Ecology and Resilient Infrastructure

Korean Society of Ecology and Infrastructure Engineering (응용생태공학회)
권호 표지
DOI QR코드

DOI QR Code

Preliminary Uncertainty Analysis to Build a Data-Driven Prediction Model for Water Quality in Paldang Dam

팔당댐 유역의 데이터 기반 수질 예측 모형 구성을 위한 사전 불확실성 분석

  • Lee, Eun Jeong (Department of Environmental Engineering, Cheongju University) ;
  • Keum, Ho Jun (Safety Research Division, National Disaster Management Research Institute)
  • 이은정 (청주대학교 환경공학과) ;
  • 금호준 (국립재난안전연구원 안전연구실)
  • Received : 2022.01.22
  • Accepted : 2022.02.11
  • Published : 2022.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

For water quality management, it is necessary to continuously improve the forecasting by analyzing the past water quality, and a Data-driven model is emerging as an alternative. Because the Data-driven model is built based on a wide range of data, it is essential to apply the correlation analysis method for the combination of input variables to obtain more reliable results. In this study, the Gamma Test was applied as a preceding step to build a faster and more accurate data-driven water quality prediction model. First, a physical-based model (HSPF, EFDC) was operated to produce daily water quality reflecting the complexity of the watershed according to various hydrological conditions for Paldang Dam. The Gamma Test was performed on the water quality at the water quality prediction site (Paldangdam2) and major rivers flowing into the Paldang Dam, and the method of selecting the optimal input data combination was presented through the analysis results (Gamma, Gradient, Standar Error, V-Ratio). As a result of the study, the selection criteria for a more efficient combination of input data that can save time by omitting trial and error when building a data-driven model are presented.

수질분야에서 물재해 안정성 강화를 위해 과거와 현재의 수질을 분석하여 예측하는 기술을 지속적으로 고도화하는 것이 필요하며 데이터 기반의 예측 모형이 하나의 대안으로 대두되고 있다. 데이터 기반 모형은 복잡하고 광범위한 자료의 양을 기반으로 구축되기 때문에 보다 신뢰도 있는 결과를 얻을 수 있는 입력자료의 조합을 위한 상관관계 분석방법의 적용이 필수적이다. 본 연구에서는 보다 신속하고 정확한 데이터 기반의 수질 예측 모형을 구성하기 위한 선행단계로 Gamma Test를 적용하였다. 먼저 팔당댐의 다양한 수문조건에 따른 해당 유역의 복잡성과 정밀성이 재현된 과거와 현재의 일단위 수질을 최대한 확보하고자 물리적 기반 모형 (HSPF, EFDC)을 구동하였다. 팔당댐 수질예측지점과 팔당댐으로 유입되는 주요 하천의 수질을 대상으로 Gamma Test를 수행한 후 해석결과 (Gamma, Gradient, Standar Error, V-Ratio)를 통해 최적의 자료조합을 선정하는 방법을 제시하였다. 본 연구의 결과는 데이터 기반 모형 구축 시 반복적인 수행과정을 생략하여 시간을 단축하면서 보다 효율적으로 최적의 입력자료를 선정할 수 있는 정량적인 기준을 보여준다.

Keywords

Acknowledgement

이 논문은 2019년도 정부 (교육부)의 재원으로 한국연구재단 기초연구사업의 지원을 받아 수행된 연구입니다 (2019R1A6A3A01090378).

References

  1. Chang, F.J., Tsai, Y.H., Chen, P.A., Coynel, A., and Vachaud, G. 2015. Modeling water quality in an urban river using hydrological factors-Data driven approaches. Journal of environmental management 151: 87-96. https://doi.org/10.1016/j.jenvman.2014.12.014
  2. Donigian, A.S. 2000. HSPF Training Workshop Handbook and CD, Lecture #19, Calibration and Verification Issues, Slide #L19-22, EPA Heaarters, Washington Information Center, Presented and prepared for U.S. EPA, Office of Water, Office of Science and Technology.
  3. Faruk, D.O. 2010. A hybrid neural network and ARIMA model for water quality time series prediction. Engineering applications of artificial intelligence 23(4): 586-594. https://doi.org/10.1016/j.engappai.2009.09.015
  4. Keum, H.J., Kim, H.I., and Kim, B. 2019. Uncertainty analysis of rainfall scenarios for the prediction of flood disasters in urban areas. Journal of the Korean Society of Hazard Mitigation 19(2): 255-264. (in Korean) https://doi.org/10.9798/kosham.2019.19.2.255
  5. Khadr, M. and Elshemy, M. 2017. Data-driven modeling for water quality prediction case study: The drains system associated with Manzala Lake, Egypt. Ain Shams Engineering Journal 8(4): 549-557. https://doi.org/10.1016/j.asej.2016.08.004
  6. Kim, J.K., Lee, S.H., Bang, H.H., and Hwang, S.O. 2009. Characteristics of algae occurrence in Lake Paldang. Journal of Korean Society of Environmental Engineers 31(5): 325-331. (in Korean)
  7. Kim, S.E. and Seo, I.W. 2015. Artificial neural network ensemble modeling with exploratory factor analysis for streamflow forecasting. Journal of Hydroinformatics 17(4): 614-639. https://doi.org/10.2166/hydro.2015.033
  8. Kim, Y.S. and Lee, E.J. 2019. Establishment of Target Water Quality for TOC of Total Water Load Management System. Journal of Korean Society on Water Environment 35(6): 520-538. (in Korean) https://doi.org/10.15681/KSWE.2019.35.6.520
  9. Lee, E. and Kim, T. 2021. Predicting BOD under Various Hydrological Conditions in the Dongjin River Basin Using Physics-Based and Data-Driven Models. Water 13(10): 1383. https://doi.org/10.3390/w13101383
  10. Lee, E.J. 2013. Application of total water load management system using watershed model and load duration curves. Doctor's thesis, Cheongju University, Choengju, Korea. (in Korean)
  11. Lee, E.J., Kim, T.G., and Keum, H.J. 2018. Application of FDC and LDC using HSPF model to support total water load management system. Journal of Korean Society on Water Environment 34(1): 33-45. (in Korean) https://doi.org/10.15681/KSWE.2017.34.1.33
  12. Ministry Of Environment (MOE). 2015. Nam River Water Management Big Data Analysis to Prepare Water Quality Improvement Plan. (in Korean)
  13. Najah, A., El-Shafie, A., Karim, O.A., and El-Shafie, A.H. 2013. Application of artificial neural networks for water quality prediction. Neural Computing and Applications 22(1): 187-201. https://doi.org/10.1007/s00521-011-0694-3
  14. National Disaster Management Research Institute (NDMI), 2018, Developing an Analytic Framework for Real-time Inundated Hazard Area. (in Korean)
  15. Niknia, N., Moghaddam, H.K., Banaei, S.M., Podeh, H.T., Omidinasab, F., and Yazdi, A.A. 2014. Application of gamma test and neuro-fuzzy models in uncertainty analysis for prediction of pipeline scouring depth. Journal of Water Resource and Protection 6(05): 514. https://doi.org/10.4236/jwarp.2014.65050
  16. Oh, C.S. 2016. Notes on applying the EFDC model for simulating the water quality of Saemangeum watershed. Korean National Committee on Irrigation and Drainage 55: 42-48. (in Korean)
  17. Park, J.D. and Oh, S.Y. 2012. Methodology for the identification of impaired waters using LDC for the management of total maximum daily loads. Journal of Korean Society on Water Environment 28(5): 693-703. (in Korean)
  18. Poul, S., Manguerra, H., and Slawecki, T. 2019. A Watershed Management Perspective, Digest of water industry and business of Korean society on water environment. Big Data Anal 20-23.
  19. Rauf, A., Ahmed, S., Ghumman, A.R., Ahmad, I., Khan, K.A., and Ahsan, M. 2016. Data Driven Modelling for Real-time Flood Forecasting. In Proceedings of the 2nd International Multi-Disciplinary Conference, Gujrat, Pakistan 19-20.
  20. Sarkar, A. and Pandey, P. 2015. River water quality modelling using artificial neural network technique. Aquatic procedia, 4: 1070-1077. https://doi.org/10.1016/j.aqpro.2015.02.135
  21. Seo, I.W. and Choi, N.J. 2007. Water Quality Modeling and Water Quality Forecasting. Environmental Engineering Research 55(1): 57-84. (in Korean)
  22. Stefansson, A., Koncar, N., and Jones, A.J. 1997. A note on the gamma test. Neural Computing & Applications 5(3): 131-133. https://doi.org/10.1007/BF01413858
  23. Tetra Tech, Inc. 2007. The Environmental Fluid Dynamics Code User Manual US EPA Version 1.01.
  24. U.S.EPA. 2001. HSPF User's Manual.