DOI QR코드

DOI QR Code

Rainfall-Runoff Analysis Utilizing Multiple Impulse Responses

복수의 임펄스 응답을 이용한 강우-유출 해석

  • Yoo, Chul-Sang (Dept. of Civil and Environmental Engineering, Korea University) ;
  • Park, Joo-Young (Dept. of Control and Instrumentation Engineering, Korea University)
  • Published : 2006.10.25

Abstract

There have been many recent studies on the nonlinear rainfall-runoff modeling, where the use of neural networks is shown to be quite successful. Due to fundamental limitation of linear structures, employing linear models has often been considered inferior to the neural network approaches in this area. However, we believe that with an appropriate extension, the concept of linear impulse responses can be a viable tool since it enables us to understand underlying dynamics principles better. In this paper, we propose the use of multiple impulse responses for the problem of rainfall-runoff analysis. The proposed method is based on a simple and fixed strategy for switching among multiple linear impulse-response models, each of which satisfies the constraints of non-negativity and uni-modality. The computational analysis performed for a certain Korean hydrometeorologic data set showed that the proposed method can yield very meaningful results.

최근들어 강우-유출 현상에 관한 비선형 모델링에 관하여 많은 연구가 있어 왔는데, 그 중에서도 신경망을 이용한 결과는 매우 성공적인 것으로 보고되어 왔다. 선형 구조가 갖는 근본적인 한계성으로 인하여, 이 분야에 선형 모델을 활용하는 것은 신경망을 사용하는 경우에 비하여 불리할 것으로 여겨지곤 한다. 하지만 우리는, 선형 모델의 경우 주어진 문제가 갖는 근본적 동특성의 원리를 보다 잘 이해할 수 있도록 해주므로, 적절한 확장 과정을 거치면 선형 임펄스 응답의 개념은 매우 경쟁력 있는 도구가 될 수 있을 것으로 생각한다. 이러한 생각에 따라, 본 논문에서 우리는 복수의 임펄스 응답의 이용을 강우-유출 해석의 문제에 적용하는 방안을 제안한다. 제안된 방법은 복수의 임펄스 응답 모델 사이에 적용되는 단순하고 고정된 스위칭 전략에 기반을 두고 있으며, 각 임펄스 응답은 음이 아닌 성분을 갖도록 하고, 동시에 한개의 봉우리만 갖는 형태를 만족하도록 한다. 우리나라의 특정한 지역의 수문기상학 자료를 대상으로 하여 적용해 본 결과, 제안된 방법은 매우 의미 있는 결과를 제공함을 보여주었다.

Keywords

References

  1. H. K. Cigizoglu, 'Estimation, forecasting and extrapolation of river flows by artificial neural networks,' Hydrological Sciences Journal, Vol. 48, No.3, pp. 349-360, 2003 https://doi.org/10.1623/hysj.48.3.349.45288
  2. H. K. Cigizoglu, 'Estimation and forecasting of daily suspended sediment data by multi-layer perceptrons,' Advances in Water Resources, Vol. 27, pp. 185-195, 2004 https://doi.org/10.1016/j.advwatres.2003.10.003
  3. H. K. Cigizoglu and M. Alp, 'Rainfall-runoff modelling using three neural network methods,' L. Rutkowski et al. (Eds.): ICAISC 2004, Lecture Notes in Artificial Intelligence, Vol. 3070, pp. 166-171. Springer-Verlag, Berlin, 2004 https://doi.org/10.1007/978-3-540-24844-6_20
  4. K P. Sudheer, A. K Gosalin, and K. S. Ramasastri, 'A data-driven algorithm for constructing artificial neural network rainfall-runoff models,' Hydrological Processes, Vol. 16, pp. 1325-1330, 2002 https://doi.org/10.1002/hyp.554
  5. H. R. Maier and G. C. Dandy, 'Neural network for the prediction and forecasting of water resources variaboes: a review of modeling issues and applications,' Environmental Modeling and Software, Vol. 15, pp. 101-124, 2000 https://doi.org/10.1016/S1364-8152(99)00007-9
  6. K. Pawelzik, J Kohlmorgen, and K-R. Muller, 'Annealed competition of experts for a segmentation and classification of switching dynamics,' Neural Computation, Vol. 8, No.2, pp. 340-356, 1996 https://doi.org/10.1162/neco.1996.8.2.340
  7. K.-R. Muller, J Kohlmorgen, and K Pawelzik, 'Analysis of switching dynamics with competing neural networks,' IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, Vol. E78- A, No. 10, pp. 1306-1315, 1995
  8. M.-W. Chang, C.-J Lin, and R. C. Weng, 'Analysis of switching dynamics with competing support vector machines,' IEEE Transactions on Neural Networks, Vol. 15, pp. 720-727, 2004 https://doi.org/10.1109/TNN.2004.824270
  9. C. Yoo and J Park, 'Rainfall-runoff analysis based on competing linear impulse responses,' Submitted, 2006
  10. T. F. Coleman, M. A. Branch, and A. Grace, Optimization Toolbox for Use with MATLAB, User's Guide, Version 2, Math Works Inc., 1999
  11. T. K Moon and W. C. Stirling, Mathematical Methods and Algorithms for Signal Processing, Prentice Hall, Upper Saddle River, NJ, 2000
  12. E. Todini, 'The CLS model,' In Mathematical models of large watershed hydrology, Singh, V. P., Frevert, D. K., and Meyer, S. P. (eds.), Water Resources Publications, Littleton, Colorade, Chapter 20, pp. 861-886, 2002