Journal of Korea Water Resources Association (한국수자원학회논문집)

Korea Water Resources Association (한국수자원학회)
권호 표지
DOI QR코드

DOI QR Code

Case study on flood water level prediction accuracy of LSTM model according to condition of reference hydrological station combination

참조 수문관측소 구성 조건에 따른 LSTM 모형 홍수위예측 정확도 검토 사례 연구

  • Lee, Seungho (Department of Hydro Science and Engineering Research, Korea Institute of Civil Engineering and Building Technology) ;
  • Kim, Sooyoung (Department of Hydro Science and Engineering Research, Korea Institute of Civil Engineering and Building Technology) ;
  • Jung, Jaewon (Department of Hydro Science and Engineering Research, Korea Institute of Civil Engineering and Building Technology) ;
  • Yoon, Kwang Seok (Department of Hydro Science and Engineering Research, Korea Institute of Civil Engineering and Building Technology)
  • 이승호 (한국건설기술연구원 수자원하천연구본부) ;
  • 김수영 (한국건설기술연구원 수자원하천연구본부) ;
  • 정재원 (한국건설기술연구원 수자원하천연구본부) ;
  • 윤광석 (한국건설기술연구원 수자원하천연구본부)
  • Received : 2023.11.27
  • Accepted : 2023.12.12
  • Published : 2023.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Due to recent global climate change, the scale of flood damage is increasing as rainfall is concentrated and its intensity increases. Rain on a scale that has not been observed in the past may fall, and long-term rainy seasons that have not been recorded may occur. These damages are also concentrated in ASEAN countries, and many people in ASEAN countries are affected, along with frequent occurrences of flooding due to typhoons and torrential rains. In particular, the Bandung region which is located in the Upper Chitarum River basin in Indonesia has topographical characteristics in the form of a basin, making it very vulnerable to flooding. Accordingly, through the Official Development Assistance (ODA), a flood forecasting and warning system was established for the Upper Citarium River basin in 2017 and is currently in operation. Nevertheless, the Upper Citarium River basin is still exposed to the risk of human and property damage in the event of a flood, so efforts to reduce damage through fast and accurate flood forecasting are continuously needed. Therefore, in this study an artificial intelligence-based river flood water level forecasting model for Dayeu Kolot as a target station was developed by using 10-minute hydrological data from 4 rainfall stations and 1 water level station. Using 10-minute hydrological observation data from 6 stations from January 2017 to January 2021, learning, verification, and testing were performed for lead time such as 0.5, 1, 2, 3, 4, 5 and 6 hour and LSTM was applied as an artificial intelligence algorithm. As a result of the study, good results were shown in model fit and error for all lead times, and as a result of reviewing the prediction accuracy according to the learning dataset conditions, it is expected to be used to build an efficient artificial intelligence-based model as it secures prediction accuracy similar to that of using all observation stations even when there are few reference stations.

최근 전세계적인 기후변화의 영향으로 강우가 집중되고 강우강도가 강해짐에 따라 홍수피해의 규모를 증가시키고 있다. 과거에 관측되지 않았던 규모의 비가 내리기도 하고, 기록되지 않았던 장기간의 장마가 발생하기도 한다. 이러한 피해들은 아세안 국가에도 집중되고 있으며, 태풍 및 집중호우로 인해 침수의 빈번한 발생과 함께 많은 사람들이 영향을 받고 있다. 특히, 인도네시아 찌따룸강 상류 유역에 위치한 반둥 지역은 분지 형태의 지형학적 특성을 가지고 있어서 홍수에 매우 취약한 실정이다. 이에 공적개발원조(ODA)를 통해 2017년에 찌따룸강 상류(Upper Citarum River) 유역에 대하여 홍수예경보시스템을 구축되었고, 현재 운영중에 있다. 그럼에도 불구하고, 찌따룸강 상류 (Upper Citarum River) 지역은 홍수발생시 인명 및 재산피해의 위험에 여전히 노출되어 있어 신속하고 정확한 홍수예경보의 실시를 통해 피해를 경감시키는 노력이 지속적으로 필요한 실정이다. 따라서 본 연구에서는 찌따룸강 상류의 Dayeuh Kolot 지점을 목표관측소로 하고, 강우관측소 4개소와 수위관측소 1개소의 10분 단위 수문자료를 수집하여 인공지능 기반의 하천홍수위예측모형을 개발하였다. 6개 관측소의 2017년 1월부터 2021년 1월까지의 10분 단위 수문관측자료를 활용하여 선행예보시간 0.5, 1, 2, 3, 4, 5, 6시간에 대해서 학습, 검증, 시험을 수행하였으며 인공지능알고리즘으로는 LSTM을 적용하였다. 연구결과 모든 선행예보시간에 대해 모형적합도 및 오차에서 좋은 결과를 나타냈으며, 학습자료 구축조건에 따른 예측정확도를 검토한 결과 참조관측소가 적은 경우에도 모든 관측소를 활용하는 경우와 유사하게 예측정확도를 확보하는 것으로 나타나 효율적인 인공지능 기반 모형 구축에 활용될 수 있을 것으로 기대된다.

Keywords

Acknowledgement

본 연구는 한국건설기술연구원 주요사업(20230289-001)의 지원을 받아 수행되었습니다.

References

  1. Fang, Z., Wang, Y., Peng, L., and Hong, H. (2021). "Predicting flood susceptibility using LSTM neural networks." Journal of Hydrology, Vol. 594, 125734.
  2. 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. https://doi.org/10.9798/KOSHAM.2021.21.3.193
  3. 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. https://doi.org/10.3741/JKWRA.2018.51.12.1207
  4. Kim, D., Lee, K., Hwang-Bo, J.G., Kim, H.S, 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. https://doi.org/10.9798/KOSHAM.2022.22.4.145
  5. Kim, D., Park, J., Han, H., Lee, H., Kim, H.S., and Kim S. (2023). "Application of AI-based models for flood water level forecasting and flood risk classification." KSCE Journal of Civil Engineering, Vol. 27, No. 7, pp. 3163-3174. https://doi.org/10.1007/s12205-023-2175-5
  6. Kim, S., Kim, H-J, and Yoon, K.S. (2021). "Development of artificial intelligence-based river flood level prediction model capable of independent self-warning." Journal of Korea Water Resources Association, Vol. 54, No. 12, pp.1285-1294. https://doi.org/10.3741/JKWRA.2021.54.12.1285
  7. Korea International Cooperation Agency (KOICA) (2017). Development of the FFWS of the CRB in Indonesia: Final result report.
  8. Krause, P., Boyle, D.P., and Base, F. (2005). "Comparison of different efficiency criteria for hydrological model assessment." Advances in Geosciences, Vol. 5, pp. 89-97. https://doi.org/10.5194/adgeo-5-89-2005
  9. Le, X.H., Ho, H.V., Lee, G., and Jung, S. (2019). "Application of long short-term memory (LSTM) neural network for flood forecasting." Water, Vol. 11, No. 7, 1387.
  10. Lee, M., Kim, J., Yoo, Y., Kim, HS., 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. S-1, pp. 1061-1069.
  11. Moriasi, D.N., Gitau, M.W., Pai, N., and Daggupati, P. (2015). "Hydrologic and water quality models: Performance measures and evaluation criteria." Transactions of the ASABE, Vol. 58, No. 6, pp. 1763-1785. https://doi.org/10.13031/trans.58.10715
  12. Olah, C. (2015). Understanding lstm networks, accessed 23 November 2021, .
  13. Park, S.H., and Kim, H.J. (2020). "Design of artificial intelligence water level prediction system for prediction of river flood." Journal of the Korea Institute of Information and Communication Engineering, Vol. 24, No. 2, pp. 198-203. https://doi.org/10.6109/JKIICE.2020.24.2.198
  14. Tran, Q.K., and Song, S.K. (2017). "Water level forecasting based on deep learning: A use case of Trinity River-Texas-The United States." Journal of KIISE, Vol. 44, No. 6, pp. 607-612. https://doi.org/10.5626/JOK.2017.44.6.607
  15. 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." Journal of Korean Society of Disaster & Security, Vol. 12, No. 2, pp. 73-82. https://doi.org/10.21729/KSDS.2019.12.2.73