Volume 3 Issue 4
Dec.  2010
Turn off MathJax
Article Contents
Article Navigation >  Water Science and Engineering  > 2010  >  3(4): 361-377
Di Liu, Yu-zhongbo, Lv haishen. 2010: Data assimilation using support vector machines and ensemble kalman filter for multi-layer soil moisture prediction. Water Science and Engineering, 3(4): 361-377. doi: 10.3882/j.issn.1674-2370.2010.04.001
Citation: Di Liu, Yu-zhongbo, Lv haishen. 2010: Data assimilation using support vector machines and ensemble kalman filter for multi-layer soil moisture prediction. Water Science and Engineering, 3(4): 361-377. doi: 10.3882/j.issn.1674-2370.2010.04.001
shu

Data assimilation using support vector machines and ensemble kalman filter for multi-layer soil moisture prediction

doi: 10.3882/j.issn.1674-2370.2010.04.001

  • Hohai university

Funds:  Major Science and Technology Program for Water Pollution Control and Treatment in China;Major Science and Technology Program for Water Pollution Control and Treatment in China
More Information
  • Corresponding author: Di Liu
  • Received Date: 2010-09-20
  • Rev Recd Date: 2010-10-21
    Abstract
  • Hybrid data assimilation (DA) is a new method used in recent hydrology and water resources research. In this paper, a DA method coupled with the support vector machines (SVM) and the ensemble kalman filter (EnKF) technology is used for the prediction of soil moisture at different soil layers: 0 cm, 30 cm, 50 cm, 100 cm, 150 cm and 200 cm. SVM method is a statistically sound and robust approach for solving the inverse problem by building statistical models. So far, SVM has a great use in such problems to classify or predict data which often contain some useful information. The principle strength of this machine lies in the use of Structural Risk Minimization (SRM) rather than Empirical Risk Minimization (ERM). EnKF is an extension of the kalman filter, a well-known method for updating information. It is one of the mostly used sequential DA methods in recently land data assimilation research. Herein, the SVM methodology is firstly used to train the ground measurements of soil moisture and meteorological parameters from Meilin study area to construct the soil moisture statistical predictor models. Then the subsequent observations and their statistics were used for the future predictions by using two approaches: SVM predictor and SVM-EnKF model by coupling SVM model with EnKF technique using DA method. Validation results showed that the proposed SVM model coupled with EnKF technology can effectively improve the predictions of soil moisture in different layers, from surface to root zone.

     

    • FullText(HTML)
  • loading
    • References(48)
  • Ahmad, S., Kalra, A., and Stephen, H. 2010. Estimating soil moisture using remote sensing data: A machine learning approach. Advances in Water Resources, 33(1), 69-80. [ doi: 10.1016/j.advwatres.2009.10.008]
    Al-Hamdan, O. Z. and Cruise, J. F. 2010. Soil moisture profile development from surface observations by principle of maximum entropy. Journal of Hydrologic Engineering, 15(5), 327-337. [doi:10.1061/ (ASCE)HE.1943-5584.0000196]
    Asefa, T., and Kemblowski, M. W. 2002. Support vector machines approximation of flow and transport models in initial groundwater contamination network design. EOS Transaction American Geophysical Union, 83. Washington: American Geophysical Union.
    Asefa, T., Kemblowski, M. W., Urroz, G., McKee, M., and Khalil, A. 2004. Support vectors-based groundwater head observation networks design. Water Resources Research, 40, W11509. [doi:10.1029/ 2004WR003304]
    Asefa, T., Kemblowski, M., McKee, M., and Khalil, A. 2006. Multi-time scale stream flow predictions: The support vector machines approach. Journal of Hydrology, 318(1-4), 7-16. [doi:10.1016/j.jhydrol.2005. 06.001]
    Bertino, L., Evensen, G., and Wackernagel, H. 2002. Combining geostatistics and Kalman filtering for data assimilation in an estuarine system. Inverse Problems, 18(1), 1-23. [doi: 10.1088/0266-5611/18/1/301]
    Chen, S. T., Yu, P. S., and Tang, Y. H. 2010. Statistical downscaling of daily precipitation using support vector machines and multivariate analysis. Journal of Hydrology, 385(1-4), 13-22. [doi:10.1016/j.jhydrol. 2010.01.021]
    Cristianini, N., and Shaw-Taylor, J. 2000. An Introduction to Support Vector Machines and Other Kernel-based Learning Methods. New York: Cambridge University Press.
    Crow, W. T., and Wood, E. F. 2003. The assimilation of remotely sensed soil brightness temperature imagery into a land surface model using ensemble Kalman filtering: A case study based on ESTAR measurements during SGP97. Advances in Water Resources, 26(2), 137-149. [doi: 10.1.1.10.9364]
    Daly, E., and Porporato, A. 2005. A review of soil moisture dynamics: From rainfall infiltration to ecosystem response. Environmental Engineering Science, 22(1), 9-24. [doi: 10.1089/ees.2005.22.9]
    Dibike, B. Y., Velickov, S., Solomatine, D., and Abbott, B. M. 2001. Model induction with support vector machines: introduction and applications. Journal of Computing in Civil Engineering, 15(3), 208-216. [doi: 10.1061/(ASCE)0887-3801(2001)15:3(208)]
    Drecourt, J. P. 2003. Kalman filtering in hydrological modeling. DAIHM technical report. Denmark: DHI Water and Environment.
    El-Sebakhy, E. A. 2009. Forecasting PVT properties of crude oil systems based on support vector machines modeling scheme. Journal of Petroleum Science and Engineering, 64(1-4), 25-34. [doi:10.1016/j.petrol. 2008.12.006]
    Evensen, G. 1994. Sequential data assimilation with a nonlinear quasi-geostrophic model using monte-carlo methods to forecast error statistics. Journal of Geophysical Research, 99(C5), 10143-10162. [doi: 10.1029/94JC00572]
    Evensen, G. 2002. Sequential data assimilation for nonlinear dynamics: The ensemble Kalman filter. Ocean Forecasting: Conceptual Basis and Applications,101-120. Berlin: Springer-Verlag.
    Gill, M. K., Kaheil, Y. H., Khalil, A., McKee, M., and Bastidas, L. 2006a. Multi-objective particle swarm optimization for parameter estimation in hydrology. Water Resources Research, 42, W07417. [doi: 10.1029/2005WR004528]
    Gill, M. K., Asefa, T., Kemblowski, M. W., and McKee, M. 2006b. Soil moisture prediction using support vector machines. Journal of American Water Resources Association, 42(4), 1033-1046. [doi:10.1111/j. 1752-1688.2006.tb04512.x]
    Gill, M. K., and McKee, M. 2007. Soil moisture data assimilation using support vector machines and ensemble Kalman filter. Journal of American Water Resources Association, 43(4), 1004-1015. [doi: 10.1111/j.1752-1688.2007.00082.x]
    Islam, S. I., and Engman, E. T. 1996. Why bother for 0.0001% of earth’s water? Challenges for soil moisture research. EOS Transaction American Geophysical Union, 77(43), 420.
    Johns, C. J., and Mandel, J. 2008. A two-stage ensemble Kalman filter for smooth data assimilation. Environmental and Ecological Statistics, 15(1), 101-110. [doi: 10.1007/s10651-007-0033-0]
    Kaheil, Y. H., Gill, M. K., McKee, M., Bastidas, L. A., and Rosero, E. 2008. Downscaling and assimilation of surface soil moisture using ground truth measurements. IEEE Transactions on Geoscience and Remote Sensing, 46(5), 1375-1384. [doi: 10.1109/TGRS.2008.916086]
    Kalman, R. E. 1960. A new approach to linear filtering and prediction problem. Transactions of the AMSE-Journal of Basic Engineering, 82(D), 35-45.
    Kalra, A., and Ahmad, S. 2009. Using oceanic-atmospheric oscillations for long lead time stream?ow forecasting. Water Resources Research, 45, W03413. [doi: 10.1029/2008WR006855]
    Khalil, A., Gill, M. K., and McKee, M. 2005. New Applications for Information Fusion and soil moisture forecasting. 8th International Conference on Information Fusion, 1622-1628. [doi:10.1109/ICIF.2005. 1592050]
    Kumar, S. V., Reichle, R. H., Peters-Lidard, C. D., Koster, R. D., Zhan, X. W., Crow, W. T., Eylander, J. B., and Houser, P. R. 2008. A land surface data assimilation framework using the land information system: Description and applications. Advances in Water Resources, 31(11), 1419-1432. [doi:10.1016/j.advwatres. 2008.01.013]
    Li, F. Q., Crow, W. T., and Kustas, W. P. 2010. Towards the estimation root-zone soil moisture via the simultaneous assimilation of thermal and microwave soil moisture retrievals. Advances in Water Resources, 33(2), 201-214. [doi: 10.1016/j.advwatres.2009.11.007]
    Liang, S. and Qin, J. 2008. Data assimilation methods for land surface variable estimation. Advances in Land Remote Sensing, 313-339. Netherlands: Springer.
    Lin, G. F., Chen, G.. R., Wu, M. C., and Chou, Y. C. 2009. Effective forecasting of hourly typhoon rainfall using support vector machines. Water Resources Research, 45, W08440. [doi: 10.1029/2009WR007911]
    Liong, S. Y., and Sivapragasam, C. 2002. Flood stage forecasting with support vector machines. Journal of the American Water Resources Association, 38(1), 173-186. [doi: 10.1111/j.1752-1688.2002.tb01544.x]
    Liou, Y. A., Galantowicz, J. F., and England, A. W. 1999. A land surface process/radio brightness with coupled heat and moisture transport for prairie grassland. IEEE Transactions on Geoscience Remote Sensing, 37(4), 1848-1859. [doi: 10.1109/36.774698]
    Liou, Y. A., Liu, S. F., and Wang, W. J. 2001. Retrieving soil moisture from simulated brightness temperature by a neural network. IEEE Transaction on Geoscience Remote Sensing, 39(8), 1662-1672. [doi:10. 1109/36.942544]
    Lo, M. H., Famiglietti, J. S., Yeh, P. J. F., and Syed, T. H. 2010. Improving parameter estimation and water table depth simulation in a land surface model using GRACE water storage and estimated base flow data. Water Resources Research, 46, W05517. [doi: 10.1029/2009WR007855]
    Maity, R., Bhagwat, P. P., and Bhatnagar, A. 2010. Potential of support vector regression for prediction of monthly streamflow using endogenous property. Hydrological Processes, 24(7), 917-923. [doi:10.1002/ hyp.7535]
    Margulis, S. A., McLaughlin, D., Entekhabi, D. and Dunne, S. 2002. Land data assimilation of soil moisture using measurements from the Southern Great Plains 1997 field experiment. Water Resources Research, 38(12), 1299. [doi: 10.1029/2001WR001114]
    Mather, J. K. 1974. Climatology: Fundamentals and Applications. New York: Mcgraw-Hill.
    McLaughlin, D., O'Neill, A., Derber, J., and Kamachi, M. 2005. Opportunities for enhanced collabration within the data assimilation community. Quarterly Journal of the Royal Meteorological Society, 131(613), 3683-3693. [doi: 10.1256/qj.05.89]
    Monsivais-Huertero, A., Graham, W. D., Judge, J., and Agrawal, D. 2010. Effect of simultaneous state-parameter estimation and forcing uncertainties on root-zone soil moisture for dynamic vegetation using EnKF. Advances in Water Resources, 33(4), 468-484. [doi: 10.1016/j.advwatres.2010.01.011]
    Moradkhani, H. 2008. Hydrologic remote sensing and land surface data assimilation. Sensors, 8(5), 2986-3004. [doi: 10.3390/s8052986]
    Mukherjee, S., Osuna, E., and Girosi, F. 1997. Nonlinear prediction of chaotic time series using support vector machines. Proceedings of IEEE Workshops on Neutral Network for Signal Processing, 511-520. New York: the Institute if Electrical and Electronic Engineers, Inc. [doi: 10.1109/NNSP.1997.622433]
    Pauwels, V. R. N., Hoeben, R., Verhoest, N. E. C., Troch, F. P. D., and Troch, P. A. 2002. Improvement of TOPLATS-based discharge predictions through assimilation of ERS-based remotely sensed soil moisture values. Hydrological Processes, 16(5), 995-1013. [doi: 10.1002/hyp.315]
    Qin, J., Liang, S. L., Yang, K., and Kaihotsu, I. 2009. Simultaneous estimation of both soil moisture and model parameters using particle filtering method through the assimilation of microwave signal. Journal of Geophysical Researches, 114, D15103. [doi: 10.1029/2008JD011358]
    Schölkopf, B., Kah-Kay, S., Burges, C. J. C., Girosi, F., Nivoqi, P., Poqqio, T. and Vapnik, V. 1997. Comparing support vector machines with Gaussian kernels to Radial basis function classifiers. IEEE Tansactions on Signal Processing, 45(11), 2758-2765. [doi: 10.1109/78.650102]
    Smola, A. J. 1998. Learning with Kernels. Ph. D. Dissertation. Berlin: Technischen University of Berlin..
    Vapnik, V. 1995. The Nature of Statistical Learning Theory. New York: Springer.
    Vapnik, V. 1998. Statistical Learning Theory. New York: Wiley.
    Welch, G., and Bishop, G., 2002. An introduction to the Kalman filter (Technical Report 95-041). Chapel Hill: Department of Computer Science, University of North Carolina at Chapel Hill..
    Xie, X. H., and Zhang, D. X. 2010. Data assimilation for distributed hydrological catchment modeling via ensemble Kalman filter. Advances in Water Resources, 33(6), 678-690. [doi:10.1016/j.advwatres. 2010.03.012]
    Yu, P. S., Chen, S. T., and Chang, I. F. 2006. Support vector regression for real-time flood stage forecasting. Journal of Hydrology, 328(3-4), 704-716. [doi: 10.1016/j.jhydrol.2006.01.021]
    • Relative Articles
    • Supplements(0)
    • Cited By
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索
    Get Citation
    PDF
    XML

    Article Metrics

    Article views (2869) PDF downloads(3117) Cited by()
    Proportional views
    Related

    Copyright © 2009 Editorial office of Water Science and Engineering 苏ICP备12023610号-1

    Supported by: Beijing Renhe Information Technology Co. Ltd   support: info@rhhz.net

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return