The Support Vector Machine for Nonlinear Spatio-Temporal Regression

Due to the increasingly demand for spatio-temporal analysis, time series and spatial statistics are extended to the spatial dimension and the temporal dimension respectively or they are combined via linear regression. However, such linear regression is just a simplification of complicated spatio-temporal associations existing in complex geographical phenomena. In this study, the Support Vector Machine is introduced to combine spatial and temporal dimensions nonlinearly. Experiment results show that nonlinearly regression via the Support Vector Machine obtained better forecasting accuracy than that using the linear regression and other conventional methods.

[1]  P. Pfeifer,et al.  A STARIMA Model-Building Procedure with Application to Description and Regional Forecasting , 1980 .

[2]  J. Ramos,et al.  Space-Time Modeling of Vector Hydrologic Sequences , 1986 .

[3]  Alexander J. Smola,et al.  Regression estimation with support vector learning machines , 1996 .

[4]  Noel A Cressie,et al.  Spatio-Temporal Statistical Modeling of Livestock Waste in Streams , 1996 .

[5]  Jiang Lin.  A New Nonlinear Compound Forecasting Method Based on ANN , 2000 .

[6]  Dong-sheng Jing,et al.  Research on nonlinear combination forecasting method based on wavelet network , 2000 .

[7]  Dong Jing-rong.  A New Nonlinear Combination Forecasting Method Based on Fuzzy Model and Its Application , 2000 .

[8]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[9]  Stéphane Canu,et al.  SPATIAL DATA MAPPING WITH SUPPORT VECTOR REGRESSION , 2000 .

[10]  Zoran Obradovic,et al.  Improved Spatial-Temporal Forecasting through Modelling of Spatial Residuals in Recent History , 2001, SDM.

[11]  Stéphane Canu,et al.  Environmental data mining and modeling based on machine learning algorithms and geostatistics , 2004, Environ. Model. Softw..

[12]  Lipo Wang,et al.  Data Mining With Computational Intelligence , 2006, IEEE Transactions on Neural Networks.

[13]  Jiaqiu Wang,et al.  Applications of spatio-temporal data mining and knowledge for forest fire , 2006 .

[14]  Jiaqiu Wang,et al.  Application of a Dynamic Recurrent Neural Network in Spatio-Temporal Forecasting , 2007, IF&GIS.