Soil Water Content Forecasting by Support Vector Machine in Purple Hilly Region

  • Wei Wu
  • Xuan Wang
  • Deti Xie
  • Hongbin Liu
Part of the The International Federation for Information Processing book series (IFIPAICT, volume 258)

Soil water distribution and variation are helpful in predicting and understanding various hydrologic processes, including weather changes, rainfall/runoff generation and irrigation scheduling. Soil water content prediction is essential to the development of advanced agriculture information systems. In this paper, we apply support vector machines to soil water content predictions and compare the results to other time series prediction methods in purple hilly area. Since support vector machines have greater generalization ability and guarantee global minima for given training data, it is believed that support vector machine will perform well for time series analysis. Predictions exhibit good agreement with actual soil water content measurements. Compared with other predictors, our results show that the SVMs predictors perform better for soil water forecasting than ANN models. We demonstrate the feasibility of applying SVMs to soil water content forecasting and prove that SVMs are applicable and perform well for soil water content data analysis.

Keywords

support vector machines soil water content statistical learning prediction forecasting time series 

References

  1. Baghdadi N, Gaultier S, King C. Retrieving Surface Roughness and Soil Moisture From Synthetic Aperture Radar (SAR) Data Using Neural Networks. Canadian Journal of Remote Sensing, 2002, 5: 701-711CrossRefGoogle Scholar
  2. Cao L J, Tay F E H. Financial forecasting using support vector machines. Neural Comput. 2001, Appl(10): 184-182Google Scholar
  3. Flake G, Lawrence S. Efficient SVM regression training with SMO. Machine Learning. 2002, 1/3: 271-290CrossRefGoogle Scholar
  4. Liou Y A, Liu S F, Wang W J. Retrieving Soil Moisture From Simulated Brightness Temperature by a Neural Network, IEEE Transactions on Geoscience Remote Sensing, 2001, 8: 1662-1672Google Scholar
  5. Liu H B, Wu W, Wei C F, Xie D T. Comparison of autoregression and neural network models for soil water content forecasting, Transactions of the CSAE, Vol. 19, No. 4, 2003, pp. 33-36 (in Chinese)Google Scholar
  6. Liu H B, Wu W, Wei C F, Xie D T. Soil water dynamics simulation by autoregression models, Journal of Mountain Science, 2004, 1: 121-125 (in Chinese)CrossRefGoogle Scholar
  7. Liu H B, Wu W, Wei C F. Study of soil water forecast with neural network, Journal of Soil and Water Conservation, 2003, 5: 59-62 (in Chinese)Google Scholar
  8. Mukherjee S, Osuna E, Girosi F. Nonlinear prediction of chaotic time series using support vector machine. In: NNSP’97: Neural Networks for Signal Processing VII: Proceedings of the IEEE Signal Processing Society Workshop, Amelia Island, FL, USA. 1997, 243-254Google Scholar
  9. Thissen U, van Brackel R. de Weijer A P, Melssen W J, Buydens L M C. Using support vector machines for time series prediction. Chemometrics and Intelligent Laboratory Systems. 2003, 69: 35-49CrossRefGoogle Scholar
  10. Vapnik V B, Golowich S E, Smola A J. Support vector method for function approximation, regression estimation, and signal processing. Advances in Neural Information Processing Systems. 1996, 9: 281-287Google Scholar
  11. Vapnik V N. The nature of statistical learning theory. New York: Springer, 1995CrossRefGoogle Scholar
  12. Xian G L, Luo X C, Xiao Y F. Statistics learning theory and support vector machine. China science and technology information. 2005, 12: 178-181 (in Chinese)Google Scholar
  13. Yan H, Zhang X G, Li Y D. Support vector machine methods in pattern recognition of sedimentary facies. Computing techniques for geophysical and geochemical exploration. 2000, 2: 158-164Google Scholar
  14. Zhang G P. Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing. 2003, 50: 159-175CrossRefGoogle Scholar

Copyright information

© IFIP International Federation for Information Processing 2008

Authors and Affiliations

  • Wei Wu
    • 1
  • Xuan Wang
    • 1
  • Deti Xie
    • 1
  • Hongbin Liu
    • 1
  1. 1.Chongqing Key Lab of Digital AgricultureSouthwest UniversityChina

Personalised recommendations