All Issue

2018 Vol.38, Issue 5 Preview Page
October 2018. pp. 671-683

The flood damage caused by heavy rains in urban watershed is increasing, and, as evidenced by many previous studies, urban flooding usually exceeds the water capacity of drainage networks. The flood on the area which considerably urbanized and densely populated cause serious social and economic damage. To solve this problem, deterministic and probabilistic studies have been conducted for the prediction flooding in urban areas. However, it is insufficient to obtain lead times and to derive the prediction results for the flood volume in a short period of time. In this study, IDNN, TDNN and NARX were compared for real-time flood prediction based on urban runoff analysis to present the optimal real-time urban flood prediction technique. As a result of the flood prediction with rainfall event of 2010 and 2011 in Gangnam area, the Nash efficiency coefficient of the input delay artificial neural network, the time delay neural network and nonlinear autoregressive network with exogenous inputs are 0.86, 0.92, 0.99 and 0.53, 0.41, 0.98 respectively. Comparing with the result of the error analysis on the predicted result, it is revealed that the use of nonlinear autoregressive network with exogenous inputs must be appropriate for the establishment of urban flood response system in the future.

도시유역에 대한 집중호우에 따른 침수피해가 증가하고 있으며, 기존에 수행된 많은 연구에서 입증 되어진 바와 같이 도시 침수는 하수관망의 통수능을 상회함에 따라 발생하는 내수침수에 주로 기인하고 있다. 도시화가 상당히 진행되고 인구가 밀집되어 있는 지역에 대한 침수피해는 심각한 사회․경제적 피해를 야기한다. 이에 따라 도시지역에 대한 홍수 예측을 위한 확정 및 확률론적 연구가 진행되어 왔지만, 충분한 선행시간을 확보하며 단시간에 홍수량에 대한 예측결과를 도출하기에는 부족한 실정이다. 본 연구에서는 최적의 실시간 도시 홍수 예측 기법을 제시하기 위하여 도시유출해석 기반 실시간 홍수 예측을 위한 IDNN, TDNN 그리고 NARX 동적신경망을 비교하였다. 강남 지역의 2010, 2011년 실제 호우사상에 대하여 총 홍수량 예측 결과, 입력 지연 인공신경망의 최대 Nash-Sutcliffe 효율 계수는 각각 0.86, 0.53, 시간 지연 인공신경망의 경우 0.92, 0.41, 외생변수를 이용한 비선형 자기 회귀의 경우 0.99, 0.98으로 나타났다. 연구 대상지역에 대한 각 맨홀 누적월류량을 고려한 예측 결과의 오차분석을 통하여 외생변수를 이용한 비선형 자기 회귀 기법을 사용하는 것이 추후 도시 홍수 대응체계 구축에 적합할 것으로 나타났다.

  1. Chang, F. J., Chen, P. A., Lu, Y. R., Huang, E. and Chang, K. Y. (2014a). “Real-time multi-step-ahead water level forecasting by recurrent neural networks for urban flood control.” Journal Hydrol., Vol. 517, pp. 836-846.10.1016/j.jhydrol.2014.06.013
  2. Chang, L. C., Shen, H. Y. and Chang, F. J. (2014b). “Regional flood inundation nowcast using hybrid SOM and dynamic neural networks.” Journal Hydrol., Vol. 519, pp. 476-489.10.1016/j.jhydrol.2014.07.036
  3. Chang, L. C., Shen, H. Y., Wang, Y. F., Huang, J. Y. and Lin, Y. T. (2010). “Clustering-based hybrid inundation model for forecasting flood inundation depths.” Journal Hydrol., Vol. 385, pp. 257-268.10.1016/j.jhydrol.2010.02.028
  4. Choi, S. M., Yoon, S. S. and Choi, Y. J. (2015). “Evaluation of high-resolution QPE data for urban runoff analysis.” Journal Korea Water Resour. Assoc., Vol. 48, pp. 719-728 (in Korean). 10.3741/JKWRA.2015.48.9.719
  5. Ha, C. Y. (2017). Parameter Optimization Analysis in Urban Flood Simulation by Applying 1D-2D Coupled Hydraulic Model. Ph.D. Thesis, Kyungpook National University.
  6. Jang, S. H., Yoon, J. Y. and Yoon, Y. N. (2006). “A study on the improvement of Huff’s method for applying in Korea : Ⅱ. Improvement of Huff’s method.” Journal Korea Water Resour. Assoc., Vol. 39, No. 9, pp. 779-786 (in Korean).
  7. Jung, K. J. (2005). “Development of the infiltration damage prediction model in a catchment using artificial neural networks.” J. Korean Society of Hazard Mitigation, Vol. 5, No. 2, p. 5 (in Korean).
  8. Kang, J. E. and Lee, M. J. (2015). “Analysis of urban infrastructure risk areas to flooding using neural network in Seoul.” J. Korean Soc. Civ. Eng., Vol. 35, No. 4, p. 997 (in Korean).10.12652/Ksce.2015.35.4.0997
  9. Lee, B. H. (2006). “A study on the characteristics and composition direction of urban flood control system.” Water and Future, pp. 50-54.
  10. Moriasi, D. N., Arnold, J. G., Van Liew, M. W., Bingner, R. L., Harmel, R. D. and Veith, T. L. (2007). “Model evaluation guidelines for systematic quantification of accuracy in watershed simulations.” ASABE., Vol. 50, No. 3, pp. 885-900.10.13031/2013.23153
  11. Oh, J. W., Park, J. H. and Kim, Y. K. (2008). “Missing hydrological data estimation using neural network and real time data reconciliation.” Journal Korea Water Resour. Assoc., Vol. 41, No. 10, p. 1059 (in Korean).10.3741/JKWRA.2008.41.10.1059
  12. Pan, T. Y., Lai, J. S., Chang, T. J., Chang, H. K., Chang, K. C. and Tan, Y. C. (2011). “Hybrid neural networks in rainfall-inundation forecasting based on a synthetic potential inundation database.” Nat. Hazards Earth Syst. Sci., Vol. 11, pp. 771-787.10.5194/nhess-11-771-2011
  13. Seoul Metropolitan City. (2015). Comprehensive Plan for Storm and Flood Damage Reduction (in Korean).
  14. Shen, H. Y. and Chang, L. C. (2013). “Online multistep-ahead inundation depth forecasts by recurrent NARX networks.” Hydrol. Earth Syst. Sci., Vol. 17, pp. 935-945.10.5194/hess-17-935-2013
  15. Son, A. L. and Han, K. Y. (2014). “The development of urban inundation reduction model combined real-time data-driven estimation and 2D hydraulic analysis.” Proc. of Conf. Korean Society of Hazard Mitigation, Vol. 2014, p. 90.
  16. Toth, E., Brath, A. and Montanari, A. (2000). “Comparison of short-term rainfall prediction models for real-time flood forecasting.” Journal Hydrol., Vol. 239, pp. 132-147.10.1016/S0022-1694(00)00344-9
  17. Tsai, M. H., Sung, E. X. and Kang, S. C. (2016). “Data-driven flood analysis and decision support.” Nat. Hazards Eearth Syst, Sci. Discuss., doi:10.5194/nhess-2016-141.10.5194/nhess-2016-141
  18. Yoon, K. H., Seo, B. C. and Shin, H. S. (2004). “Dam inflow forecasting for short term flood based on neural networks in nakdong river basin.” Journal Korea Water Resour. Assoc., Vol. 37, No. 1, pp. 67-75 (in Korean).10.3741/JKWRA.2004.37.2.14510.3741/JKWRA.2004.37.1.067
  • Publisher :Korean Society of Civil Engineers
  • Publisher(Ko) :대한토목학회
  • Journal Title(Ko) :대한토목학회 논문집
  • Volume : 38
  • No :5
  • Pages :671-683
  • Received Date :2018. 08. 08
  • Accepted Date : 2018. 08. 30