KSCE Journal of Civil and Environmental Engineering Research (대한토목학회논문집)

Korean Society of Civil Engeneers (대한토목학회)
권호 표지

The Forecast of Hydrologic Time Series Using the State-Space Model and the Nearest Neighbor Method

상태-공간 모형과 Nearest Neighbor 방법을 통한 수문시계열 예측에 관한 연구

Kwon, Hyun-Han;Moon, Young-Il
권현한;문영일

  • Published : 2005.07.31

⟨ Previous Next ⟩

Abstract

We have investigated the properties of the Nearest Neighbor method coupled to the State-Space model which makes it possible to consider the nonlinearity of the hydrologic time series and the complement linear model. These methods were normally used to predict hydrologic time series. This study introduced the methodology of estimating the delay time and embedding dimension in order to construct the State-Space model. Furthermore, we monitored this methodology with the daily water level of the Soyang river and have identified that the low dimensional nonlinearity has an embedding dimension of five. Before predicting it, the combinations between the nearest neighbor and the embedding dimension were evaluated by DVS (deterministic versus stochastic) algorithms. The predictions, based on each time step, were carried out. Although this model demonstrated encouraging and promising results in a short-term prediction (15 days), the prediction error was proportional to the increasing time step. Thus, the Nearest Neighbor method presented in this study suggests a competitive methodology for the forecast of hydrologic time series.

수문시계열의 예측을 위해 주로 사용되고 있는 선형 모형을 보완할 수 있고 비선형 특성을 고려할 수 있는 Nearest Neighbor 방법을 수문시계열의 적용하고 이에 대한 특징을 검토하였다. 상태-공간 모형을 구축하기 위한 지체시간과 Embedding Dimension의 결정방법론을 제시하였고, 소양강 일수위에 대해서 방법론을 적용하여 Embedding Dimension 5를 갖는 낮은 차원의 비선형성을 확인할 수 있었다. 예측에 앞서 DVS(deterministic versus stochastic) 알고리즘을 이용하여 Nearest Neighbor와 Embedding Dimension의 최적 조합을 추정한 후, 이를 토대로 각 시간-Step 별로 예측을 실시하였으며 15일 정도의 단기예측에서 0.9이상의 상관계수를 갖는 모의가 가능하였으나 예측-Step이 증가할수록 오차가 커지는 것을 확인할 수 있었다. 따라서 비선형 수문시계열의 단기예측을 위한 모형으로 적용이 가능할 것으로 판단된다.

Keywords

References

  1. 김형수, 최시중, 김중훈(1998) DVS 알고리즘을 이용한 일 유량 자료의 예측, 대한토목학회논문집, 대한토목학회, 제18권, 제 II-6 호, pp. 563-570
  2. 문영일(1997) 시계열 수문자료의 비선형 상관관계. 한국수자원학회논문집, 한국수자원학회, 제30권, pp. 641-648
  3. 문영일(2000) 지역가중다항식을 이용한 예측모형, 한국수자원학회논문집, 한국수자원학회, 제33권, pp. 31-38
  4. 박무종, 윤용남 (1989) Multiplicative ARIMA 모형에 의한 월 유량의 추계학적 모의 예측, 한국수자원학회논문집, 한국수자원학회, 제22권, pp. 331-339
  5. 안상진, 이재경 (2000) 추계학적 모의발생기법을 이용한 월 유출 예측, 한국수자원학회논문집, 한국수자원학회, 제33권, pp. 159-167
  6. 윤강훈, 서봉철, 신현석 (2004) 신경망을 이용한 낙동강 유역 홍 수기 댐유입량 예측, 한국수자원학회논문집, 한국수자원학회, 제37권, pp. 67-75
  7. Abarbanel, H.D.I. (1996) Analysis of Observed Chaotic Data. Spinger-Verlag, New York
  8. Abarbanel. H.D.I., Brown, Sidorowich, J.J., and Tsimring, L.S. (1993) The analysis of observed chaotic data in physical systems, Rev. Mod. Phys., Vol. 65, No. 4, pp. 1331-1392 https://doi.org/10.1103/RevModPhys.65.1331
  9. Abarbanel, H.D.I., Carroll, T.A., Pecora, L.M., Sidorowich, J.J., and Tsimring, L.S. (1994) Predicting physical variables in timedelay embedding, Physical Review E, Vol. 49, pp. 1840-1853 https://doi.org/10.1103/PhysRevE.49.1840
  10. Abarbabel, H.D.I., and Kennel, M.B. (1992) Local false nearest neighbors and dynamcal dimensions from observed chaotic data, Phys. Rev., E47, pp. 3057-3068
  11. Abarbanel, H.D.I., Lall, U., Moon, Young-II, Mann, M., and Sangoyomi, T. (1996) Nonlinear dynamic of the Great Salt Lake: A predictable indicator of regional climate, Energy, Vol. 21(7/8), pp. 655-665 https://doi.org/10.1016/0360-5442(96)00018-7
  12. Cao, L. (1997), Practical method for determining the minimum embedding dimension of a scalar time series, Physica D, Vol. 110, pp. 43-50 https://doi.org/10.1016/S0167-2789(97)00118-8
  13. Casdagli, M. (1992) Chaos and deterministic vs stochastic non-linear modelling, JRSS series B, Vol. 54, pp. 303-328
  14. Casdagli, M. and Weigend, A. (1994) Time Series Prediction, Studies in the Science of Complexity, Santa Fe Institute, edited by A. Weigend and M. Gerschenfeld (Addison-Wesley, Reading), Vol. XV, pp. 347-366
  15. Fraser, A.M. and Swinney, H.L. (1986) Independent coordinates for strange attractors from mutual information, Physical Review A, Vol. 33, pp. 1134-1140 https://doi.org/10.1103/PhysRevA.33.1134
  16. Gao, J. and Zheng, Z. (1994) Direct dynamical test for deterministic chaos and optimal reconstruction using a geometrical construction, Physical Review A, Vol 45, No. 6, pp. 3403-3411 https://doi.org/10.1103/PhysRevA.45.3403
  17. Graf, K.E., and Elbert, T. (1990) Dimensional analysis of the waking EEG, in Chaos in Brain Function, edited by E. Basar, pp. 135-152, Springer-Verlag, New York
  18. Grassberger. P. and Procaccia. I. (1983). Measuring the strangeness of strange attractors. Physica D. Vol. 7. pp 153-180 https://doi.org/10.1016/0167-2789(83)90125-2
  19. Hilborn, R.C. (1994) Chaos and Nonlinear Dynamics, Oxford University Press
  20. Holzfuss, J., and Mayer-Kress, G. (1986) An approach to error-estimation in the application of dimension algorithms, in Dimensions and Entropies in Chaotic Systems, edited by G. Mayer- Kress, pp. 114-147, Springer-Verlag, New York
  21. Kember, G., Flower, A.C., and Holubeshen, J. (1993) Forecasting river flow using nonlinear dynamics, Sthoch. Hydrol. Hydraul., Vol. 7, pp. 205-212 https://doi.org/10.1007/BF01585599
  22. Martinerie, J.M., Albano, A.M., Mees, A.I., and Rapp, P.E. (1992) Mutual information, strange attractors, and the optimal estimation of dimension, Physical Review A, Vol. 45, pp. 7058-7064 https://doi.org/10.1103/PhysRevA.45.7058
  23. Moon, Y.I. and Lall, U. (1996) Atmospheric flow indices and interannual Great Salt Lake variability, Journal of Hydrologic Engineering, Vol. 1, pp. 55-62 https://doi.org/10.1061/(ASCE)1084-0699(1996)1:2(55)
  24. Muller, K.R., Smola, A., Rätsch, G., Scholkopf, B., Kohlmorgen, J., and Vapnik, V. (1999) Predicting time series with support vector machines. In Scholkopf, B. Burges, C. and Smola, A. editors, Advances in Kernel Methods: Support Vector Learning, Cambridge, MA, MIT Press, pp. 243-254
  25. Sangoyorni. T.B.U. Lall, and Abarbanel, H.D.I. (1996). Nonlinear dynamics of the Great Salt Lake: dimension estimation, Water Resources Research. Vol. 32, No. 1. pp. 149-159 https://doi.org/10.1029/95WR02872
  26. Sauer, Y., Yorke, J.A., and Casdagli, M. (1991) Embedology. Journal of Statistical Physics, Vol. 65, pp. 579-616 https://doi.org/10.1007/BF01053745
  27. Schroeder, M. (1991) Fractals, in Chasos and Power Laws: Minutes From an Infinite Paradise, pp. 429., W.H. Freeman, New York
  28. Schuster, H. (1988). Deterministic chaos, an introduction. Physik- Verlag, Weinheim, 2nd edition
  29. Smith, J.A. (1991) Long-range streamflow forecasting using nonparametric regression, Water Resour, Bull., Vol. 27, No. 1, pp. 39-46
  30. Takens, F. (1981) Detecting strange attractors in turbulence. In, Rand, D.A. and L.S. Young (eds.). Dynamical systems and Turbulence. Springer-Verlag. Berlin, pp. 366-381
  31. Tsonis, A.A., and Elsner, J.B. (1988) The weather attractor over very short time scales, Nature, Vol. 333, pp. 545-547
  32. Yakowitz, S., and Karlsson, M. (1987) Nearest neighbor methods with application to rainfall/runoff prediction, Stochastic hydrology, Edited by Macneil, J.B., and Humphries, G.J., D. Reidel, Hingham, MA, pp. 149-160