illustration purpose. The effectiveness of the framework is shown by an enhanced forecasting accuracy and more balanced behaviors.

Keywords

Hide Layer Target Location Time Series Data Time Series Model Dynamic Selection 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    British National River Flow Archive, http://www.nerc-wallingford.ac.uk/ih/nrfa/index.htm
  2. 2.
    Box, G.E.P., Cox, D.R.: An analysis of transformation. Journal of Royal Statistical Society (1964)Google Scholar
  3. 3.
    Box, G.E.P., Jenkins, G.M., Reinsel, G.C.: Time Series Analysis: Forecasting and Control. Prentice-Hall, Englewood Cliffs (1994)MATHGoogle Scholar
  4. 4.
    Cho, S.-B.: Neural-network classifiers for recognizing totally unconstrained handwritten numerals. IEEE Transactions on Neural Networks (1997)Google Scholar
  5. 5.
    Cressie, N., Majure, J.J.: Spatio-temporal statistical modeling of livestock waste in streams. Journal of Agricultural, Biological and Environmental Statistics (1997)Google Scholar
  6. 6.
    Deutsch, S.J., Ramos, J.A.: Space-time modeling of vector hydrologic sequences. Water Resource Bulletin (1986)Google Scholar
  7. 7.
    Dougherty, M., See, L., Corne, S., Openshaw, S.: Some initial experiments with neural network models of flood forecasting on the river ouse. In: Proceedings of the 2nd Annual Conference of GeoComputation (1997)Google Scholar
  8. 8.
    Dunham, M.H.: Data Mining Introductory and Advanced Topics. Prentice-Hall, Englewood Cliffs (2002)Google Scholar
  9. 9.
    Jothityangkoon, C., Sivapalan, M., Viney, N.R.: Tests of a space-time model of daily rainfall in southwestern australia based on nonhomogeneous random cascades. Water Resource Research (2000)Google Scholar
  10. 10.
    Pace Kelly, R., Barry, R., Clapp, J., Rodriquez, M.: Spatiotemporal autoregressive models of neighborhood effects. Journal of Real Estate Economics (1998)Google Scholar
  11. 11.
    Pfeifer, P.E., Deutsch, S.J.: A three-stage iterative procedure for space-time modelling. TECHNOMETRICS (1980)Google Scholar
  12. 12.
    Pfeifer, P.E., Deutsch, S.J.: A statima model-building procedure with applicationto description and regional forecasting. Journal of Forecasting (1990)Google Scholar
  13. 13.
    Pokrajac, D., Obradovic, Z.: Improved spatial-temporal forecasting through modeling of spatial residuals in recent history. In: First SIAM International Conference on Data Mining, SDM 2001 (2001)Google Scholar
  14. 14.
    Roddick, J.F., Hornsby, K., Spiliopoulou, M.: Improved spatialtemporal forecasting through modeling of spatial residuals in recent history. In: Roddick, J., Hornsby, K.S. (eds.) TSDM 2000. LNCS (LNAI), vol. 2007, p. 147. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  15. 15.
    Shaheen, S.I., Atiya, A.F., El_Shoura, S.M., El_Sherif, M.S.: A comparison between neural network forecasting techniques. IEEE Transactions on Neural Networks (1999)Google Scholar
  16. 16.
    Singh, G.D., Chaplain, M.A.J., McLachlan, J.: On Growth and Form: Spatio-Temporal Pattern Formation in Biology. John Wiley & Sons, Chichester (1999)MATHGoogle Scholar
  17. 17.
    Srinivasa, N., Ahuja, N.: A topological and temporal correlator network for spatiotemporal pattern learning, recognition, and recall. IEEE Transactions on Neural Networks (1999)Google Scholar
  18. 18.
    Stofer, D.S.: Estimation and identification of space-time armax models in the presence of missing data. Journal of American Statistical Association (1986)Google Scholar
  19. 19.
    Wei, W.W.S.: Time Series Analysis: Univariate and Multivariant Methods. Addison-Wesley, Reading (1990)Google Scholar
  20. 20.
    Woods, K., Philip Kegelmeyer, W., Bowyer, K.: Combination of multiple classifiers using local accuracy estimates. IEEE Transaction on Pattern Analysis and Machine Intelligence (1997)Google Scholar
  21. 21.
    Woodward, W.A., Gray, H.L.: On the relationship between the s array and the box-jenkins method of arma model identification. Journal of American Statistical Association (1981)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Zhigang Li
    • 1
  • Margaret H. Dunham
    • 1
  • Yongqiao Xiao
    • 2
  1. 1.Dept. of Computer Science and EngineeringSouthern Methodist UniversityDallasUSA
  2. 2.Dept. of Math and Computer ScienceGeorgia College & State UniversityMilledgevilleUSA

Personalised recommendations