Journal of Korea Water Resources Association (한국수자원학회논문집)

Korea Water Resources Association (한국수자원학회)
권호 표지

The Flood Water Stage Prediction based on Neural Networks Method in Stream Gauge Station

하천수위표지점에서 신경망기법을 이용한 홍수위의 예측

  • 김성원 (콜로라도 주립대학교 토목공학과) ;
  • 호세살라스 (콜로라도 주립대학교 토목공학과)
  • Published : 2000.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, the WSANN(Water Stage Analysis with Neural Network) model was presented so as to predict flood water stage at Jindong which has been the major stream gauging station in Nakdong river basin. The WSANN model used the improved backpropagation training algorithm which was complemented by the momentum method, improvement of initial condition and adaptive-learning rate and the data which were used for this study were classified into training and testing data sets. An empirical equation was derived to determine optimal hidden layer node between the hidden layer node and threshold iteration number. And, the calibration of the WSANN model was performed by the four training data sets. As a result of calibration, the WSANN22 and WSANN32 model were selected for the optimal models which would be used for model verification. The model verification was carried out so as to evaluate model fitness with the two-untrained testing data sets. And, flood water stages were reasonably predicted through the results of statistical analysis. As results of this study, further research activities are needed for the construction of a real-time warning of the impending flood and for the control of flood water stage with neural network method in river basin. basin.

본 연구에서는 낙동강유역의 주요 수위표지점중 진동수위표지점에서 홍수위를 예측하기위한 신경망모형인 WSANN모형이 제시되었다. WSANN모형은 모멘트방법, 초기조건의 개선 및 적응학습속도에 의해 보완되어진 개선된 역전파훈련 알고리즘을 이용하였고, 본 연구에 사용된 자료는 훈련자료와 테스팅자료로 분할하였으며, 최적 은닉층 노드수를 결정하기 위하여 은닉층노드와 임계학습횟수로부터 경험식이 유도되었다. 그리고 WSANN모형의 보정은 4개의 훈련자료에 의해 실시되었으며, WSANN22와 WSANN32모형이 모델의 검증에 사용될 최적모형으로 결정되었다. 모형의 검증은 훈련되지 않은 2개의 테스팅자료를 이용하여 모형의 적합성을 평가하기 위하여 이루어 졌으며, 통계분석의 결과를 통하여 홍수위를 합리적으로 예측하는 것으로 나타났다. 따라서 본 연구의 결과를 기본으로 신경망기법을 이용한 실시간 홍수예경보 시스템의 구축 및 홍수위의 제어에 관한 지속적인 연구가 필요것으로 사료된다.

Keywords

References

  1. 건설교통부, 한국수자원공사(1999). 기존댐 용수공급 능력조사(낙동강.금강수계)보고서
  2. 김주환 (1993). 신경회로망을 이용한 하천유출량의 수문학적 예측에 관한 연구, 박사학위논문, 인하대학교
  3. 신현석, 박무종(1999a). '신경망기법을 이용한 연평균 강우량의 공간해석', 한국수자원학회논문집, 한국수자원학회, 제32권, 제1호, pp.3-13
  4. 신현석, 박무종(1999b). '신경망을 이용한 우리나라의 시공간적 가뭄의 해석', 한국수자원학회논문집, 한국수자원학회, 제32권, 제1호, pp.15-29
  5. 심순보, 김만식(1999a). '충주 다목적댐 홍수유입량 예측을 위한 최적 신경망모형의 개발', 대한토목학회논문집, 대한토목학회, 제19권, 제II-1호, pp.67-78
  6. 오남선, 선우중호(1996). '신경망이론에 의한 강우 예측에 관한 연구', 한국수자원학회논문집, 한국수자원학회, 제29권, 제4호, pp.109-118
  7. Bonafe, A., Galeati, G., and Sfoma, M.(1994). 'Neural networks for daily mean now forecasting.' in Hydraulic Engineering Software V, Vol. 1, edited by W.R. Blain and K.L. Katsifarakis, Water Resources and Distribution, Computational Mechanics Publication, Southampton, UK, pp. 131-138
  8. Bras, R.L., and Rodrigues - Iturbe, I.( 1985). Random functions and hydrology. AddisonWesley Publication
  9. Crespo, L., and Mora, E.(1993). 'Drought estimation with neural networks.' Advanced in Engineering Software, Elsevier, Whitstable, Kent, UK, pp. 167-170 https://doi.org/10.1016/0965-9978(93)90064-Z
  10. Dawson, C.W., and Wilby, R. (1998). 'An artificial neural network approach to rainfall-runoff modeling.' Hydrological Sciences, Vol. 43, No.1, pp. 47-66
  11. Demuth, H., and Beale, M.(1998). Neural network toolbox : for use with MA TLAB user's guide, The Math Works Inc.
  12. Freeman, J.A., and Skapure, D.M.(1991). Neural networks algorithms, applications and programming technology, Addison-Wesley Publishing Co., Reading, MA
  13. French, M.N., Krajewski, W.F., and Cuykendal, R.R.(1992). 'Rainfall forecasting in space and time using a neural network.' J. of Hydrology, Amsterdam, Netherlands, Vol. 137, pp. 1-37 https://doi.org/10.1016/0022-1694(92)90046-X
  14. Gallant, S.I.(1993), Neural network learning and expert systems, MIT Press, Cambridge, MA
  15. Haykin, S.(1994). Neural networks A comprehensive foundation, Macmillan College Pub. Comp., Inc.
  16. Hsu, K, Gupta, H.V., and Soroosian, S.(1995). 'Artificial neural networks modeling of the rainfall-runoff process.' Water Reour. Res., Vol. 31, No. 10, pp. 2517-2106
  17. Karunanithi, N., Grenney, W. J., Whitley, D., and Bovee, K.(1994). 'Neural Networks for river flow prediction.' J. of Computing in Civ. Engrg., ASCE, Vol. 8, No.2, pp. 201-220 https://doi.org/10.1061/(ASCE)0887-3801(1994)8:2(201)
  18. Karunanithi, N., Whitley, D., and Malaiya, Y.K. (1992b). 'Using neural networks in reliability prediction.' IEEE Software, Vol. 9, No.4, pp. 53-59 https://doi.org/10.1109/52.143107
  19. Kosko, B.(1992). Neural Network and Fuzzy systems, Prentice-Hall, Inc., Eaglewood Cliffs, N.J.
  20. Markus, Salas, J.D. and M., Shin, H.S.(1995). Predicting streamflows based on neural network.' 1995 First International Conference on Water Resources Engineering, ASCE, San Antonio, TX
  21. Mutreja, K.N., Yin, A., and Martino, I.(1987). 'Flood forecasting model for Citandy River.' Flood hydrology, V.P. Singh, ed., Reidel, Dordrecht, The Netherlands, pp. 211-220
  22. Nguyen, D.H. and Widrow, B.(1990). 'Neural network for self-learning control systems.' IEEE Contrl Systems Magazine, pp. 18-23
  23. Roman, H. and Chandramouli, V.(l996). 'Deriving a general operating policy for reservoirs using neural network.' J. of Water Resour. Ping. and Mgmt., ASCE, Vol. 122, No.5, pp. 342-347 https://doi.org/10.1061/(ASCE)0733-9496(1996)122:5(342)
  24. Salas, J.D., Delleur, J.W., Yevjevich, V., and Lane, W.L.(1980). Applied and modeling of hydrologic time series, Water Resources Publication, Littleton, CO
  25. Salas, J.D., Smith, R. A, Tabios III, G. Q., and Heo, J. H. (1999). Statistical computer techniques in water resources and environmental engineering, Unpublished text book in CE622, Colorado State University, Fort Collins, CO
  26. Sigmon, K.(1989). MATLAB primer, Dept. of Mathematics, Univ. of Florida, Gainesville, FL
  27. Shin, H.S., and Salas, J.D.(1997). 'Spatial analysis neural network model and its applications to hydrological and environmental data.' Water Resources Paper, No. 109, Dept. of Civil Engr., Colorado State University, Fort Collins, CO
  28. Smith, J.(1992). Streamflow forecasting using a back propagation neural network, M.S. Thesis, West Virginia Univ., Morgantown, WV
  29. Smith, J, and Eli, R.N.(1995). 'Neural network models of rainfall-runoff process.' J. of Water Resour. PIng. and Mgmt., ASCE, Vol. 121, No.6, pp. 499-508 https://doi.org/10.1061/(ASCE)0733-9496(1995)121:6(499)
  30. Smith, M.,(1993). Neural networks for statistical modelling, Van Nostrand Reinhod, New York, pp. 1-114
  31. Tawfik, M., Ibrahim, A, and Fahmy, H.(1997). 'Hysteresis sensitive neural network for modeling rating curves.' J. of Computing in Civ. Engrg., ASCE, Vol. 11, No.3, pp. 206-211 https://doi.org/10.1061/(ASCE)0887-3801(1997)11:3(206)
  32. Thirumalaiah, K., and Deo, M.C.(1998). 'River stage forecasting using artificial neural networks.' J. of Hydro. Eng., ASCE, Vol. 3, No.1, pp. 26-32 https://doi.org/10.1061/(ASCE)1084-0699(1998)3:1(26)
  33. Tsoukalas, L.H., and Uhrig, R.H.(1997). Fuzzy and neural approaches in engineering, John Wiley & Sons Inc