Journal of Korean Society on Water Environment (한국물환경학회지)

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

DOI QR Code

Data-driven Model Prediction of Harmful Cyanobacterial Blooms in the Nakdong River in Response to Increased Temperatures Under Climate Change Scenarios

기후변화 시나리오의 기온상승에 따른 낙동강 남세균 발생 예측을 위한 데이터 기반 모델 시뮬레이션

  • Gayeon Jang (Department of Civil and Environmental Engineering, Yonsei University) ;
  • Minkyoung Jo (Department of Civil and Environmental Engineering, Yonsei University) ;
  • Jayun Kim (Department of Civil and Environmental Engineering, Yonsei University) ;
  • Sangjun Kim (Department of Civil and Environmental Engineering, Yonsei University) ;
  • Himchan Park (Department of Civil and Environmental Engineering, Yonsei University) ;
  • Joonhong Park (Department of Civil and Environmental Engineering, Yonsei University)
  • 장가연 (연세대학교 건설환경공학과) ;
  • 조민경 (연세대학교 건설환경공학과) ;
  • 김자연 (연세대학교 건설환경공학과) ;
  • 김상준 (연세대학교 건설환경공학과) ;
  • 박힘찬 (연세대학교 건설환경공학과) ;
  • 박준홍 (연세대학교 건설환경공학과)
  • Received : 2024.01.24
  • Accepted : 2024.04.29
  • Published : 2024.05.30
Download PDF
⟨ Previous Next ⟩

Abstract

Harmful cyanobacterial blooms (HCBs) are caused by the rapid proliferation of cyanobacteria and are believed to be exacerbated by climate change. However, the extent to which HCBs will be stimulated in the future due to increased temperature remains uncertain. This study aims to predict the future occurrence of cyanobacteria in the Nakdong River, which has the highest incidence of HCBs in South Korea, based on temperature rise scenarios. Representative Concentration Pathways (RCPs) were used as the basis for these scenarios. Data-driven model simulations were conducted, and out of the four machine learning techniques tested (multiple linear regression, support vector regressor, decision tree, and random forest), the random forest model was selected for its relatively high prediction accuracy. The random forest model was used to predict the occurrence of cyanobacteria. The results of boxplot and time-series analyses showed that under the worst-case scenario (RCP8.5 (2100)), where temperature increases significantly, cyanobacterial abundance across all study areas was greatly stimulated. The study also found that the frequencies of HCB occurrences exceeding certain thresholds (100,000 and 1,000,000 cells/mL) increased under both the best-case scenario (RCP2.6 (2050)) and worst-case scenario (RCP8.5 (2100)). These findings suggest that the frequency of HCB occurrences surpassing a certain threshold level can serve as a useful diagnostic indicator of vulnerability to temperature increases caused by climate change. Additionally, this study highlights that water bodies currently susceptible to HCBs are likely to become even more vulnerable with climate change compared to those that are currently less susceptible.

Keywords

Acknowledgement

This research was supported by the Basic Science Research Program through the National Research Foundation of Korea, funded by the Ministry of Education (No. 2018R1A6A1A08025348).

References

  1. Aggarwal, C. C. (2018). Neural networks and deep learning, Springer. https://doi.org/10.1007/978-3-319-94463-0
  2. Bae, D., Shin, S. Y., Shim, J. H., Jeong, S. S., and Shin, S. Y. (2015). The 3rd forum on future policies civil engineering dealing with climate change and urbanization - Preparedness plan for disasters in urban areas, Journal of the Korean Society of civil engineers, 63(7), 36-51. [Korean Literature]
  3. Bernat-Quesada, F., Alvaro, M., Garcia, H., and Navalon, S. (2020). Impact of chlorination and pre-ozonation on disinfection by-products formation from aqueous suspensions of cyanobacteria: Microcystis aeruginosa, Anabaena aequalis and Oscillatoria tenuis, Water Research, 183, 116070. https://doi.org/10.1016/j.watres.2020.116070
  4. Cha, Y., Cho, K., Lee, H., Kang, T., and Kim, J. H. (2017). The relative importance of water temperature and residence time in predicting cyanobacteria abundance in regulated rivers, Water Research, 124, 11-19. https://doi.org/10.1016/j.watres.2017.07.040
  5. Cho, Y. M., Seo, Y., Maeng, S. K., and Hong, Y. (2020). Improving the safety of tap water in Gyeonggi-do, Gyeonggi Research Institute. [Korean Literature]
  6. Choi, S. Y., Han, K. Y., and Kim, B. H. (2012). Comparison of different multiple linear regression models for real-time flood stage forecasting, Journal of the Korean Society of Civil Engineers, 32(1B), 9-20.
  7. Health Canada. (2022). Guidelines for Canadian recreational water quality - Cyanobacteria and their Toxins, Health Canada.
  8. Huisman, J., Codd, G. A., Paerl, H. W., Ibelings, B. W., Verspagen, J. M. H., and Visser, P. M. (2018). Cyanobacterial blooms, Nature reviews, Microbiology, 16(8), 471-483. https://doi.org/10.1038/s41579-018-0040-1
  9. Intergovernmental Panel on Climate Change (IPCC). (2014). Climate change 2014: Synthesis report. Contribution of working groups I, II and III to the fifth assessment report of the intergovernmental panel on climate change, Core Writing Team, Pachauri, R. K. and Meyer, L. A. (eds.), Geneva, Switzerland, 151.
  10. Johnk, K. D., Huisman, J., Sharples, J., Sommeijer, B., Visser, P. M., and Stroom, J. M. (2008). Summer heatwaves promote blooms of harmful cyanobacteria, Global Change Biology, 14, 495-512. https://doi.org/10.1111/j.1365-2486.2007.01510.x
  11. Jung, W., Kim, S. E., and Kim, Y. D. (2021). Analysis of influential factors of cyanobacteria in the mainstream of Nakdong river using random forest, Journal of Wetlands Researh, 23(1), 27-34. [Korean Literature] https://doi.org/10.17663/JWR.2021.23.1.27
  12. Jung, Y. J. and Kim, Y. J. (2016). Relationship between energy consumption and operational variables at wastewater treatment plant, Journal of Korean Society on Water Environment, 32(3), 253-260. https://doi.org/10.15681/KSWE.2016.32.3.253
  13. Kim, H. G., Cha, Y., and Cho, K. H. (2024). Projected climate change impact on cyanobacterial bloom phenology in temperate rivers based on temperature dependency, Water Research, 249, 120928. https://doi.org/10.1016/j.watres.2023.120928
  14. Kim, H. G., Cho, K. H., and Recknagel, F. (2023). Time-series modelling of harmful cyanobacteria blooms by convolutional neural networks and wavelet generated time-frequency images of environmental driving variables, Water Research, 246, 120662. https://doi.org/10.1016/j.watres.2023.120662
  15. Kim, J., Jung, W., An, J., Oh, H. J., and Park, J. (2023). Self-optimization of training dataset improves forecasting of cyanobacterial bloom by machine learning, The Science of the Total Environment, 866, 161398. https://doi.org/https://doi.org/10.1016/j.scitotenv.2023.161398
  16. Lee, S., Choi, B., Kim, S. J., Kim, J., Kang, D., and Lee, J. (2022). Relationship between freshwater harmful algal blooms and neurodegenerative disease incidence rates in South Korea, Environmental Health, 21(1), 1-11. https://doi.org/10.1186/s12940-022-00935-y
  17. Li, Z., Chen, Q., Xu, Q., and Blanckaert, K. (2013). Generalized likelihood uncertainty estimation method in uncertainty analysis of numerical Eutrophication models: Take bloom as an example, Mathematical Problems in Engineering, 2013, 701923. https://doi.org/10.1155/2013/701923
  18. Ministry of Environment. (2020). Korean climate change assessment report 2020, Publish No. 11-1480000-001691-01, Ministry of Environment. [Korean Literature]
  19. Ministry of Environment. (2022). Annual report on algae (green algae) occurrence and response, Publish No. 11-14800000-001363-10, Ministry of Environment. [Korean Literature]
  20. Moon, H., Baik, J., Hwang, S., and Choi, M. (2014). Spatial downscaling of grid precipitation using support vector machine regression, Journal of Korea Water Resources Association, 47(11), 1095-1105. [Korean Literature]
  21. National Disaster Management Research Institute. (2023). Disaster and safety system improvement report: Expansion of heat wave vulnerability management targets due to climate crisis, Publish No. 11-1741056-000568-01, National Disaster Management Research Institute. [Korean Literature]
  22. Paerl, H. W. and Huisman, J. (2008). Blooms like it hot, Science, 320(5872), 57-58. https://doi.org/10.1126/science.1155398
  23. Schneider, M. and Blaha, L. (2020). Advanced oxidation processes for the removal of cyanobacterial toxins from drinking water, Environmental Sciences Europe, 32(1), 94. https://doi.org/10.1186/s12302-020-00371-0
  24. United Stated Environmental Protection Agency (U. S. EPA.). (2019). Recommended human health recreational ambient water quality criteria or swimming advisories for microcystins and cylindrospermopsin, EPA 822-R-19-001. https://www.epa.gov/sites/default/files/2019-05/documents/hh-rec-criteria-habs-document-2019.pdf.
  25. Villanueva, P., Yang, J., Radmer, L., Liang, X., Leung, T., Ikuma, K., Swanner, E. D., Howe, A., and Lee, J. (2023). One-week-ahead prediction of cyanobacterial harmful algal blooms in Iowa lakes, Environmental Science & Technology, 57(49), 20636-20646. https://doi.org/10.1021/acs.est.3c07764
  26. Wisniewska, K., Lewandowska, A. U., and Sliwinska-Wilczewska, S. (2019). The importance of cyanobacteria and microalgae present in aerosols to human health and the environment-Review study, Environment International, 131, 104964. https://doi.org/10.1016/j.envint.2019.104964
  27. Woo, C. Y., Yun, S. L., Kim, S. K., and Lee, W. (2020). Occurrence of harmful blue-green algae at algae alert system and water quality forecast system sites in Daegu and Gyeongsangbuk-do between 2012 and 2019, Journal of Korean Society of Environmental Engineers, 42(12), 664-673. [Korean Literature] https://doi.org/10.4491/KSEE.2020.42.12.664
  28. World Health Organization (WHO). (2021). Guidelines on recreational water quality: Volume 1 Coastal and fresh waters, World Health Organization.
  29. Xiao, X., He, J., Huang, H., Miller, T. R., Christakos, G., Reichwaldt, E. S., Ghadouani, A., Lin, S., Xu, X., and Shi, J. (2017). A novel single-parameter approach for forecasting algal blooms, Water Research, 108, 222-231. https://doi.org/10.1016/j.watres.2016.10.076
  30. Xie, Z., Lou, I., Ung, W. K., and Mok, K. M. (2012). Freshwater algal bloom prediction by support vector machine in Macau storage reservoirs, Mathematical Problems in Engineering, 2012, 397473. https://doi.org/10.1155/2012/397473