DOI QR코드

DOI QR Code

A study on the derivation and evaluation of flow duration curve (FDC) using deep learning with a long short-term memory (LSTM) networks and soil water assessment tool (SWAT)

LSTM Networks 딥러닝 기법과 SWAT을 이용한 유량지속곡선 도출 및 평가

  • Choi, Jung-Ryel (Department of Urban Environmental Disaster Management, Kangwon National University) ;
  • An, Sung-Wook (Department of Urban Environmental Disaster Management, Kangwon National University) ;
  • Choi, Jin-Young (Department of Environment Certification & Inspection, Korea Environment Corporation) ;
  • Kim, Byung-Sik (Department of Urban Environmental Disaster Management, Kangwon National University)
  • 최정렬 (강원대학교 도시환경재난관리전공) ;
  • 안성욱 (강원대학교 도시환경재난관리전공) ;
  • 최진영 (한국환경공단 환경인증검사처) ;
  • 김병식 (강원대학교 도시환경재난관리전공)
  • Received : 2021.09.27
  • Accepted : 2021.11.05
  • Published : 2021.12.31

Abstract

Climate change brought on by global warming increased the frequency of flood and drought on the Korean Peninsula, along with the casualties and physical damage resulting therefrom. Preparation and response to these water disasters requires national-level planning for water resource management. In addition, watershed-level management of water resources requires flow duration curves (FDC) derived from continuous data based on long-term observations. Traditionally, in water resource studies, physical rainfall-runoff models are widely used to generate duration curves. However, a number of recent studies explored the use of data-based deep learning techniques for runoff prediction. Physical models produce hydraulically and hydrologically reliable results. However, these models require a high level of understanding and may also take longer to operate. On the other hand, data-based deep-learning techniques offer the benefit if less input data requirement and shorter operation time. However, the relationship between input and output data is processed in a black box, making it impossible to consider hydraulic and hydrological characteristics. This study chose one from each category. For the physical model, this study calculated long-term data without missing data using parameter calibration of the Soil Water Assessment Tool (SWAT), a physical model tested for its applicability in Korea and other countries. The data was used as training data for the Long Short-Term Memory (LSTM) data-based deep learning technique. An anlysis of the time-series data fond that, during the calibration period (2017-18), the Nash-Sutcliffe Efficiency (NSE) and the determinanation coefficient for fit comparison were high at 0.04 and 0.03, respectively, indicating that the SWAT results are superior to the LSTM results. In addition, the annual time-series data from the models were sorted in the descending order, and the resulting flow duration curves were compared with the duration curves based on the observed flow, and the NSE for the SWAT and the LSTM models were 0.95 and 0.91, respectively, and the determination coefficients were 0.96 and 0.92, respectively. The findings indicate that both models yield good performance. Even though the LSTM requires improved simulation accuracy in the low flow sections, the LSTM appears to be widely applicable to calculating flow duration curves for large basins that require longer time for model development and operation due to vast data input, and non-measured basins with insufficient input data.

지구온난화로 인해 발생한 기후변화는 한반도의 홍수, 가뭄 등의 발생빈도를 증가시켰으며, 이로 인해 인적, 물적 피해가 증가한 것으로 나타났다. 수재해 대비 및 대응을 위해서는 국가 차원의 수자원 관리 계획 수립이 필요하며, 유역 단위 수자원 관리를 위해서는 장기간 관측된 유량 자료를 이용하여 도출된 유량지속곡선이 필요하다. 전통적으로 수자원 분야에서 유량지속곡선을 도출하기 위하여 물리적 기반의 강우-유출 모형이 많이 사용되고 있으며, 최근에는 데이터 기반의 딥러닝 기법을 이용한 유출량 예측 기법에 관한 연구가 진행된 바 있다. 물리적 기반의 모형은 수문학적으로 신뢰도 높은 결과를 도출할 수 있으나, 사용자의 높은 이해도가 요구되며, 모형 구동 시간이 오래 걸릴 수 있는 단점이 있다. 데이터 기반의 딥러닝 기법의 경우 입력 자료가 간단하며, 모형 구동 시간이 비교적 짧으나 입력 및 출력자료 간의 관계가 블랙박스로 처리되어 수리·수문학적 특성을 반영할 수 없는 단점이 있다. 본 연구에서는 물리적 기반 모형으로 국내외에서 적용성이 검증된 Soil Water Assessment Tool (SWAT)의 매개변수 보정(Calibration)을 통해 장기간의 결측치 없는 데이터를 산출하고, 이를 데이터 기반 딥러닝 기법인 Long Short-term Memory (LSTM)의 훈련(Training) 데이터로 활용하였다. 시계열 데이터 분석 결과 검·보정 전체 기간('07-'18) 동안 Nash-Sutcliffe Efficiency (NSE)와 적합도 비교를 위한 결정계수는 각각 0.04, 0.03 높게 도출되어 모형에서 도출된 SWAT의 결과가 LSTM보다 전반적으로 우수한 것으로 나타났다. 또한, 모형에서 도출된 연도별 시계열 자료를 내림차순하여 산정된 유량지속곡선과 관측유량 기반의 유량지속곡선과 비교한 결과 NSE는 SWAT과 LSTM 각각 0.95, 0.91로 나타났으며, 결정계수는 0.96, 0.92로 두 모형 모두 우수한 성능을 보였다. LSTM 모형의 경우 저유량 부분 모의의 정확도 개선이 필요하나, 방대한 입력 자료로 인해 모형 구축 및 구동 시간이 오래 걸리는 대유역과 입력 자료가 부족한 미계측 유역의 유량지속곡선 산정 등에 활용성이 높을 것으로 판단된다.

Keywords

Acknowledgement

본 연구는 행정안전부 극한재난대응기반기술개발 사업의 연구비 지원(2019-MOIS31-010)에 의해 수행되었습니다.

References

  1. Arnold, J.G., Allen, P.M., and Bernhardt, G. (1993). "A comprehensive surface-groundwater flow Model." Journal of Hydrology, Vol. 142, No. 1-4, pp. 47-69. doi: 10.1016/0022-1694(93)90004-S
  2. Chen, X., Li, F.W., Li, J.Z., and Feng, P. (2019). "Three-dimensional identification of hydrological drought and multivariate drought risk probability assessment in the Luanhe River basin, China." Theoretical and Applied Climatology, Vol. 137, pp. 3055-3076. doi: 10.1007/s00704-019-02780-5
  3. Choi, J.R., Chung, I.M., Jeung, S.J., Choo, K.S., Oh, C.H., and Kim, B.S. (2021a). "Development and verification of the available number of water intake days in ungauged local water source using the SWAT model and flow recession." Water, Vol. 13, No. 11, 1511. doi: 10.3390/w13111511
  4. Choi, J.R., Yoon, H.C., Won, C.H., Lee, B.H., and Kim, B.S. (2021b). "A study on the estimation and evaluation of ungauged reservoir inflow for local government's agricultural drought forecasting and warning." Journal of the Korea Water Resources Association, Vol. 54, No. 6, pp. 395-405. doi: 10.3741/JKWRA.2021.54.6.395
  5. Han, H.C., Choi, C.H., Jung, J.W., and Kim, H.S. (2021). "Application of sequence to sequence learning based LSTM model (LSTM-s2s) for forecasting dam inflow." Journal of the Korea Water Resources Association, Vol. 54, No. 3, pp. 157-166. doi: 10.3741/JKWRA.2021.54.3.157
  6. Han, J.H., Ryu, T.S., Lim, K.J., and Jung, Y.H. (2016). "A review of baseflow analysis techniques of watershed-scale runoff models." Journal of the Korean Society of Agricultural Engineers, Vol. 58, No. 4, pp. 75-83. doi: 10.5389/KSAE.2016.58.4.075
  7. Hochreiter, S., and Schmidhuber, J. (1997). "Long short-term memory." Neural Computation, Vol. 9, No. 8, pp. 1735-1780. doi: 10.1162/neco.1997.9.8.1735
  8. Hoyos, N., Correa-Metrio, A., Jepsen, S.M., Wemple, B., Valencia, S., Marsik, M., Doria, R., Escobar, J., Restrepo, J.C., and Velez, M.I. (2019). "Modeling streamflow response to persistent drought in a coastal tropical mountainous watershed, Sierra Nevada De Santa Marta, Colombia." Water, Vol. 11, No. 1, p. 94. doi: 10.3390/w11010094
  9. 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
  10. Jung, J.W., Mo, H.L., Lee, J.H., Yoo, Y.H., 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. doi: 0.9798/KOSHAM.2021.21.3.193
  11. Jung, S.H., Cho, H.S., Kim, J.Y., and Lee, G.H. (2018). "Prediction of water level in a tidal river using a deep-learning based LSTM model" Journal of the Korea Water Resources Association, Vol. 51, No. 12, pp. 1207-1216. doi: 10.3741/JKWRA.2018.51.12.1207
  12. Khalilian, S., and Shahvari, N. (2019). "A SWAT evaluation of the effects of climate change on renewable water resources in salt lake sub-basin, Iran." AgriEngineering, Vol. 1, No. 1, pp. 44-57. doi: 10.3390/agriengineering1010004
  13. Kim, C.G., and Kim, N.W. (2012). "Comparison of natural flow estimates for the han river basin using TANK." Journal of the Korea Water Resources Association, Vol. 45, No. 3, pp. 301-316. doi: 10.3741/JKWRA.2012.45.3.301
  14. Kim, D.H., Hwang, S.W., Jang, T.I., and So, H.C. (2018). "Assessing climate change impacts on hydrology and water quality using SWAT model in the Mankyung watershed." Journal of the Korean Society of Agricultural Engineers, Vol. 60, No. 6, pp. 83-96. doi: 10.5389/KSAE.2018.60.6.083
  15. Kim, D.R., and Kim, S.J. (2017). "A study on parameter estimation for SWAT calibration considering streamflow of long-term drought periods." Journal of the Korean Society of Agricultural Engineers, Vol. 59, No. 2, pp. 19-27. doi: 10.5389/KSAE.2017.59.2.019
  16. Kim, E.D., Ko, S.K., and Lee, B.T. (2021). "Technical trends of time-series data imputation." ETRI Electronics and Telecommunications Trends. doi: /0.22648/ETRI.2021.J.360414
  17. Korea Research Institute for Human Settlements (KRIHS) (2020). A proposal to establish the reference discharges for rational river management.
  18. 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. doi: 10.5194/hess-22-6005-2018
  19. Le, M.H., Lakshmi, V., Bolten, J., and Bui, D.D. (2020). "Adequacy of satellite-derived precipitation estimate for hydrological modeling in Vietnam basins." Journal of Hydrology, Vol. 586. doi: 10.1016/j.jhydrol.2020.124820
  20. Lee, D.E., Lee, G.H., Kim, S.W., and Jung, S.H. (2020). "Future runoff analysis in the mekong river basin under a climate change scenario using deep learning." Water, Vol. 12, No. 6. doi: 10.3390/w12061556
  21. Lee, G.H., and Jung, S.H. (2018). "Comparison of physics-based and data-driven models for streamflow simulation of the mekong river." Journal of the Korea Water Resources Association, Vol. 51, No. 6, pp. 503-514. doi: 10.3741/JKWRA.2018.51.6.503
  22. Leta, O.T., and Bauwens, W. (2018). "Assessment of the impact of climate change on daily extreme peak and low flows of Zenne Basin in Belgium." Hydrology, Vol. 5, No. 3, pp. 38. doi: 10.3390/hydrology5030038
  23. Mao, G., Wang, M., Liu, J., Wang, Z., Wang, K., Meng, Y., and Zhong, R. (2021). "Comprehensive comparison of artificial neural networks and long short-term memory networks for rainfall-runoff simulation." Physics and Chemistry of the Earth, Vol. 123, No. 1, 103026. doi: 10.1016/j.pce.2021.103026
  24. Ministry of Land, Infrastructure and Transportation of Korea (MOLIT) (2000). The long-term comprehensive water resource plan (Water Vision 2020).
  25. Mok, J.Y., Choi, J.H., and Moon, Y.I. (2020). "Prediction of multipurpose dam inflow using deep learning." Journal of the Korea Water Resources Association, Vol. 53, No. 2, pp. 97-105. doi: 10.3741/JKWRA.2020.53.2.97
  26. Nash, J.E., and Sutcliffe, J.V. (1970) "River flow forecasting through conceptual models part I - A discussion of principles." Journal of Hydrology, Vol. 10, No. 3, pp. 282-290. doi: 10.1016/0022-1694(70)90255-6
  27. Ouma, Y.O., Cheruyot, R., and Wachera, A.N. (2021). "Rainfall and runoff time-series trend analysis using LSTM recurrent neural network and wavelet neural network with satellite-based meteorological data: case study of Nzoia hydrologic basin." Complex & Intelligent Systmes, doi: 10.1007/s40747-021-00365-2
  28. Park, J.K. (2009). "Application of SWAT model for daily streamflow at the Kum River." Journal of the Korea Society of Environmental Administration, Vol. 15, No. 1, pp. 29-36.
  29. Sehgal, V., and Sridhar, V. (2018). "Effect of hydroclimatological teleconnections on the watershed-scale drought predictability in the southeastern United States." International Journal of Climatology, Vol. 38, No. S1, pp. e1139-e1157. doi: 10.1002/joc.5439
  30. Shim, K.H., Kim, G.H., Im, T.H., Kim, Y.S., and Kim, S.M. (2021). "A study on the water quality improvement of major tributaries in Seoul, applying watershed evaluation techniques." Journal of Korean Society on Water Environment, Vol. 37, No. 1, pp. 32-46. doi: 10.15681/KSWE.2021.37.1.32
  31. Visakh, S., Raju, P.V., Kulkarni, S.S., and Diwakar, P.G. (2019). "Inter-comparison of water balance components of river basins draining into selected delta districts of Eastern India." The Science of the Total Environment, Vol. 654, pp. 1258-1269. doi: 10.1016/j.scitotenv.2018.11.162
  32. Xu, W., Jiang, Y., Jhang, X., Li, Y., Zhang, R., and Fu, G. (2020). "Using long short-term memory networks for river flow prediction." Hydrology Research, Vol. 51, No. 6, pp. 1358-1376. doi: 10.2166/nh.2020.026
  33. Yang, M.H., Nam, W.H., Kim, H.J., Kim, T.G., Shin, A.K., and Kang, M.S. (2021). "Anomaly detection in reservoir water level data using the LSTM model based on deep learning." Journal of the Korean Society of Hazard Mitigation, Vol. 21, No. 1, pp. 71-81. doi: 10.9798/KOSHAM.2021.21.1.71