Abstract
The importance of forecasting cannot be overemphasized in modern environment surveillance applications, including flood control, rainfall analysis, pollution study, nuclear leakage prevention and so on. That is why we proposed STIFF (SpatioTemporal Integrated Forecasting Framework) in previous work [11], trying to answer such a challenging problem of doing forecasting in natural environment with both spatial and temporal characteristics involved. However, despite its promising performance on univariate-based data, STIFF is not sophisticated enough for more complicated environmental data derived from multiple correlated variables. Therefore in this paper we add multivariate analysis to the solution, take the correlation between different variables into account and further extend STIFF to address spatiotemporal forecasting involving multiple variables. Our experiments show that this introduction and integration of multivariate correlation not only has a more reasonable and rational interpretation of the data itself, but also produces a higher accuracy and slightly more balanced behavior.
Supported by the National Science Foundation under Grant No. IIS-9820841.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
George E. P. Box, Gwilym M. Jenkins, and Gregory C. Reinsel. Time Series Analysis: Forecasting and Control. Prentice-Hall, 1994.
Sung-Bae Cho. Neural-network classifiers for recognizing totally unconstrained handwritten numerals. IEEE Transactions on Neural Networks, 8(1):43–53, 1997.
N. Cressie and J. J. Majure. Spatio-temporal statistical modeling of livestock waste in streams. Journal of Agricultural, Biological and Environmental Statistics, 1997.
S. J. Deutsch and J. A. Ramos. Space-time modeling of vector hydrologic sequences. Water Resource Bulletin, 22:967–980, 1986.
M. Dougherty, Linda See, S. Corne, and S. Openshaw. Some initial experiments with neural network models of flood forecasting on the river ouse. In Proceedings of the 2nd Annual Conference of GeoComputation, 1997.
Margaret H. Dunham. Data Mining: Introductory and Advanced Topics. Prentice Hall, 2003.
Henry L. Gray. Theory and Applications of ARMA Models. Springer-Verlag, 2002.
R. A. Johnson and D. W. Wichern. Applied Multivariate Statistical Analysis. Prentice Hall, 2002.
C. Jothityangkoon, M. Sivapalan, and N. R. Viney. Tests of a space-time model of daily rainfall in southwestern australia based on nonhomogeneous random cascades. Water Resource Research, 2000.
Pacific Marine Environmental Laboratory. Tropic atmosphere ocean project. http://www.pmel.noaa.gov/tao/.
Zhigang Li and Margaret H. Dunham. Stiff: A forecasting framework for spatiotemporal data. In Workshop on Knowledge Discovery in Multimedia and Complex Data, PAKDD 02, 2002.
Phillip E. Pfeifer and Stuart J. Deutsch. A test of space-time arma modelling and forecasting of hotel data. Journal of Forecasting, 9:225–272, 1990.
D. Pokrajac and Z. Obradovic. Improved spatial-temporal forecasting through modeling of spatial residuals in recent history. In First SIAM International Conference on Data Mining (SDM’2001), 2001.
A. C. Rencher. Methods of Multivariate Analysis. John Wiley & Sons, 2002.
S. I. Shaheen, A. F. Atiya, S. M. El Shoura, and M. S. El Sherif. A comparison between neural network forecasting techniques. IEEE Transactions on Neural Networks, 10(2):402–409, 1999.
D. S. Stofer. Estimation and identification of space-time armax models in the presence of missing data. Journal of American Statistical Association, 81:762–772, 1986.
William W. S. Wei. Time Series Analysis: Univariate and Multivariant Methods. Addison Wesley, 1990.
Michael Q. Zhang. Discriminant analysis and its application in dna sequence motif recognition. Briefings in Bioinformatics, 1(4):1–12, 2000.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Li, Z., Liu, L., Dunham, M.H. (2003). Considering Correlation between Variables to Improve Spatiotemporal Forecasting. In: Whang, KY., Jeon, J., Shim, K., Srivastava, J. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2003. Lecture Notes in Computer Science(), vol 2637. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-36175-8_52
Download citation
DOI: https://doi.org/10.1007/3-540-36175-8_52
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-04760-5
Online ISBN: 978-3-540-36175-6
eBook Packages: Springer Book Archive