한국수자원학회논문집 (Journal of Korea Water Resources Association)

  • 제57권7호
  • /
  • Pages.471-479
  • /
  • 2024
  • /
  • 2799-8746(pISSN)
  • /
  • 2799-8754(eISSN)
한국수자원학회 (Korea Water Resources Association)
권호 표지
DOI QR코드

DOI QR Code

고해상도 강우자료와 딥러닝 알고리즘을 활용한 수위 변동성 예측

Utilizing deep learning algorithm and high-resolution precipitation product to predict water level variability

  • 한희찬 (조선대학교 토목공학과) ;
  • 강나래 (한국건설기술연구원 수자원하천연구본부) ;
  • 윤정수 (한국건설기술연구원 수자원하천연구본부) ;
  • 황석환 (한국건설기술연구원 수자원하천연구본부)
  • Han, Heechan (Department of Civil Engineering, Chosun University) ;
  • Kang, Narae (Department of Hydro Science and Engineering Research, Korea Institute of Civil Engineering and Building Technology) ;
  • Yoon, Jungsoo (Department of Hydro Science and Engineering Research, Korea Institute of Civil Engineering and Building Technology) ;
  • Hwang, Seokhwan (Department of Hydro Science and Engineering Research, Korea Institute of Civil Engineering and Building Technology)
  • 투고 : 2024.04.04
  • 심사 : 2024.06.25
  • 발행 : 2024.07.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

기후변화로 인한 집중호우의 발생으로 홍수 피해가 심각해지고 있다. 하천의 수위 변동성을 예측하고 신속한 홍수 예·경보를 위해 물리적 기반의 수문 모형이 활용됐다. 최근에는 수문 데이터 간의 비선형적인 관계를 기반으로 머신러닝, 딥러닝 알고리즘을 활용한 수문 모의가 주목받고 있다. 본 연구에서는 Long Short-Term Memory (LSTM) 알고리즘을 활용하여 섬진강 수계의 하천 수위를 예측하고자 한다. 또한 Climate Prediction Center morphing method (CMORPH) 기반의 격자형 강우 자료를 알고리즘의 입력자료로 적용하여 지상 데이터의 한계를 보완하고자 한다. CMORPH 데이터와 LSTM 알고리즘을 결합한 모형의 수위 예측 결과는 평균 CC가 0.98, RMSE는 0.07 m, 그리고 NSE는 0.97로 나타났다. 향후 딥러닝과 원격자료를 활용하여 수위 예측을 수행한다면 지상 관측 데이터의 단점을 보완하고, 신뢰도 높은 예측 결과를 얻을 수 있을 것으로 기대되는 바이다.

Flood damage is becoming more serious due to the heavy rainfall caused by climate change. Physically based hydrological models have been utilized to predict stream water level variability and provide flood forecasting. Recently, hydrological simulations using machine learning and deep learning algorithms based on nonlinear relationships between hydrological data have been getting attention. In this study, the Long Short-Term Memory (LSTM) algorithm is used to predict the water level of the Seomjin River watershed. In addition, Climate Prediction Center morphing method (CMORPH)-based gridded precipitation data is applied as input data for the algorithm to overcome for the limitations of ground data. The water level prediction results of the LSTM algorithm coupling with the CMORPH data showed that the mean CC was 0.98, RMSE was 0.07 m, and NSE was 0.97. It is expected that deep learning and remote data can be used together to overcome for the shortcomings of ground observation data and to obtain reliable prediction results.

키워드

과제정보

이 논문은 행정안전부 기후변화대응 AI 기반 풍수해 위험도 예측기술개발 사업의 지원을 받아 수행된 연구임(2022-MOIS61-002).

참고문헌

  1. Arora, V.K., and Boer, G.J. (2001). "Effects of simulated climate change on the hydrology of major river basins." Journal of Geophysical Research: Atmospheres, Vol. 106, No. D4, pp. 3335-3348.
  2. Assem, H., Ghariba, S., Makrai, G., Johnston, P., Gill, L., and Pilla, F. (2017). "Urban water flow and water level prediction based on deep learning." In Machine Learning and Knowledge Discovery in Databases: European Conference, Springer, Skopje, Macedonia, Vol. 10536, pp. 317-329.
  3. Baek, S.S., Pyo, J., and Chun, J.A. (2020). "Prediction of water level and water quality using a CNN-LSTM combined deep learning approach." Water, Vol. 12, No. 12, 3399.
  4. Bitew, M.M., and Gebremichael, M. (2011). "Evaluation of satellite rainfall products through hydrologic simulation in a fully distributed hydrologic model." Water Resources Research, Vol. 47, No. 6. doi: 10.1029/2010WR009917.
  5. Godin, F., Degrave, J., Dambre, J., De Neve, W. (2018). "Dual rectified linear units (DReLUs): A replacement for tanh activation functions in quasi-recurrent neural networks." Pattern Recognition Letters, Vol. 116, pp. 8-14.
  6. Han, H., Abitew, T.A., Park, S., Green, C.H., and Jeong, J. (2023). "Spatiotemporal evaluation of satellite-based precipitation products in the Colorado river basin." Journal of Hydrometeorology, Vol. 24, No. 10, pp. 1739-1754.
  7. Han, H., and Morrison, R.R. (2022). "Improved runoff forecasting performance through error predictions using a deep-learning approach." Journal of Hydrology, Vol. 608, 127653.
  8. Han, H., Choi, C., Kim, J., Morrison, R.R., Jung, J., and Kim, H.S. (2021). "Multiple-depth soil moisture estimates using artificial neural network and long short-term memory models." Water, Vol. 13, No. 18, 2584.
  9. Harris, A., Rahman, S., Hossain, F., Yarborough, L., Bagtzoglou, A. C., and Easson, G. (2007). "Satellite-based flood modeling using TRMM-based rainfall products." Sensors, Vol. 7, No. 12, pp. 3416-3427.
  10. Hochreiter, S., and Schmidhuber, J. (1997). "Long short-term memory." Neural Computation, Vol. 9, No. 8, pp. 1735-1780.
  11. Hu, C., Wu, Q., Li, H., Jian, S., Li, N., and Lou, Z. (2018). "Deep learning with a long short-term memory networks approach for rainfall-runoff simulation." Water, Vol. 10, No. 11, 1543. doi: 10.3390/w10111543.
  12. Huffman, G.J., Bolvin, D.T., Nelkin, E.J., Wolff, D.B., Adler, R.F., Gu, G., Hong, Y., Bowman, K.P., and Stocker, E.F. (2007). "The TRMM multisatellite precipitation analysis (TMPA): Quasi-global, multiyear, combined-sensor precipitation estimates at fine scales." Journal of Hydrometeorology, Vol. 8, No. 1, pp. 38-55.
  13. Joyce, R.J., Janowiak, J.E., Arkin, P.A., and Xie, P. (2004). "CMORPH: A method that produces global precipitation estimates from passive microwave and infrared data at high spatial and temporal resolution." Journal of Hydrometeorology, Vol. 5, No. 3, pp. 487-503.
  14. Kay, A.L., Rudd, A.C., Fry, M., Nash, G., and Allen, S. (2021). "Climate change impacts on peak river flows: Combining national-scale hydrological modelling and probabilistic projections." Climate Risk Management, Vol. 31, 100263.
  15. Kim, D., Han, H., Wang, W. and Kim, H. S. (2022). "Improvement of deep learning models for river water level prediction using complex network method." Water, Vol. 14, 466.
  16. Kim, J., and Han, H. (2021). "Evaluation of the CMORPH high-resolution precipitation product for hydrological applications over South Korea." Atmospheric Research, Vol. 258, 105650.
  17. Le, M.H., Lakshmi, V., Bolten, J., and Du Bui, D. (2020). "Adequacy of satellite-derived precipitation estimate for hydrological modeling in Vietnam basins." Journal of Hydrology, Vol. 586, 124820.
  18. Lee, M., Kim, J., Yoo, Y., Kim, H.S., Kim, S.E., and Kim, S. (2021). "Water level prediction in Taehwa River basin using deep learning model based on DNN and LSTM." Journal of Korea Water Resources Association, Vol. 54, No. spc1, pp. 1061-1069.
  19. Li, G., Liu, Z., Zhang, J., Han, H., and Shu, Z. (2024). "Bayesian model averaging by combining deep learning models to improve lake water level prediction." Science of The Total Environment, Vol. 906, 167718.
  20. Li, W., Gao, X., Hao, Z. and Sun, R. (2022). "Using deep learning for precipitation forecasting based on spatio-temporal information: A case study." Climate Dynamics, Vol. 58, pp. 443-457.
  21. Park, K., Jung, Y., Seong, Y., and Lee, S. (2022). "Development of deep learning models to improve the accuracy of water levels time series prediction through multivariate hydrological data." Water, Vol. 14, No. 3, 469.
  22. Schreider, S.Y., Smith, D.I., and Jakeman, A.J. (2000). "Climate change impacts on urban flooding." Climatic Change, Vol. 47, pp. 91-115.
  23. Sorooshian, S., Hsu, K.L., Gao, X., Gupta, H.V., Imam, B., and Braithwaite, D. (2000). "Evaluation of PERSIANN system satellite-based estimates of tropical rainfall." Bulletin of the American Meteorological Society, Vol. 81, No. 9, pp. 2035-2046.
  24. Szandala, T. (2021). Review and comparison of commonly used activation functions for deep neural networks. Bio-inspired Neurocomputing, Springer, Singapore, pp. 203-224.
  25. Tarekegn, N., Abate, B., Muluneh, A., and Dile, Y. (2022). "Modeling the impact of climate change on the hydrology of Andasa watershed." Modeling Earth Systems and Environment, Vol. 8, No. 1, pp. 103-119.
  26. Tessema, N., Kebede, A., and Yadeta, D. (2021). "Modelling the effects of climate change on streamflow using climate and hydrological models: the case of the Kesem sub-basin of the Awash River basin, Ethiopia." International Journal of River Basin Management, Vol. 19, No. 4, pp. 469-480.
  27. Tobin, K.J., and Bennett, M.E. (2010). "Adjusting satellite precipitation data to facilitate hydrologic modeling." Journal of Hydrometeorology, Vol. 11, No. 4, pp. 966-978.
  28. Velpuri, N.M., Senay, G.B., and Asante, K.O. (2012). "A multisource satellite data approach for modelling Lake Turkana water level: calibration and validation using satellite altimetry data." Hydrology and Earth System Sciences, Vol. 16, No. 1, pp. 1-18.
  29. Wang, Q., and Wang, S. (2020). "Machine learning-based water level prediction in Lake Erie." Water, Vol. 12, No. 10, 2654.
  30. Xiang, Z., Yan, J., and Demir, I. (2020). "A rainfall-runoff model with LSTM-based sequence-to-sequence learning." Water Resources Research, Vol. 56, No. 1, e2019WR025326.
  31. Xie, P., Joyce, R., Wu, S., Yoo, S. H., Yarosh, Y., Sun, F. Lin, R. (2017). "Reprocessed, bias-corrected CMORPH global high-resolution precipitation estimates from 1998." Journal of Hydrometeorology, Vol. 18, pp. 1617-1641.
  32. Xie, Z., Liu, Q. and Cao, Y. (2021). "Hybrid deep learning modeling for water level prediction in Yangtze River." Intelligent Automation & Soft Computing, Vol. 28, pp. 153-166.