Magazine of the Korean Society of Agricultural Engineers (한국농공학회지)

The Korean Society of Agricultural Engineers (한국농공학회)
권호 표지

Short-term Flood Forecasting Using Artificial Neural Networks

인공신경망 이론을 이용한 단기 홍수량 예측

  • 강문성 (서울대학교 농업생명과학연구원) ;
  • 박승우 (서울대학교 농공대학)
  • Published : 2003.03.01
Download PDF
⟨ Previous Next ⟩

Abstract

An artificial neural network model was developed to analyze and forecast Short-term river runoff from the Naju watershed, in Korea. Error back propagation neural networks (EBPN) of hourly rainfall and runoff data were found to have a high performance In forecasting runoff. The number of hidden nodes were optimized using total error and Bayesian information criterion. Model forecasts are very accurate (i.e., relative error is less than 3% and $R^2$is greater than 0.99) for calibration and verification data sets. Increasing the time horizon for application data sets, thus mating the model suitable for flood forecasting. decreases the accuracy of the model. The resulting optimal EBPN models for forecasting hourly runoff consists of ten rainfall and four runoff data(ANN0410 model) and ten rainfall and ten runoff data(ANN1010 model). Performances of the ANN0410 and ANN1010 models remain satisfactory up to 6 hours (i.e., $R^2$is greater than 0.92).

Keywords

References

  1. Ahn, K. S., and J. H. Kim. 1998. A study on the simulation of runoff hydrograph by using artificial neural network. Journal of Korea Water Resources Association 31(1): 13-25. (in Korean)
  2. Anmala. J., and K. V. Nedunuri. 1995. Neural networks for prediction of watershed runoff, 1st International Conference on Water Resources Eng. Water Resources Planning and Management Div., ASCE, San Antonio, Texas, USA, Aug. 14-18, pp. 348-357
  3. Anthony, W. M., 1996. Extened rainfall-runoff nodeling using aritificial neural networks, Proc. of the 2nd International Conf. on Hydroinforrnatics, '96, Zurich, Switzerland, pp, 207-213
  4. Asaad, Y. S.. 1997. Application of a neural network technique to rainfall-runoff modeling. Journal of Hydrology 199: 272-294
  5. Choi, J. K., and M. S. Kang. 2000. Application of neural network to water resources. Korean National Committee on Irrigation and Drainage Journal 7(2): 246-258. (in Korean)
  6. Dawson, C. W., and R. Wilby. 1998. An artificial neural network approach to rainfall-runoff modeling, Hydrological Sciences 43(1): 47-66
  7. Hsu, K. N., H. V. Gupta, and S. sorooshian. 1995. Artificial neural network modeling of the rainfall-runoff process. Water Resources Research 31(10): 2517-2530
  8. Huynh, N. P. and S. Sureerattanan, 2000. Neural networks for filtering and forecasting of daily and monthly streamflows, Water Resources Publications, LLC, WEESHE, Hydrologic Modeling, pp. 203-218
  9. Kang, M. S., and S. W. Park. 2001. Forecasting long-term streamflow from a small watershed using artificial neural network. Journal of the Korean Society of Agricultural Engineers 43(2): 69-77. (in Korean)
  10. Kim, J. H. 1993. A study on hydrologic forecasting of streamflows based on artificial neural network. Ph.D. diss. Inha University. (in Korean)
  11. Marina, C., P. Andreussi, and A. Soldati. 1999. River flood forecasting with a neural network model. Water Resources Research 35(4): 1191-1197
  12. Nash. J. E. and J. V. Sutcliffe. 1970. River flow forecasting through conceptual models part I-A discussion of principles. Journal of Hydrology 10: 282-290
  13. Sajikumar, N. and B. S. Thandaveswara. 1999. A nonlinear rainfall-runoff model using ANN. Journal of Hydrology, 216: 32-55 https://doi.org/10.1016/S0022-1694(98)00273-X
  14. Shim, S. B., M. S. Kim, and K. C. Shim. 1998. Flood inflow forecasting on multipurpose reservoir by neural network. Journal of Korea Water Resources Association 31 (1): 45-57. (in Korean)
  15. Shin. H. S., and M. J. Park. 1999. Spatial analysis for mean annual precipitation based on neural networks. Journal of Korea Water Resources Association 32(1): 3-13. (in Korean)
  16. Shin, H. S.. and M. J. Park. 1999. Spatialtemporal drought analysis of South Korea based on neural networks. Journal of Korea Water Resources Association 32(1): 15-29. (in Korean)
  17. Shin, H. S.. 1998. Application of neural network to water resources and environments. Magazine of Korea Water Resources Association 31 (1): 97 -103. (in Korean)
  18. Sureerattanar, S. and H. N. Phien. 1997. Back-propagation networks for daily stream flow forecasting. Water Resources Journal No. 195: 1-7
  19. Zealand, C. M., D. H. Burn, and S. P. Simonovic. 1999. Short term stream flow forecasting using ANN, Journal of Hydrology, Vol., 214, pp. 32-48