Journal of Korea Water Resources Association (한국수자원학회논문집)

Korea Water Resources Association (한국수자원학회)
권호 표지
DOI QR코드

DOI QR Code

Estimation of regional flow duration curve applicable to ungauged areas using machine learning technique

머신러닝 기법을 이용한 미계측 유역에 적용 가능한 지역화 유황곡선 산정

  • Jeung, Se Jin (Kangwon Institute of Inclusive Technology, Kangwon National University) ;
  • Lee, Seung Pil (H.L.Construction co., Ltd) ;
  • Kim, Byung Sik (Department of Urban Environment & Disaster Management, Kangwon National University)
  • 정세진 (강원종합기술연구원 토양기후환경연구센터) ;
  • 이승필 (H.L.건설) ;
  • 김병식 (강원대학교 방재전문대학원)
  • Received : 2021.10.12
  • Accepted : 2021.11.24
  • Published : 2021.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Low flow affects various fields such as river water supply management and planning, and irrigation water. A sufficient period of flow data is required to calculate the Flow Duration Curve. However, in order to calculate the Flow Duration Curve, it is essential to secure flow data for more than 30 years. However, in the case of rivers below the national river unit, there is no long-term flow data or there are observed data missing for a certain period in the middle, so there is a limit to calculating the Flow Duration Curve for each river. In the past, statistical-based methods such as Multiple Regression Analysis and ARIMA models were used to predict sulfur in the unmeasured watershed, but recently, the demand for machine learning and deep learning models is increasing. Therefore, in this study, we present the DNN technique, which is a machine learning technique that fits the latest paradigm. The DNN technique is a method that compensates for the shortcomings of the ANN technique, such as difficult to find optimal parameter values in the learning process and slow learning time. Therefore, in this study, the Flow Duration Curve applicable to the unmeasured watershed is calculated using the DNN model. First, the factors affecting the Flow Duration Curve were collected and statistically significant variables were selected through multicollinearity analysis between the factors, and input data were built into the machine learning model. The effectiveness of machine learning techniques was reviewed through statistical verification.

Low flow는 하천수의 공급관리 및 계획, 관개용수 등 다양한 분야에 영향을 미친다. 이러한 유황곡선을 산정하기 위해서는 30년 이상의 충분한 기간의 유량자료의 확보가 필수적이다. 하지만 국가하천 단위 이하의 하천의 경우 장기간의 유량자료가 없거나 중간에 일정기간 동안 결측된 관측소가 있어 하천별 유황 곡선을 산정하기에 한계가 있다. 이에 과거에는 미계측 유역의 유황을 예측하기 위해 다중회귀분석(Multiple Regression Analysis), ARIMA 모형 등 통계학적 기반의 기법들을 사용하였지만, 최근에는 머신러닝, 딥러닝 모형의 수요가 증가하고 있다. 이에 본 연구에서는 최신 패러다임에 맞는 머신러닝 기법인 DNN기법을 제시한다. DNN기법은 ANN기법의 단점인 학습과정에서 최적 매개변수 값을 찾기 어렵고, 학습시간이 느린 단점을 보완한 방법이다. 따라서 본연구에서는 DNN 모형을 이용하여 미계측 유역에 적용 가능한 유황곡선을 산정하고자 한다. 먼저, 유황곡선에 영향을 미치는 인자들을 수집하고 인자들 간의 다중공선성 분석을 통해 통계적으로 유의한 변수를 선정하여, 머신러닝 모형에 입력자료를 구축하였다. 통계적 검증을 통해 머신러닝 기법의 효용성을 검토하였다.

Keywords

Acknowledgement

본 연구는 행정안전부 지능형 상황관리 기술 개발사업의 연구비지원(과제번호 2021-MOIS37-001)에 의해 수행되었습니다.

References

  1. Bengio, Y., Courville, A., and Vincent, P. (2013). "Representation learning: A review and new perspectives." Cornell University, special issue Learning Deep Architectures, Accessed 24 June, .
  2. Byeon, S.J., Lee, S.H., Choi, G.W., and Jung, J.G. (2014). "Use ofgauged water level and precipitation data to predict short termwater level changes." Korean Review of Crisis and Emergency Management, Vol.10, pp. 247-264.
  3. Castillo, J.M.M., Cspedes, J.M.S., and Cuchango, H.E.E. (2018). "Water level prediction using artificial neural network model." International Journal of Applied Engineering Research, Vol. 13, pp. 14378-14381.
  4. Choi, S.Y., Han, K.Y., and Kim, B.H. (2012). "Comparison ofdifferent multiple linear regression models for real-time floodstage forecasting." Journal of the Korean Society of Civil Engineers B, Vol. 32, No. 1, pp. 9-20.
  5. Jeung, S.J. (2019). Impact assessments of climate and hydrologicalcycle changes in North Korea based on RCP climate changescenarios. Ph.D dissertation, Kangwon National University.
  6. Jun, H.D., and Lee, J.H. (2013). "A methodology for floodforecasting and warning based on the characteristic of observedwater levels between up stream and downstream." Journal of the Korean Society of Hazard Mitigation, Vol. 13, pp. 367-374. https://doi.org/10.9798/KOSHAM.2013.13.6.367
  7. Kim, D.H., Kim, J.W., Kwak, J., and Kim, J., and Kim, H.S. (2020). "Development of water level prediction models using deep-neural network in mountain wetlands." Journal of Wetlands Research, Vol.22, No. 2, pp. 106-112. https://doi.org/10.17663/JWR.2020.22.2.106
  8. Lee, T.H. (2016). Development of regional regression model forestimating mean low flow in ungauged basins. Ph.D dissertation, Ajou University.
  9. Lim, G.G. (2020). A study on estimation of lowflow indices inungauged basin using multiple regression. Master's thesis, Kangwon National University.
  10. Matsumoto, W., Hagiwara, M., Boufounos, P., Fukushima K., Mariyama, T., and Xiongxin, Z. (2016). "A deep neural network architecture usingdimensionality reduction with sparse matrices." ICONIP 2016: Neural Information Processing, International Conference on Neural Information Prcessing, Kyoto, Japan, pp 397-404.
  11. Park, S.D., (2003) "Dimensionless flow duration curve in natural river." Journal of Korea Water Resources Association, Vol. 36, No. 1, pp. 33-44. https://doi.org/10.3741/JKWRA.2003.36.1.033
  12. Rezaeianzadeh, M., Kalin, L., and Anderson, C. (2015). "Wetland-water-level prediction using ANN in conjunction with baseflowrecession analysis." Journal of Hydrologic Engineering, Vol. 22, pp. 1-11.
  13. Rezaeianzadeh, M., Kalin, L., and Hantush, M. (2018). "An integrated approach for modeling wetland water level: Applicationto a headwater wetland in Coastal Alabama, USA." Water, Vol. 10, pp. 1-17. https://doi.org/10.3390/w10020001
  14. Ryoo, K.S., and Chong, K.Y. (2008). "Development of multiple regression models for the prediction of reservoir inflow in the floodseason." 2008 Conference of Korean Society of Civil Engineers, pp. 3500-3503.
  15. Tiwari, M.K., and Chatterjee, C. (2010). "Development of an accurateand reliable hourly flood forecasting model using Wavelet-Bootstrap-ANN (WBANN) hybrid approach." Journal of Hydrology, Vol. 394, pp. 458-470. https://doi.org/10.1016/j.jhydrol.2010.10.001
  16. Yoon, Y.N. (2007). Hydrology, Cheongmungak.