KSCE Journal of Civil and Environmental Engineering Research (대한토목학회논문집)

Korean Society of Civil Engeneers (대한토목학회)
권호 표지
DOI QR코드

DOI QR Code

Linkage of Hydrological Model and Machine Learning for Real-time Prediction of River Flood

수문모형과 기계학습을 연계한 실시간 하천홍수 예측

  • 이재영 (한국건설기술연구원 국토보전연구본부) ;
  • 김현일 (경북대학교 건설환경에너지공학부) ;
  • 한건연 (경북대학교 토목공학과)
  • Received : 2019.11.20
  • Accepted : 2019.12.11
  • Published : 2020.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

The hydrological characteristics of watersheds and hydraulic systems of urban and river floods are highly nonlinear and contain uncertain variables. Therefore, the predicted time series of rainfall-runoff data in flood analysis is not suitable for existing neural networks. To overcome the challenge of prediction, a NARX (Nonlinear Autoregressive Exogenous Model), which is a kind of recurrent dynamic neural network that maximizes the learning ability of a neural network, was applied to forecast a flood in real-time. At the same time, NARX has the characteristics of a time-delay neural network. In this study, a hydrological model was constructed for the Taehwa river basin, and the NARX time-delay parameter was adjusted 10 to 120 minutes. As a result, we found that precise prediction is possible as the time-delay parameter was increased by confirming that the NSE increased from 0.530 to 0.988 and the RMSE decreased from 379.9 ㎥/s to 16.1 ㎥/s. The machine learning technique with NARX will contribute to the accurate prediction of flow rate with an unexpected extreme flood condition.

수자원분야에서 이용되는 강우에 따른 유역의 수문학적 시스템, 도시지역 및 하천에 대한 수리학적 시스템은 비선형성이 강하고 많은 변수들을 포함하고 있다. 이러한 특성을 가진 시계열 자료에서 기계학습을 통한 예측은 예측시점 이전의 자료 특성을 반영하지 못하는 등 기본적인 신경망으로는 부족한 상황이 발생하기도 한다. 본 연구에서 적용할 강우-유출량과 같이 비선형성이 강하고 시간종속성이 높은 복잡한 시계열 자료를 예측하기 위해 신경망의 학습능력을 극대화한 순환형 동적 신경망(Recurrent Dynamic Neural Network)의 한 종류인 동시에, 시간 지연 신경망(Time-Delay Neural Network)의 특성을 가진 비선형 자기회귀(NARX, Nonlinear Autoregressive Exogenous Model) 인공신경망을 사용하였다. 이를 태화강 지방하천 구간에 적용하여 NARX 인공신경망의 시간 지연 매개변수를 10분에서 120분까지 조정하며 모의한 결과에 대해 여러 통계지표를 이용해 정량적으로 평가하였다. 그 결과 지연시간이 증가할수록 효율계수(NSE)가 0.530에서 0.988으로 증가하고, 평균제곱근편차(RMSE)가 379.9 ㎥/s에서 16.1 ㎥/s로 감소하는 등 정교한 예측이 가능함을 확인하였다.

Keywords

References

  1. Chang F. J., Chen, P. A., Lu, Y. R., Huang, E. and Chang, K. Y. (2014). "Real-time multi-step-ahead water level forecasting by recurrent neural networks for urban flood control." Journal of Hydrology, Vol. 517, pp. 836-846. https://doi.org/10.1016/j.jhydrol.2014.06.013
  2. Gupta, H. V., Sorooshian, S. and Yapo, P. O. (1999). "Status of automatic calibration for hydrologic models: Comparison with multilevel expert calibration." Journal of Hydrology, Vol. 4, No. 2, pp. 135-143.
  3. Keum, H. J. (2018). Development of flood disaster prediction and management system combining machine learning technique with big data, Ph.D. Dissertation, Kyungpook National University (in Korean).
  4. Kim, B. J. (2016). Urban inundation analysis using deterministic approach and data-driven model, Master's Thesis, Kyungpook National University (in Korean).
  5. Kim, H. I., Keum, H. J. and Han, K. Y. (2018). "Application and comparison of dynamic artificial neural networks for urban inundation analysis." Journal of the Korean Society of Civil Engineers, KSCE, Vol. 38, No. 5, pp. 671-683 (in Korean). https://doi.org/10.12652/Ksce.2018.38.5.0671
  6. Ministry of Land, Infrastructure and Transport (MOLIT) (2016). River design standard (in Korean).
  7. 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." American Society of Agricultural and Biological Engineering, Vol. 50, No. 3, pp. 885-900.
  8. Nash, J. E. and Sutcliffe, J. V. (1970). "River flow forecasting through conceptual models, Part I - A discussion of principles." Journal of Hydrology, Vol. 10, No. 3, pp. 282-290. https://doi.org/10.1016/0022-1694(70)90255-6
  9. Nayak, P. C., Sudheer, K. P., Rangan, D. M. and Ramasastri, K. S. (2005). "Short-term flood forecastig with a neuro-fuzzy model." Water Resources Research, Vol. 41, No. 4, W04004.
  10. Oh, J. W. Park, J. H. and Kim, Y. K. (2008). "Missing hydrological data estimation using neural network and real time data reconciliation." Journal of Korea Water Resources Association, KWRA, Vol. 41, No. 10, pp. 1059-1065 (in Korean). https://doi.org/10.3741/JKWRA.2008.41.10.1059
  11. Shen, H. Y. and Chang, L. C. (2013). "Online multistep-ahead inundation depth forecasts by recurrent NARX networks." Hydrology and Earth System Sciences, Vol. 17, pp. 935-945. https://doi.org/10.5194/hess-17-935-2013
  12. Toth, E. (2009). "Classification of hydro-meteorological conditions and multiple artificial neural networks for stream forecasting." Hydrology and Earth System, Vol. 13, pp. 1555-1566. https://doi.org/10.5194/hess-13-1555-2009
  13. Ulsan Metropolitan City (2017). Analysis of flood damage in bancheon hyundai apartment in Ulju-gun (in Korean).