Journal of Korean Society on Water Environment (한국물환경학회지)

Korean Society on Water Environment (한국물환경학회)
권호 표지
DOI QR코드

DOI QR Code

Estimating Optimal Parameters of Artificial Neural Networks for the Daily Forecasting of the Chlorophyll-a in a Reservoir

호소내 Chl-a의 일단위 예측을 위한 신경망 모형의 적정 파라미터 평가

  • Yeon, Insung (Water Quality Control Center, National Institute of Environmental Research) ;
  • Hong, Jiyoung (Water Quality Control Center, National Institute of Environmental Research) ;
  • Mun, Hyunsaing (Water Quality Control Center, National Institute of Environmental Research)
  • 연인성 (국립환경과학원 수질통합관리센터) ;
  • 홍지영 (국립환경과학원 수질통합관리센터) ;
  • 문현생 (국립환경과학원 수질통합관리센터)
  • Received : 2011.05.06
  • Accepted : 2011.07.07
  • Published : 2011.07.30
Download PDF
⟨ Previous Next ⟩

Abstract

Algal blooms have caused problems for drinking water as well as eutrophication. However it is difficult to control algal blooms by current warning manual in rainy season because the algal blooms happen in a few days. The water quality data, which have high correlations with Chlorophyll-a on Daecheongho station, were analyzed and chosen as input data of Artificial Neural Networks (ANN) for training pattern changes. ANN was applied to early forecasting of algal blooms, and ANN was assessed by forecasting errors. Water temperature, pH and Dissolved oxygen were important factors in the cross correlation analysis. Some water quality items like Total phosphorus and Total nitrogen showed similar pattern to the Chlorophyll-a changes with time lag. ANN model (No. 3), which was calibrated by water temperature, pH and DO data, showed lowest error. The combination of 1 day, 3 days, 7 days forecasting makes outputs more stable. When automatic monitoring data were used for algal bloom forecasting in Daecheong reservoir, ANN model must be trained by just input data which have high correlation with Chlorophyll-a concentration. Modular type model, which is combined with the output of each model, can be effectively used for stable forecasting.

Keywords

Acknowledgement

Supported by : 국립환경과학원

References

  1. 국립환경과학원(2008). 대청호 조류상습 발생수역이 본류 수질에 미치는 영향 분석(II).
  2. 국립환경과학원(2009). 대청호 수질 및 조류발생 실태조사.
  3. 김동균(2008). Plankton community dynamics in Nakdong river basin: the prediction based on ecological modeling. 박사학위논문, 부산대학교.
  4. 박혜경, 김은경, 정동일(2005). 팔당호 조류 발생 예측 모델. 공동춘계학술발표회 논문집, 한국물환경학회.대한상하수도학회, pp. 115-118.
  5. 서동일(1997). 댐 유역 오염물질 유입특성 및 영향에 관한 연구(2차년도). 한국수자원공사.
  6. 심순보, 고덕구, 이요상, 오이성(1995). WASP5 수질모형을 이용한 대청호의 부영양화 예측. 건설기술논문집, 14(2), pp. 41-53.
  7. 연인성, 홍지영, 홍은영, 임병진(2010). 연속 측정된 대청호 Chlorophyll-a의 자료 특성 및 상관 분석. 수질보전 한국물환경학회지, 26(6), pp. 994-999.
  8. 유병로(2001). WASP5 수질모형을 이용한 대청호 부영양화 인자의 특성연구. 한국환경기술학회지, 2(3), pp. 297-306.
  9. 유순주, 황종연, 채민희, 김상용(2006). 대청호 유속에 따른 조류이동 영향. 수질보전 한국물환경학회지, 22(5), pp.887-894.
  10. 정건희(2001). 신경망 모형을 이용한 대청댐의 수질예측에 관한 연구. 석사학위논문, 고려대학교.
  11. 정광석(2004). Application of machine learning to pattern and predict the phytoplankton time-series data in a flowregulated river system (the lower Nakdong river). 박사학위논문, 부산대학교.
  12. 정세웅, 박재호, 김유경, 윤성환(2007). 대청호 부영양화 모의를 위한 CE-QUAL-W2 모형의 적용. 수질보전 한국물환경학회지, 23(1), pp. 52-63.
  13. 정종혁, 정하규, 권원태(2008). 조류를 이용한 수계모니터링 시스템에서 뉴럴 네트눠크에 의한 실시간 독성물질 판단. 수질보전 한국물환경학회지, 24(1), pp. 1-6.
  14. Chen, S. H., Jakeman, A. J., and Norton, J. P. (2008). Artificial Intelligence techniques: An introduction to their use for modelling environmental systems. Mathematics and Computers in Simulation, 78(2), pp. 379-400. https://doi.org/10.1016/j.matcom.2008.01.028
  15. Hornsby shire council. (2008). Estuary management program (2007-2008 annual report). Australia.
  16. Karul, C., Soyupak, S., Cilesiz, A. F., Akbay, N., and Germen, E. (2000). Case studies on the use of neural networks in eutrophication modeling. Ecological Modelling, 134(2), pp. 145-152. https://doi.org/10.1016/S0304-3800(00)00360-4
  17. Lee, J. H. W., Huang, Y., Dickman, M., and Jayawardena, A. W. (2003). Neural network modelling of coastal algal blooms. Ecological Modelling, 159(2), pp. 179-201. https://doi.org/10.1016/S0304-3800(02)00281-8
  18. Maier, H. R., Dandy, G. C., and Burch, M. D. (1998). Use of artificial neural networks for modelling cyanobacteria Anabaena spp. in the River Murray. Ecological Modelling, 105(2), pp. 257-272.
  19. Oh, H. M., Ahn, C. Y., Lee, J. W., Chon, T. S., and Choi, K. H. (2007). Community patterning and identification of predominant factors in algal bloom in Daechung Reservoir (Korea) using artificial neural networks. Ecological Modelling, 203(1), pp. 109-118. https://doi.org/10.1016/j.ecolmodel.2006.04.030
  20. Palani, S., Liong, S. Y., and Tkalich, P. (2008). An ANN application for water quality forecasting. Marine Pollution Bulletin, 56(9), pp. 1586-1597. https://doi.org/10.1016/j.marpolbul.2008.05.021
  21. Recknagel, F., French, M., Harkonen, P., and Yabunaka, K. I. (1997). Artificial neural network approach for modelling and prediction of algal blooms. Ecological Modelling, 96(2), pp. 11-28.
  22. Velo-Suarez, L. and Gutierrez-Estrada, J. (2007). Artificial neural network approaches to one-step weekly prediction of Dinophysis acuminata blooms in Huelva. Harmful Algae, 6(3), pp. 361-371. https://doi.org/10.1016/j.hal.2006.11.002
  23. WAMIS (2007-2009). http://www.wamis.go.kr/.