Journal of Korean Society of Coastal and Ocean Engineers (한국해안·해양공학회논문집)

Korean Society of Coastal and Ocean Engineers (한국해안·해양공학회)
권호 표지
DOI QR코드

DOI QR Code

Prediction of DO Concentration in Nakdong River Estuary through Case Study Based on Long Short Term Memory Model

Long Short Term Memory 모델 기반 Case Study를 통한 낙동강 하구역의 용존산소농도 예측

  • Park, Seongsik (Department of Ocean Engineering, Pukyong National University) ;
  • Kim, Kyunghoi (Department of Ocean Engineering, Pukyong National University)
  • Received : 2021.11.12
  • Accepted : 2021.12.05
  • Published : 2021.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, we carried out case study to predict dissolved oxygen (DO) concentration of Nakdong river estuary with LSTM model. we aimed to figure out a optimal model condition and appropriate predictor for prediction in dissolved oxygen concentration with model parameter and predictor as cases. Model parameter case study results showed that Epoch = 300 and Sequence length = 1 showed higher accuracy than other conditions. In predictor case study, it was highest accuracy where DO and Temperature were used as a predictor, it was caused by high correlation between DO concentration and Temperature. From above results, we figured out an appropriate model condition and predictor for prediction in DO concentration of Nakdong river estuary.

본 연구에서는 LSTM 모델을 활용하여 낙동강 하구역의 DO 농도 예측을 위한 최적 모델 조건과 적합한 예측변수를 찾기 위한 Case study를 수행하였다. 모델 매개변수 case study 결과, Epoch = 300과 Sequence length = 1에서 상대적으로 높은 정확도를 보였다. 예측변수 case study 결과, DO와 수온을 예측변수로 했을 때 가장 높은 정확도를 보였으며, 이는 DO 농도와 수온의 높은 상관성에 기인한 것으로 판단된다. 상기 결과로부터 낙동강 하구역의 DO 농도 예측에 적합한 LSTM 모델 조건과 예측변수를 찾을 수 있었다.

Keywords

Acknowledgement

본 연구는 부경대학교 자율창의학술연구비(2021)에 의하여 연구되었음.

References

  1. Ahn, S., Yeon, I., Han, Y. and Lee, J. (2001). Water quality forecasting at Gongju station in Geum River using neural network model. Journal of Korea Water Resources Association, 34, 701-711.
  2. Baden, S.P., Loo, L.O., Pihl, L. and Rosenberg, R. (1990). Effects of eutrophication on benthic communities including fish: Swedish west coast. AMBIO A Journal of the Human Environment, 13(3), 113-122.
  3. Bengio, Y., Simard, P., and Frasconi, P. (1994). Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks, 5(2), 157-166. https://doi.org/10.1109/72.279181
  4. Breitburg, D.L., Steinberg, N., Dubeau, S., Cooksey, C. and Houde, E.D. (1994). Effects of low dissolved oxygen on predation on estuarine fish larvae. Mar. Ecol. Prog. Ser., 104, 235-246. https://doi.org/10.3354/meps104235
  5. Diaz, R.J. and Solow, A. (1999). Ecological and economic consequences of hypoxia: topic 2 report for the integrated assessment on hypoxia in the Gulf of Mexico. NOAA Coastal Ocean Program Decision Analysis Series No. 16. National Oceanic and Atmospheric Administration, Coastal Ocean Office, Silver Spring, MD.
  6. Dupond, S. (2019). A thorough review on the current advance of neural network structures. Annual Reviews in Control, 14, 200-230.
  7. Eze, E. and Ajmal, T. (2020). Dissolved Oxygen Forecasting in Aquaculture: A Hybrid Model Approach. Appl. Sci., 10(20), 7079. https://doi.org/10.3390/app10207079
  8. Hochreiter, S. and Schmidhuber J. (1997). Long short-term memory. Neural Computation, 9, 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  9. Huck, P.M. and Farquhar, G.J. (1974). Water quality models using the Box-Jenkins method. Journal of the Environmental Engineering, 100, 733-751.
  10. Jang, S.T. and Kim, K.C. (2006). Change of Oceanographic Environment in the Nakdong Estuary. Journal of the Korean Society of Oceanography, 11(1), 11-20.
  11. KOEM (Korea Marine Environment Management Corporation), Monitoring the marine environment, https://www.koem.or.kr/site/koem/main.do, 2020.
  12. K-water. (1996). A study on the prediction of pollutant advection and dispersion and on the reduction countermeasures in a large river: Focusing on the main stream of Nakdong River. K-water, Korea.
  13. Li, W., Wu, H., Zhu, N., Jiang, Y., Tan, J. and Guo, Y. (2021). Prediction of dissolved oxygen in a fishery pond based on gated recurrent unit (GRU). Information Processing in Agriculture, 8(1), 185-193. https://doi.org/10.1016/j.inpa.2020.02.002
  14. Lim, H., An, H., Choi, E. and Kim, Y. (2020). Prediction of the DO concentration using the machine learning algorithm: case study in Oncheoncheon, Republic of Korea. Korean Journal of Agricultural Science, 47, 1029-1037. https://doi.org/10.7744/KJOAS.20200086
  15. MEIS (Marine Environmental Information System), Marine Environment Observation & Survey, https://www.meis.go.kr/mei/observe/port.do, 2020.
  16. Paerl, H.W., Pinckney, J.L., Fear, J.M. and Peierls, B.L. (1998). Ecosystem Responses to Internal and Watershed Organic Matter Loading: Consequences for Hypoxia in the Eutrophying Neuse River Estuary, North Carolina, USA. Marine Ecology Progress Series, 166, 17-25. https://doi.org/10.3354/meps166017
  17. Rosenberg, R., Elmgren, R., Fleischer, S., Jonsson, P., Persson, G. and Dahlin, H. (1990). Marine eutrophication case studies in Sweden: a synopsis. Ambio, 19, 102-108.
  18. Rumelhart, D., Hinton, G. and Williams, R. (1986). Learning representations by back-propagating errors. Nature, 323, 533-536. https://doi.org/10.1038/323533a0
  19. Song, K.O., Ahn, O.S. and Park, C.K. (1993). Water quality modeling in the Nakdong river (2) - A study on DO balance. Korean Society on Water Environment, 9(1), 54-66.
  20. Tealab, A. (2018). Time series forecasting using artificial neural networks methodologies: A systematic review. Future Computing and Informatics Journal, 3(2), 334-340. https://doi.org/10.1016/j.fcij.2018.10.003
  21. Yin, K., Lin, Z. and Ke, Z. (2004). Temporal and spatial distribution of dissolved oxygen in the Pearl River Estuary and adjacent coastal waters. Continental Shelf Research, 24(16), 1935-1948. https://doi.org/10.1016/j.csr.2004.06.017
  22. Zhou, G.R. (2004). Theory of statistics. 2nd Ed. Nankai University Press, Tianjin.