Journal of Korea Water Resources Association (한국수자원학회논문집)

Korea Water Resources Association (한국수자원학회)
권호 표지
DOI QR코드

DOI QR Code

Prediction of cyanobacteria harmful algal blooms in reservoir using machine learning and deep learning

머신러닝과 딥러닝을 이용한 저수지 유해 남조류 발생 예측

  • Kim, Sang-Hoon (Bohyunsan Dam Office of K-water) ;
  • Park, Jun Hyung (National Civil Defence and Disaster Management Training Institute, Ministry of the Interior and Safety) ;
  • Kim, Byunghyun (Department of Civil Engineering, Kyungpook National University)
  • 김상훈 (한국수자원공사 보현산댐지사) ;
  • 박준형 (행정안전부 국가민방위재난안전교육원) ;
  • 김병현 (경북대학교 토목공학과)
  • Received : 2021.09.30
  • Accepted : 2021.11.21
  • Published : 2021.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

In relation to the algae bloom, four types of blue-green algae that emit toxic substances are designated and managed as harmful Cyanobacteria, and prediction information using a physical model is being also published. However, as algae are living organisms, it is difficult to predict according to physical dynamics, and not easy to consider the effects of numerous factors such as weather, hydraulic, hydrology, and water quality. Therefore, a lot of researches on algal bloom prediction using machine learning have been recently conducted. In this study, the characteristic importance of water quality factors affecting the occurrence of Cyanobacteria harmful algal blooms (CyanoHABs) were analyzed using the random forest (RF) model for Bohyeonsan Dam and Yeongcheon Dam located in Yeongcheon-si, Gyeongsangbuk-do and also predicted the occurrence of harmful blue-green algae using the machine learning and deep learning models and evaluated their accuracy. The water temperature and total nitrogen (T-N) were found to be high in common, and the occurrence prediction of CyanoHABs using artificial neural network (ANN) also predicted the actual values closely, confirming that it can be used for the reservoirs that require the prediction of harmful cyanobacteria for algal management in the future.

녹조 현상과 관련하여 독성물질을 배출하는 남조류 4종의 경우 유해 남조류로 지정하여 관리하고 있으며, 물리적인 모형을 이용한 예측 정보도 함께 발표하고 있다. 그러나 조류는 살아 있는 생명체로 물리 역학에 따른 예측에 어려움이 있으며, 기상, 수리·수문, 수질 등 수많은 인자에 의한 영향을 고려하기가 쉽지 않다. 따라서, 최근 머신러닝을 이용한 녹조발생 예측 연구가 많이 진행되고 있다. 본 연구에서는 경북 영천에 소재한 보현산댐과 영천댐을 대상으로 랜덤 포레스트 모형을 이용하여 유해남조류 발생에 영향을 미치는 수질인자의 특성중요도를 분석해 보았으며, 이 중 가장 높은 특성중요도를 나타낸 수온을 이용하여 머신러닝과 딥러닝을 이용하여 유해남조류 발생을 예측하고 그 정확성을 확인하였다. 특성중요도 분석 결과, 수온과 총질소(T-N)이 공통적으로 높게 나왔으며, 인공신경망(ANN)을 이용한 유해남조류 발생예측에서도 실제와 근접한 값이 예측되어 앞으로 녹조관리를 위해 유해남조류 예측이 필요한 저수지의 경우 이를 활용할 수 있음을 확인하였다.

Keywords

Acknowledgement

이 논문은 2020년도 정부(교육부)의 재원으로 국연구재단의 지원을 받아 수행된 기초연구사업임(No. 2020R1I1A3074459).

References

  1. Ahn, C.Y., Lee, C.S., Choi, J.W., Lee, S., and Oh, H.M. (2015). "Global occurrence of harmful cyanobacterial blooms and N, P-limitation strategy for bloom control." Korean Journal of Environmental Biology, Vol. 33, No. 1, pp. 1-6. (in Korean) https://doi.org/10.11626/KJEB.2015.33.1.001
  2. Breiman, L. (2001). "Random forests." Machine learning, Vol. 45, No. 1, pp. 5-32. https://doi.org/10.1023/A:1010933404324
  3. Cha, Y., Shin, J., and Kim, Y. (2020). "data-driven modeling of freshwater aquatic systems: Status and prospects." Journal of Korean Society on Water Environment, Vol. 36, No. 6, pp. 611-620. (in Korean) https://doi.org/10.15681/KSWE.2020.36.6.611
  4. Chollet, F. (2018). Deep learning with Python (Vol. 361). Manning, NY, U.S., pp. 28-47.
  5. Chung, J., Gulcehre, C., Cho, K., and Bengio, Y. (2014). "Empirical evaluation of gated recurrent neural networks on sequence modeling." arXiv preprint, arXiv1412.3555.
  6. Dale, D. (2017). Summing feature importance in Scikit-learn for a set of features, accessed 10 October 2021, .
  7. Derot, J., Yajima, H., and Jacquet, S. (2020). "Advances in forecasting harmful algal blooms using machine learning models a case study with Planktothrix rubescens in Lake Geneva." Harmful Algae, Vol. 99, 101906. https://doi.org/10.1016/j.hal.2020.101906
  8. Evans, J.D. (1996). Straightforward statistics for the behavioral sciences. Thomson Brooks/Cole Publishing Co., Pacific Grove, CA, U.S.
  9. Guzel, H.O. (2019). Prediction of freshwater harmful algal blooms in Western Lake Erie using artificial neural network modeling techniques. Master Thesis, North Dakota State University, U.S.
  10. Hochreiter, S., and Schmidhuber, J. (1997). "Long short-term memory." Neural Computation, Vol. 9, No. 8, pp. 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  11. Hong, H.W., Jo, E.S., Kang, S.A., and Han, K.J. (2020). Development and application of algae bloom phenomenon prediction technology using artificial intelligence deep learning. Korea Environmental Institute. (in Korean)
  12. Huang, J., Zheng, H., Wang, H., and Jiang, X. (2017). "Machine learning approaches for cyanobacteria bloom prediction using metagenomic sequence data, a case study." 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) IEEE, Kansas City, MO, U.S., pp. 2054-2061.
  13. Jung, K.W., Yoon, C.G., Jang, J.H., and Jeon, J.H. (2006). "Water quality and correlation analysis between water quality parameters in the Hwaong watershed." Journal of The Korean Society of Agricultural Engineers, Vol. 48, No. 1. (in Korean)
  14. Jung, W.S., Jo, B.G., Kim, Y.D., and Kim, S.E. (2019). "A study on the characteristics of cyanobacteria in the mainstream of Nakdong river using decision trees." Journal of Wetlands Research, Vol. 21, No. 4, pp. 312-320. (in Korean) https://doi.org/10.17663/JWR.2019.21.4.312
  15. Korea Environmental Institute (KEI) (2018). Environmental big data analysis and service development (II). (in Korean)
  16. K-water (2010). Bohyeonsan multipurpose dam construction project detailed design report. (in Korean)
  17. K-water (2019). Bohyeonsan dam basin pollution source detailed investigation report. (in Korean)
  18. Lee, H.M., Shin, R.Y., Lee, J.H., and Park, J.G. (2019). "A study on the relationship between cyanobacteria and environmental factors in Yeongcheon Lake." Journal of Korean Society on Water Environment, Vol. 35, No. 4, pp. 352-361. (in Korean) https://doi.org/10.15681/KSWE.2019.35.4.352
  19. Liaw, A., and Wiener, M. (2002). "Classification and regression by randomForest." R News, Vol. 2, No. 3, pp. 18-22.
  20. Liu, X., Lu, X., and Chen, Y. (2011). "The effects of temperature and nutrient ratios on microcystis blooms in Lake Taihu, China an 11-year investigation." Harmful Algae, Vol. 10, No. 3, pp. 337-343. https://doi.org/10.1016/j.hal.2010.12.002
  21. McCulloch, W.S., and Pitts, W. (1943). "A logical calculus of the ideas immanent in nervous activity." The Bulletin of Mathematical Biophysics, Vol. 5, No. 4, pp. 115-133. https://doi.org/10.1007/BF02478259
  22. Mitchell, A.W., Bramley, R.G.V., and Johnson, A.K.L. (1997). "Export of nutrients and suspended sediment during a cyclone-mediated flood event in the Herbert River catchment, Australia." Marine and Freshwater Research, Vol. 48, No. 1, pp. 79-88. https://doi.org/10.1071/MF96021
  23. National Information Society Agency (NIA) (2017). Development of machine learning-based algal bloom prediction model. (in Korean)
  24. National Institute of Environmental Research (NIER) (2011). A study on early forecasting for algal blooms using artificial neural networks (II). (in Korean)
  25. National Institute of Environmental Research (NIER) (2018). A study on the characteristics of algae depending rivers and lake (I). (in Korean)
  26. National Institute of Environmental Research (NIER) (2021). Water environment information system, accessed 13 September 2021, .
  27. Park, J., Moon, M., Lee, H., and Kim, K. (2014). "A study on characteristics of water quality using multivariate analysis in Sumjin River basin." Journal of Korean Society on Water Environment, Vol. 30, No. 2, pp. 119-127. (in Korean) https://doi.org/10.15681/KSWE.2014.30.2.119
  28. Shin, Y., Kim, T., Hong, S., Lee, S., Lee, E., Hong, S., Lee, C., Kim, T., Park M., Park J., and Heo, T.Y. (2020). "Prediction of chlorophyll-a concentrations in the Nakdong River using machine learning methods." Water, Vol. 12, No. 6, 1822. https://doi.org/10.3390/w12061822
  29. Song, E.S., Cho, K.A., and Shin, Y.S. (2015). "Exploring the dynamics of dissolved oxygen and vertical density structure of water column in the Youngsan Lake." Journal of Environmental Science International, Vol. 24, No. 2, pp. 163-174. (in Korean) https://doi.org/10.5322/JESI.2015.24.2.163
  30. Tayfur, G. (2014). Soft computing in water resources engineering Artificial neural networks, fuzzy logic and genetic algorithms. WIT Press, Southampton, UK.
  31. Water Resources Management Information System (WAMIS) (2021). Republic of Korea, accessed 10 September 2021, .
  32. Weiss, R.F. (1970). "The solubility of nitrogen, oxygen and argon in water and seawater." Deep Sea Research and Oceanographic Abstracts, Vol. 17, No. 4, pp. 721-735. https://doi.org/10.1016/0011-7471(70)90037-9
  33. Yi, H.S., Park, S., An, K.G., and Kwak, K.C. (2018). "Algal bloom prediction using extreme learning machine models at artificial weirs in the Nakdong River, Korea." International Journal of Environmental Research and Public Health, Vol. 15, No. 10, p. 2078. https://doi.org/10.3390/ijerph15102078
  34. Yu, P., Gao, R., Zhang, D., and Liu, Z.P. (2021). "Predicting coastal algal blooms with environmental factors by machine learning methods." Ecological Indicators, Vol. 123, 107334. https://doi.org/10.1016/j.ecolind.2020.107334