DOI QR코드

DOI QR Code

Flood prediction in the Namgang Dam basin using a long short-term memory (LSTM) algorithm

  • Lee, Seungsoo (Division for Integrated Water Management, Korea Environmental Institute) ;
  • An, Hyunuk (Department of Agricultural and Rural Engineering, Chungnam National University) ;
  • Hur, Youngteck (K-water Research Institute) ;
  • Kim, Yeonsu (K-water Research Institute) ;
  • Byun, Jisun (Department of Civil Engineering, Chungnam National University)
  • Received : 2020.04.23
  • Accepted : 2020.07.14
  • Published : 2020.09.01

Abstract

Flood prediction is an important issue to prevent damages by flood inundation caused by increasing high-intensity rainfall with climate change. In recent years, machine learning algorithms have been receiving attention in many scientific fields including hydrology, water resources, natural hazards, etc. The performance of a machine learning algorithm was investigated to predict the water elevation of a river in this study. The aim of this study was to develop a new method for securing a large enough lead time for flood defenses by predicting river water elevation using the a long- short-term memory (LSTM) technique. The water elevation data at the Oisong gauging station were selected to evaluate its applicability. The test data were the water elevation data measured by K-water from 15 February 2013 to 26 August 2018, approximately 5 years 6 months, at 1 hour intervals. To investigate the predictability of the data in terms of the data characteristics and the lead time of the prediction data, the data were divided into the same interval data (group-A) and time average data (group-B) set. Next, the predictability was evaluated by constructing a total of 36 cases. Based on the results, group-A had a more stable water elevation prediction skill compared to group-B with a lead time from 1 to 6 h. Thus, the LSTM technique using only measured water elevation data can be used for securing the appropriate lead time for flood defense in a river.

References

  1. Hinton G, Osindero S, Teh Y. 2006. A fast learning algorithm for deep belief nets. Neural computation 18:1527-1554. https://doi.org/10.1162/neco.2006.18.7.1527
  2. Hochreiter S, Schmidhuber J. 1997. Long short-term memory. Neural computation 9:1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  3. Jung S, Cho H, Kim J, Lee G. 2018a. Prediction of water level in a tidal river using a deep-learning based LSTM model. Journal of Korea Water Resources Association 51:1207-1216. [in Korean]
  4. Jung S, Lee D, Lee K. 2018b. Prediction of river water level using deep learning open library. Journal of the Korean Society of Hazard Mitigation 18:1-11. [in Korean] https://doi.org/10.9798/KOSHAM.2018.18.1.1
  5. KMA (Korean Meteorological Administration). 2012. Korean climate change assessment report. KMA, Seoul, Korea.
  6. Lee G, Jung S, Lee D. 2018. Comparison of physics-based and data-driven models for streamflow simulation of the Mekong river. Journal of Korea Water Resources Association 51:503-514. [in Korean]
  7. Lee H, Jung S, Choi E. 2016. A case study on improving performance of machine learning application and learning algorithm. Digital fusion research 14:245-258. [In Korean]
  8. Liang C, Li H, Lei M, Du Q. 2018. Dongting Lake water level forecast and its relationship with the three Gorges Dam based on a long short-term memory network. Water 10:1389. https://doi.org/10.3390/w10101389
  9. Li L, Kim H, Jun K, Choi M. 2016. Estimation of river discharge using satellite-derived flow signals and artificial neural network model: Application to imjin river. Journal of Korea Water Resources Association 49:589-597. [in Korean] https://doi.org/10.3741/JKWRA.2016.49.7.589
  10. Lim H, An H, Kim H, Lee J. 2019. Prediction of pollution loads in the Geum River upstream using the recurrent neural network algorithm. Korean Journal of Agricultural Science 46:67-78. [in Korean]
  11. McCulloch, Warren S, Walter Pitts. 1943. A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics 5:115-133. https://doi.org/10.1007/BF02478259
  12. Olah C. 2015. Understanding lstm networks. GITHUB blog. Accessed in http://colah.github.io/posts/2015-08-Understanding-LSTMs/ on 1 March 2020.
  13. Rumelhar D, Geoffrey E, Ronald J. 1986. Learning representations by back-propagating errors. Nature 323:533. https://doi.org/10.1038/323533a0
  14. Ryu Y, Shin J, Nam W, Heo J. 2012. Forecast of the daily inflow with artificial neural network using wavelet transform at Chungju Dam. Journal of Korea Water Resources Association 45:1321-1330. [in Korean] https://doi.org/10.3741/JKWRA.2012.45.12.1321
  15. Seo Y, Choi E, Yeo W. 2017. Reservoir water level forecasting using machine learning Models. Journal of The Korean Society of Agricultural Engineers 59:97-110. [in Korean]
  16. Sheng W, Lewis A. 2011. Short-term prediction of an artificial neural network in an oscillating water column. International Journal of Offshore and Polar Engineering 21.
  17. Yeo W, Seo Y, Lee S, Jee H. 2010. Study on water stage prediction using hybrid model of artificial neural network and genetic algorithm. Journal of Korea Water Resources Association 43:721-731. [in Korean] https://doi.org/10.3741/JKWRA.2010.43.8.721
  18. Yoon E, Park J, Lee J, Shin H. 2018. Reliability evaluations of time of concentration using artificial neural network model-focusing on Oncheoncheon basin. Journal of Korea Water Resources Association 51:71-80. [in Korean]
  19. Zhang D, Lindholm G, Ratnaweera H. 2018. Use long short-term memory to enhance Internet of Things for combined sewer overflow monitoring. Journal of Hydrology 556:409-418. https://doi.org/10.1016/j.jhydrol.2017.11.018