Journal of Korea Water Resources Association (한국수자원학회논문집)

Korea Water Resources Association (한국수자원학회)
권호 표지
DOI QR코드

DOI QR Code

Water level prediction in Taehwa River basin using deep learning model based on DNN and LSTM

DNN 및 LSTM 기반 딥러닝 모형을 활용한 태화강 유역의 수위 예측

  • Lee, Myungjin (Institute of Water Resources System, Inha University) ;
  • Kim, Jongsung (Institute of Water Resources System, Inha University) ;
  • Yoo, Younghoon (Program in Smart City Engineering, Inha University) ;
  • Kim, Hung Soo (Department of Civil Engineering, Inha University) ;
  • Kim, Sam Eun (Department of Civil Engineering, Inha University) ;
  • Kim, Soojun (Department of Civil Engineering, Inha University)
  • 이명진 (인하대학교 수자원시스템 연구소) ;
  • 김종성 (인하대학교 수자원시스템 연구소) ;
  • 유영훈 (인하대학교 스마트시티공학과) ;
  • 김형수 (인하대학교 사회인프라공학과) ;
  • 김삼은 (인하대학교 토목공학과) ;
  • 김수전 (인하대학교 사회인프라공학과)
  • Received : 2021.09.27
  • Accepted : 2021.10.26
  • Published : 2021.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, the magnitude and frequency of extreme heavy rains and localized heavy rains have increased due to abnormal climate, which caused increased flood damage in river basin. As a result, the nonlinearity of the hydrological system of rivers or basins is increasing, and there is a limitation in that the lead time is insufficient to predict the water level using the existing physical-based hydrological model. This study predicted the water level at Ulsan (Taehwagyo) with a lead time of 0, 1, 2, 3, 6, 12 hours by applying deep learning techniques based on Deep Neural Network (DNN) and Long Short-Term Memory (LSTM) and evaluated the prediction accuracy. As a result, DNN model using the sliding window concept showed the highest accuracy with a correlation coefficient of 0.97 and RMSE of 0.82 m. If deep learning-based water level prediction using a DNN model is performed in the future, high prediction accuracy and sufficient lead time can be secured than water level prediction using existing physical-based hydrological models.

최근 이상 기후로 인해 극한 호우 및 국지성 호우의 규모 및 빈도가 증가하여 하천 주변의 홍수 피해가 증가하고 있다. 이에 따라 하천 또는 유역 내 수문학적 시스템의 비선형성이 증가하고 있으며, 기존의 물리적 기반의 수문 모형을 활용하여 홍수위를 예측하기에는 선행시간이 부족한 한계점이 존재한다. 본 연구에서는 Deep Neural Network (DNN) 및 Long Short-Term Memory (LSTM)기반의 딥러닝 기법을 적용하여 울산시(태화교) 지점의 수위를 0, 1, 2, 3, 6, 12시간에 대해 선행 예측을 수행하였고 예측 정확도를 비교 분석하였다. 그 결과 sliding window 개념을 적용한 DNN 모형이 선행시간 12시간까지 상관계수 0.97, RMSE 0.82 m로 가장 높은 정확도를 보이고 있음을 확인하였다. 향후 DNN 모형을 활용하여 딥러닝 기반의 수위 예측을 수행한다면 기존의 물리적 모형을 통한 홍수위 예측보다 향상된 예측 정확도와 충분한 선행시간을 확보할 수 있을 것으로 판단된다.

Keywords

Acknowledgement

본 결과물은 환경부의 재원으로 한국환경산업기술원 물관리연구사업의 지원을 받아 연구되었습니다. 이에 감사드립니다(127570).

References

  1. Adnan, R.M., Yuan, X., Kisi, O., and Yuan, Y. (2017). "Streamflow forecasting using artificial neural network and support vector machine models." American Scientific Research Journal for Engineering, Technology, and Sciences (ASRJETS), Vol. 29, No. 1, pp. 286-294.
  2. Bae, Y., Kim, J., Wang, W., Yoo, Y., Jung, J., and Kim, H.S. (2019). "Monthly inflow forecasting of Soyang River Dam using VARMA and machine learning models." Journal of Climate Research, Vol. 14, No. 3, pp. 183-198. https://doi.org/10.14383/cri.2019.14.3.183
  3. 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
  4. Coulibaly, P., and Anctil, F. (1999). "Real-time short-term natural water inflows forecasting using recurrent neural networks." International Joint Conference on IEEE, Washington DC, U.S., pp. 3802-3805.
  5. Dawson, C.W., and Wilby, R. (1998). "An artificial neural network approach to rainfall-runoff modelling". Hydrological Sciences Journal, Vol. 43, No. 1, pp. 47-66. https://doi.org/10.1080/02626669809492102
  6. Hinton, G.E., Osindero, S., and Teh, Y.W. (2006). "A fast learning algorithm for deep belief nets." Neural Computation, Vol. 18, No. 7, pp. 1527-1554. https://doi.org/10.1162/neco.2006.18.7.1527
  7. Hochreiter, S., and Schmidhuber, J. (1997). "Long short-term memory." Neural Computation, Vol. 9, No. 8, pp. 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  8. Huang, X., Li, Y., Tian, Z., Ye, Q., Ke, Q., Fan, D., Mao, G., Chen, A. Liu, J. (2021). "Evaluation of short-term streamflow prediction methods in Urban river basins." Physics and Chemistry of the Earth, Parts A/B/C, Vol. 123.
  9. Jung, J., Mo, H., Lee, J., Yoo, Y., and Kim, H.S. (2021). "Flood stage forecasting at the Gurye-Gyo station in Sumjin River using LSTM-based deep learning models." Journal of the Korean Society of Hazard Mitigation, Vol. 21, No. 3, pp. 193-201.
  10. Jung, S., Cho, H., Kim, J., and Lee, G. (2018). "Prediction of water level in a tidal river using a deep-learning based LSTM model." Journal of Korea Water Resources Association, Vol. 51, No. 12, pp. 1207-1216.
  11. Kim, B.J. (2007). Comparative study of storage function and SSARR models for the flood hydrograph forecasting of a Miho Stream. Ph. D. dissertation, Inha University,
  12. Kim, D., Kim, J., Kwak, J., Necesito, I.V., Kim, J., and Kim, H.S. (2020a). "Development of water level prediction models using deep neural network in mountain wetlands." Journal of Wetlands Research, Vol. 22, No. 2, pp. 106-112. https://doi.org/10.17663/JWR.2020.22.2.106
  13. Kim, H.I., Lee, J.Y., Han, K.Y. and Cho, J.W. (2020b). "Applying observed rainfall and deep neural network for urban flood analysis." Journal of the Korean Society of Hazard Mitigation, Vol. 20, No. 1, pp. 339-350. https://doi.org/10.9798/kosham.2020.20.1.339
  14. Kim, Y.J., Kim, T.W., Yoon, J.S., and Kim, I.H. (2019a). "Study on prediction of similar typhoons through neural network optimization." Journal of Ocean Engineering and Technology, Vol. 33, No. 5, pp. 427-434. https://doi.org/10.26748/KSOE.2019.065
  15. Kim, Y.J., Kim, T.W., Yoon, J.S., and Kim, M.K. (2019b). "Study of the construction of a coastal disaster prevention system using deep learning." Journal of Ocean Engineering and Technology, Vol. 33, No. 6, pp. 590-596. https://doi.org/10.26748/KSOE.2019.066
  16. Koc, C.K. (1995). "Analysis of sliding window techniques for exponentiation." Computers & Mathematics with Applications, Vol. 30, No. 10, pp. 17-24. https://doi.org/10.1016/0898-1221(95)00153-P
  17. Lee, G.H., Ryu, Y.U., and Park, J.S. (2020). "Investigation and analysis of causes of flood damage in the Yeongsan River and Seomjin River basins in August 2020." Water for Future, Vol. 53, No. 11, pp. 21-48.
  18. Lee, M., You, Y., Kim, S., Kim, K., and Kim, H. (2018). "Decomposition of water level time series of a tidal river into tide, wave and rainfall-runoff components." Water, Vol. 10, No. 11, pp. 1568. https://doi.org/10.3390/w10111568
  19. Olah, C. (2015). Understanding lstm networks, Accessed on August, 2011, .
  20. Pan, M., Zhou, H., Cao, J., Liu, Y., Hao, J., Li, S., and Chen, C.H. (2020). "Water level prediction model based on GRU and CNN." Ieee Access, Vol. 8, pp. 60090-60100. https://doi.org/10.1109/access.2020.2982433
  21. Seo, Y., Choi, E., and Yeo, W. (2017). "Reservoir water level forecasting using machine learning models." Journal of the Korean Society of Agricultural Engineers, Vol. 59, No. 3, pp. 97-110. https://doi.org/10.5389/KSAE.2017.59.3.097
  22. Yoo, H.J., Lee, S.O., Choi, S.H., and Park, M.H. (2019). "A study on the data driven neural network model for the prediction of time series data: Application of water surface elevation forecasting in Hangang River bridge." Korean Society of Disaster & Security, Vol. 12, No. 2, pp. 73-82.