All Issue

2026 Vol.59, Issue 2 Preview Page

Research Article

Development and performance evaluation of LSTM-based multi-points water level forecasting model for downstream region of Yongdam Dam

LSTM을 활용한 용담댐 하류 다중지점 시간 단위 하천 수위 예측 모델 개발과 성능평가

HyunSeok Yanga
,
YoungDon Choib*
,
SungHoon Kimc
,
JunSeok Leed
양 현석a
,
최 영돈b*
,
김 성훈c
,
이 준석d
aResearcher, K-water Research Institute, AI Research Center, Daejeon, Korea
bPrinciple Researcher, K-water Research Institute, AI Research Center, Daejeon, Korea
cHead Researcher, K-water Research Institute, AI Research Center, Daejeon, Korea
dSenior Manager, Keum River Basin Management Department, K-water, Jeonju, Korea
aK-water연구원 AI연구소 위촉연구원
bK-water연구원 AI연구소 책임연구원
cK-water연구원 AI연구소 소장
dK-water 금강유역관리처 수자원운영부 차장
*Corresponding Author
28 February 2026. pp. 173-186
PDF XML Citation
Abstract

This study developed a multi-point water level forecasting model for 21 observation stations located between Yongdam Dam and Daecheong Dam in the Geum River Basin, considering upstream-downstream hydrological connectivity. Rainfall, water level, and dam discharge data were used as input variables, and station-specific forecasting models were constructed using the CUDA-LSTM framework provided by NeuralHydrology. A configuration-based structure was implemented to sequentially propagate upstream predictions to downstream models. Model performance during the development phase was evaluated using the higher NSE value between the validation and testing periods, while the forecasting phase assessed 72-hour water level predictions—consistent with the operational flood forecasting procedure—using both NSE and RMSE. As a result, 18 stations during the development phase and 14 stations during the forecasting phase achieved NSE values of 0.6 or higher, demonstrating stable performance at more than half of the observation stations. These findings confirm the practical applicability of the proposed multi-point water level forecasting model for real-world flood forecasting operations, and its effectiveness was verified.

Keywords
Water level forecasting
Flood forecasting
LSTM
Deep learning

본 연구는 금강 유역 용담댐부터 대청댐까지 21개 수위관측소를 대상으로 상·하류 상관관계를 고려한 다중지점 수위 예측 모델을 구축하였다. 강우, 수위, 댐 방류량을 입력자료로 활용하고 NeuralHydrology의 CUDA-LSTM을 적용하여 관측소별 예측 모델을 개발하였으며, Configuration 파일을 기반으로 상류 예측값이 하류 모델의 입력으로 순차 반영되는 구조를 구현하였다. 모델 개발 단계에서는 Validation과 Testing 중 더 높은 NSE 값을 기준으로 성능을 평가하였고, 예측 단계에서는 실제 홍수예측 절차와 동일하게 72시간 수위 예측을 수행하여 NSE와 RMSE로 예측성능을 검증하였다. 그 결과, 개발 단계에서는 21개 관측소 중 18개 관측소에서, 예측 단계에서는 14개 관측소에서 NSE 0.6 이상의 성능이 확인되었으며, 이를 통해 다중지점 하천수위 예측 모델의 실제 적용 가능성을 검증하였다.

키워드
수위 예측
홍수 예측
LSTM
딥러닝
References
1

Bennett, N.D., Croke, B.F., Guariso, G., Guillaume, J.H., Hamilton, S.H., Jakeman, A.J., Marsili-Libelli, S., Newham, L.T., Norton, J.P., and Perrin, C. et al. (2013). “Characterising performance of environmental models.” Environmental Modelling and Software, Vol. 40, pp. 1-20.

10.1016/j.envsoft.2012.09.011
2

Beven, K. (1989). “Changing ideas in hydrology - the case of physically-based models.” Journal of Hydrology, Vol. 105, No. 1-2, pp. 157-172.

10.1016/0022-1694(89)90101-7
3

Blöschl, G., Bierkens, M.F., Chambel, A., Cudennec, C., Destouni, G., Fiori, A., Kirchner, J.W., McDonnell, J.J., Savenije, H.H., and Sivapalan, M., et al. (2019). “Twenty-three unsolved problems in hydrology (UPH)-a community perspective.” Hydrological Sciences Journal, Vol. 64, No.10, pp. 1141-1158.

10.1080/02626667.2019.1620507
4

Bui, T.C., Le, V.D., and Cha, S.K. (2018). “A deep learning approach for forecasting air pollution in South Korea using LSTM.” arXiv preprint arXiv:1804.07891.

5

Byaruhanga, N., Kibirige, D., Gokool, S., and Mkhonta, G. (2024). “Evolution of flood prediction and forecasting models for flood early warning systems: A scoping review.” Water, Vol. 16, No. 13, 1763.

10.3390/w16131763
6

Choi, Y.D., and Kim, S.H. (2025). “Enhancing dam inflow prediction performance of LSTM using improved inflow fluctuation of the simple water balance method by applying event identification and exponential smoothing.” Crisisonomy, Vol. 21, No. 2, pp. 123-132.

10.14251/crisisonomy.2025.21.2.123
7

Dankers, R., and Feyen, L. (2008). “Climate change impact on flood hazard in Europe: An assessment based on high-resolution climate simulations.” Journal of Geophysical Research: Atmospheres, Vol. 113, No. D19105, doi: 10.1029/2007JD009719.

10.1029/2007JD009719
8

Fang, Z., Wang, Y., Peng, L., and Hong, H. (2021) “Predicting flood susceptibillity using LSTM neural notworks.” Journal of Hydrology, Vol. 594, 125734.

10.1016/j.jhydrol.2020.125734
9

Frame, J.M., Kratzert, F., Klotz, D., Gauch, M., Shalev, G., Gilon, O., Qualls, L.M., Gupta, H.V., and Nearing, G.S. (2022). “Deep learning rainfall-runoff predictions of extreme events.” Hydrology and Earth System Sciences, Vol. 26, No. 13, pp. 3377-3392.

10.5194/hess-26-3377-2022
10

Gauch, M., Kratzert, F., Klotz, D., Nearing, G., Lin, J., and Hochreiter, S. (2021). “Rainfall-runoff prediction at multiple timescales with a single Long Short-Term Memory network.” Hydrology and Earth System Sciences, Vol. 25, No. 4, pp. 2045-2062.

10.5194/hess-25-2045-2021
11

Gharbia, S., Riaz, K., Anton, I., Makrai, G., Gill, L., Creedon, L., McAfee, M., Johnston, P., and Pilla, F. (2022). “Hybrid data-driven models for hydrological simulation and projection on the catchment scale.” Sustainability, Vol. 14, No. 7, 4037.

10.3390/su14074037
12

Gude, V., Corns, S., and Long, S. (2020). “Flood prediction and uncertainty estimation using deep learning.” Water, Vol. 12, No. 3, 884.

10.3390/w12030884
13

Hochreiter, S., and Schmidhuber, J. (1997). “Long short-term memory.” Neural Computation, Vol. 9, No. 8, pp. 1735-1780.

10.1162/neco.1997.9.8.1735
14

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.

10.9798/KOSHAM.2021.21.3.193
15

Kaur, A., Ayyagari, S., Mishra, M., and Thukral, R. (2020). “A literature review on device-to-device data exchange formats for iot applications.” Journal of Intelligent Systems and Computing, Vol. 1, No. 1), pp. 1-10.

10.51682/JISCOM.00101001.2020
16

Kim, D., Lee, K., Hwang-bo, J., Kim, H., and Kim, S. (2022). “Development of the method for flood water level forecasting and flood damage warning using an AI-based model.” Journal of the Korean Society of Hazard Mitigation, Vol. 22, No. 4, pp. 145-156.

10.9798/KOSHAM.2022.22.4.145
17

Kim, S., and Tachikawa, Y. (2018). “Real-time river-stage prediction with artificial neural network based on only upstream observation data.” Japanese Journal of JSCE B1, Vol. 74, No. 4, pp. I_1375-I_1380.

10.2208/jscejhe.74.I_1375
18

Kratzert, F., Gauch, M., Nearing, G., and Klotz, D. (2022). “NeuralHydrology-A Python library for Deep Learning research in hydrology.” Journal of Open Source Software, Vol. 7, No. 71, 4050.

10.21105/joss.04050
19

Kratzert, F., Klotz, D., Brenner, C., Schulz, K., and Herrnegger, M. (2018). “Rainfall-runoff modelling using long short-term memory (LSTM) networks.” Hydrology and Earth System Sciences, Vol. 22, No. 11, pp. 6005-6022.

10.5194/hess-22-6005-2018
20

Kratzert, F., Nearing, G., Addor, N., Erickson, T., Gauch, M., Gilon, O., Gudmundsson, L., Hassidim, A., Klotz, D., and Nevo, S., et al. (2023). “Caravan-A global community dataset for large-sample hydrology.” Scientific Data, Vol. 10, No. 1, 61.

10.1038/s41597-023-01975-w36717577PMC9887008
21

Kwon, D., Min, S.K., Lee, M., Seo, G.Y., and Son, S.W. (2025). “Attribution of 2022 August heavy precipitation event in South Korea using high‐resolution pseudo global warming simulations: Sensitivity to vertical temperature changes.” Geophysical Research Letters, Vol. 52, No. 2, e2024GL112392.

10.1029/2024GL112392
22

Lee, J.G., and Jun, K.S. (2024). “A hybrid river flow forecasting model combining hydrodynamic and machine learning models.” Journal of Korea Water Resources Association, Vol. 57, No. 11, pp. 859-872.

10.3741/JKWRA.2024.57.11.859
23

Lees, T., Reece, S., Kratzert, F., Klotz, D., Gauch, M., De Bruijn, J., Sahu, R.K., Freve, P., Slater, L., and Dadson, S. (2021). “Hydrological concept formation inside long short-term memory (LSTM) networks.” Hydrology and Earth System Sciences Discussions, Vol. 2021, pp. 1-37.

10.5194/hess-2021-566
24

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. Transactions of the ASABE, Vol. 50, No. 3, pp. 885-900.

10.13031/2013.23153
25

Mosavi, A., Ozturk, P., and Chau, K.W. (2018). “Flood prediction using machine learning models: Literature review.” Water, Vol. 10, No. 11, 1536.

10.3390/w10111536
26

Motta, M., de Castro Neto, M., and Sarmento, P. (2021). “A mixed approach for urban flood prediction using Machine Learning and GIS.” International Journal of Disaster Risk Reduction, Vol. 56, 102154.

10.1016/j.ijdrr.2021.102154
27

Mount, N.J., Maier, H.R., Toth, E., Elshorbagy, A., Solomatine, D., Chang, F.J., and Abrahart, R.J. (2016). “Data-driven modelling approaches for socio-hydrology: Opportunities and challenges within the Panta Rhei Science Plan.” Hydrological Sciences Journal, Vol. 61, No. 7, pp. 1192-1208.

10.1080/02626667.2016.1159683
28

Munawar, S., Hammad, A.W., and Waller, S.T. (2022). “Remote sensing methods for flood prediction: A review.” Sensors, Vol. 22, No. 3, 960.

10.3390/s2203096035161706PMC8838435
29

Nearing, G.S., Kratzert, F., Sampson, A.K., Pelissier, C.S., Klotz, D., Frame, J.M., Prieto, C., and Gupta, H.V. (2021). “What role does hydrological science play in the age of machine learning?.” Water Resources Research, Vol. 57, No. 3, e2020WR028091.

10.1029/2020WR028091
30

Nevo, S., Morin, E., Gerzi Rosenthal, A., Metzger, A., Barshai, C., Weitzner, D., Voloshin, D., Kratzert, F., Elidan, G. and Dror, G. et al. (2022). “Flood forecasting with machine learning models in an operational framework.” Hydrology and Earth System Sciences, Vol. 26, No. 15, pp. 4013-4032.

10.5194/hess-26-4013-2022
31

Oh, J., and Bartos, M. (2025). “Flood early warning system with data assimilation enables site-level forecasting of bridge impacts.” npj Natural Hazards, Vol. 2, No. 1, 64.

10.1038/s44304-025-00116-0
32

Oyebode, O.K., Otieno, F.A.O., and Adeyemo, J. (2014). “Review of three data-driven modelling techniques for hydrological modelling and forecasting.” Fresenius Environmental Bulletin, Vol. 23, No. 7, pp. 1443-1454.

33

Sabzipour, B., Arsenault, R., Troin, M., Martel, J.L., Brissette, F., Brunet, F., and Mai, J. (2023). “Comparing a long short-term memory (LSTM) neural network with a physically-based hydrological model for streamflow forecasting over a Canadian catchment.” Journal of Hydrology, Vol. 627, 130380.

10.1016/j.jhydrol.2023.130380
34

Thapa, U., Pati, B.M., Thapa, S., Pyakurel, D., and Shrestha, A. (2024). “Comparative analysis of snowmelt-driven streamflow forecasting using machine learning techniques. Water, Vol. 16, No. 15, 2095.

10.3390/w16152095
35

Wollheim, W.M., Bernal, S., Burns, D.A., Czuba, J.A., Driscoll, C.T., Hansen, A.T., Hensley, R.T., Hosen, J.D., Inamdar, S., Kaushal, S.S., et al. (2018). “River network saturation concept: Factors influencing the balance of biogeochemical supply and demand of river networks.” Biogeochemistry, Vol. 141, No. 3, pp. 503-521.

10.1007/s10533-018-0488-0
36

Yeo, W.K., Seo, Y.M., Lee, S.Y., and Jee, H.K. (2010). “Study on water stage prediction using hybrid model of artificial neural network and genetic algorithm.” Journal of Korea Water Resources Association, Vol. 43, No. 8, pp. 721-731.

10.3741/JKWRA.2010.43.8.721
37

Yoo, C., Lee, J., Chang, K., and Yang, D. (2019). “Sensitivity evaluation of the flash flood warning system introduced to ungauged small mountainous basins in Korea.” Journal of Mountain Science, Vol. 16, No. 5, pp. 971-990.

10.1007/s11629-018-4984-4
Information
  • Publisher :KOREA WATER RESOURECES ASSOCIATION
  • Publisher(Ko) :한국수자원학회
  • Journal Title :Journal of Korea Water Resources Association
  • Journal Title(Ko) :한국수자원학회 논문집
  • Volume : 59
  • No :2
  • Pages :173-186
  • Received Date : 2025-12-10
  • Revised Date : 2025-12-30
  • Accepted Date : 2025-12-31
  • DOI :https://doi.org/10.3741/JKWRA.2026.59.2.173
Journal Informaiton Journal of Korea Water Resources Association Journal of Korea Water Resources Association
Online Submission
Archives
  • scopus
  • KCI-수자원
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close