생태와환경 (Korean Journal of Ecology and Environment)

  • 제56권3호
  • /
  • Pages.268-279
  • /
  • 2023
  • /
  • 2288-1115(pISSN)
  • /
  • 2288-1123(eISSN)
한국수생태학회 (The Korean Society of Limnology)
권호 표지
DOI QR코드

DOI QR Code

담수 유해남조 세포수·대사물질 농도 예측을 위한 머신러닝과 딥러닝 모델링 연구동향: 알고리즘, 입력변수 및 학습 데이터 수 비교

Machine- and Deep Learning Modelling Trends for Predicting Harmful Cyanobacterial Cells and Associated Metabolites Concentration in Inland Freshwaters: Comparison of Algorithms, Input Variables, and Learning Data Number

  • 박용은 (건국대학교 사회환경공학부) ;
  • 김진휘 (건국대학교 사회환경공학부) ;
  • 이한규 (건국대학교 사회환경플랜트공학과) ;
  • 변서현 (건국대학교 사회환경플랜트공학과) ;
  • 황순진 (건국대학교 환경보건과학과) ;
  • 신재기 (수생태원 한강 (韓江))
  • Yongeun Park (School of Civil and Environmental Engineering, Konkuk University) ;
  • Jin Hwi Kim (School of Civil and Environmental Engineering, Konkuk University) ;
  • Hankyu Lee (Graduate School of Civil, Environmental and Plant Engineering, Konkuk University) ;
  • Seohyun Byeon (Graduate School of Civil, Environmental and Plant Engineering, Konkuk University) ;
  • Soon-Jin Hwang (Department of Environmental Health and Science, Konkuk University) ;
  • Jae-Ki Shin (Limnoecological Science Research Institute Korea (THE HANGANG))
  • 투고 : 2023.08.13
  • 심사 : 2023.10.01
  • 발행 : 2023.09.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

근래에 들어, 머신러닝과 딥러닝 모델은 다양한 수체 내 수질변화를 예측하기 위해 광범위하게 사용되고 있다. 특히, 담수호의 물 이용과 수생태계 건강성에 위협 요인으로 작용할 수 있는 유해남조의 발생을 예측하기 위해 많은 연구자들이 인공지능 모델을 활용하고 있다. 따라서, 본 연구에서는 최근까지 유해남조의 발생을 예측하기 위해 적용된 인공지능 모델링의 선행 연구들을 검토하였고, 딥러닝을 포함하여 머신러닝 모델을 이용한 이 분야 연구의 발전방향을 모색하고자 하였다. 먼저, Elsevier의 초록 인용 데이터베이스인 Scopus를 활용하여 체계적인 문헌 연구를 수행하였다. 주요 키워드를 이용하여 탐색 및 정리된 문헌들을 리뷰한 결과, 딥러닝 모델은 주로 남조 세포수 예측에만 사용되었고, 머신러닝 모델은 남조 세포수 이외에 microcystin, geosmin, 2-MIB와 같은 대사물질 예측에도 초점을 맞추고 있었다. 또한, 남조 세포수와 대사물질의 예측을 위해 활용된 입력변수들은 현저한 차이가 있었다. 남조의 대사물질을 예측하기 위해 딥러닝 모델이 적용된 바가 없었는데, 향후 빅데이터 구축을 통한 대사물질을 예측하는 연구가 필요할 것으로 사료된다.

Nowadays, artificial intelligence model approaches such as machine and deep learning have been widely used to predict variations of water quality in various freshwater bodies. In particular, many researchers have tried to predict the occurrence of cyanobacterial blooms in inland water, which pose a threat to human health and aquatic ecosystems. Therefore, the objective of this study were to: 1) review studies on the application of machine learning models for predicting the occurrence of cyanobacterial blooms and its metabolites and 2) prospect for future study on the prediction of cyanobacteria by machine learning models including deep learning. In this study, a systematic literature search and review were conducted using SCOPUS, which is Elsevier's abstract and citation database. The key results showed that deep learning models were usually used to predict cyanobacterial cells, while machine learning models focused on predicting cyanobacterial metabolites such as concentrations of microcystin, geosmin, and 2-methylisoborneol (2-MIB) in reservoirs. There was a distinct difference in the use of input variables to predict cyanobacterial cells and metabolites. The application of deep learning models through the construction of big data may be encouraged to build accurate models to predict cyanobacterial metabolites.

키워드

과제정보

본 논문의 심사과정에서 세세한 검토와 코멘트를 해 주신 익명의 심사위원들께 감사드립니다.

참고문헌

  1. Al-Sulttani, A.O., M. Al-Mukhtar, A.B. Roomi, A.A. Farooque, K.M. Khedher and Z.M. Yaseen. 2021. Proposition of new ensemble data-intelligence models for surface water quality prediction. IEEE (Institute of Electrical and Electronics Engineers) Access 9: 108527-108541. https://doi.org/10.1109/ACCESS.2021.3100490
  2. Anderson, D.M., A.D. Cembella and G.M. Hallegraeff. 2012. Progress in understanding harmful algal blooms: paradigm shifts and new technologies for research, monitoring, and management. Annual Review of Marine Science 3: 143-176. https://doi.org/10.1146/annurev-marine-120308-081121
  3. Baker, R.E., J.M. Pena, J. Jayamohan and A. Jerusalem. 2018. Mechanistic models versus machine learning, a fight worth fighting for the biological community? Biology Letters 14: 20170660.
  4. Bertone, E., M.A. Burford and D.P. Hamilton. 2018. Fluorescence probes for real-time remote cyanobacteria monitoring: a review of challenges and opportunities. Water Research 141: 152-162. https://doi.org/10.1016/j.watres.2018.05.001
  5. Bruder, S., M. Babbar-Sebens, L. Tedesco and E. Soyeux. 2014. Use of fuzzy logic models for prediction of taste and odor compounds in algal bloom-affected inland water bodies. Environmental Monitoring Assessment 186: 1525-1545. https://doi.org/10.1007/s10661-013-3471-1
  6. Cawley, G.C. and N.L. Talbot. 2010. On over-fitting in model selection and subsequent selection bias in performance evaluation. Journal Machine Learning Research 11: 2079-2107.
  7. Chen, C., J.C. Huang, Q.W. Chen, J.Y. Zhang, Z.J. Li and Y.Q. Lin. 2019. Assimilating multi-source data into a three-dimensional hydro-ecological dynamics model using Ensemble Kalman Filter. Environmental Modelling and Software 117: 188-199. https://doi.org/10.1016/j.envsoft.2019.03.028
  8. Chen, Q.W. and A.E. Mynett. 2003. Integration of data mining techniques and heuristic knowledge in fuzzy logic modelling of eutrophication in Taihu Lake. Ecological Modelling 162: 55-67. https://doi.org/10.1016/S0304-3800(02)00389-7
  9. Dodds, W.K., W.W. Bouska, J.L. Eitzmann, T.J. Pilger, K.L. Pitts, A.J. Riley, J.T. Schloesser and D.J. Thornbrugh. 2009. Eutrophication of U.S. freshwaters: Analysis of potential economic damages. Environmental Science and Technology 43: 12-19. https://doi.org/10.1021/es801217q
  10. Fornarelli, R., S. Galelli, A. Castelletti, J.P. Antenucci and C.L. Marti. 2013. An empirical modeling approach to predict and understand phytoplankton dynamics in a reservoir affected by interbasin water transfers. Water Resources Research 49: 3626-3641. https://doi.org/10.1002/wrcr.20268
  11. Gardner, R.C. 2000. Correlation, causation, motivation, and second language acquisition. Canadian Psychology/Psychologie Canadienne 41: 10-24. https://doi.org/10.1037/h0086854
  12. Gelman, A. and J. Hill. 2006. Data Analysis Using Regression and Multilevel/Hierarchical Models. Cambridge University Press, Cambridge, England. 648p.
  13. Guven, B. and A. Howard. 2006. A review and classification of the existing models of cyanobacteria. Progress in Physical Geography: Earth and Environment 30: 1-24. https://doi.org/10.1191/0309133306pp464ra
  14. Hamilton, D.P., K.R. O'Brien, M.A. Burford, J.D. Brookes and C.G. McBride. 2010. Vertical distributions of chlorophyll in deep, warm monomictic lakes. Aquatic Sciences 72: 295-307. https://doi.org/10.1007/s00027-010-0131-1
  15. Harada, M., T. Tominaga, K. Hiramatsu and A. Marui. 2013. Real-time prediction of chlorophyll-a time series in a eutrophic agricultural reservoir in a coastal zone using recurrent neural networks with periodic chaos neurons. Irrigation and Drainage 62: 36-43. https://doi.org/10.1002/ird.1757
  16. Harris, T.D. and J.L. Graham. 2017. Predicting cyanobacterial abundance, microcystin, and geosmin in a eutrophic drinking-water reservoir using a 14-year dataset. Lake and Reservoir Management 33: 32-48. https://doi.org/10.1080/10402381.2016.1263694
  17. Hwang, S.J., K. Kim, C. Park, W. Seo, B.G. Choi, H.S. Eum, M.H. Park, H.R. Noh, Y.B. Sim and J.K. Shin. 2016. Hydro-meteorological effects on water quality variability in Paldang Reservoir, confluent area of the South-Han River-North-Han River-Gyeongan Stream, Korea. Korean Journal of Ecology and Environment 49: 354-374. https://doi.org/10.11614/KSL.2016.49.4.354
  18. Hwang, S.J., Y.B. Sim, B.G. Choi, K. Kim, C. Park, W. Seo, M.H. Park, S.W. Lee and J.K. Shin. 2017. Rainfall and hydrological comparative analysis of water quality variability in Euiam Reservoir, the North-Han River, Korea. Korean Journal of Ecology and Environment 50: 29-45. https://doi.org/10.11614/KSL.2017.50.1.029
  19. Kim, S.H., J.H. Park and B. Kim. 2021. Prediction of cyanobacteria harmful algal blooms in reservoir using machine learning and deep learning. Journal of Korea Water Resources Association 54: 1167-1181. https://doi.org/10.3741/JKWRA.2021.54.S-1.1167
  20. Kratzert, F., D. Klotz, M. Herrnegger, A.K. Sampson, S. Hochreiter and G.S. Nearing. 2019. Toward improved predictions in ungauged basins: Exploiting the power of machine learning. Water Resources Research 55: 11344-11354. https://doi.org/10.1029/2019WR026065
  21. LeCun, Y., Y. Bengio and G. Hinton. 2015. Deep learning. Nature 521: 436-444. https://doi.org/10.1038/nature14539
  22. Lee, E., E.H. Na and K. Kim. 2012. The establishment of water quality forecasting system for preemptive water quality management. Rural Resources 54: 50-55.
  23. Liu, Y., Z. Wang, H. Guo, S. Yu and H. Sheng. 2013. Modelling the effect of weather conditions on cyanobacterial bloom outbreaks in Lake Dianchi: a rough decision-adjusted logistic regression model. Environmental Modeling and Assessment 18: 199-207. https://doi.org/10.1007/s10666-012-9333-3
  24. Luo, Y., K. Yang, Z.Y. Yu, J.Y. Chen, Y.F. Xu, X.L. Zhou and Y. Yang. 2017. Dynamic monitoring and prediction of Dianchi Lake cyanobacteria outbreaks in the context of rapid urbanization. Environmental Science and Pollution Research 24: 5335-5348. https://doi.org/10.1007/s11356-016-8155-2
  25. Maier, H.R. and G.C. Dandy. 2000. Neural networks for the prediction and forecasting of water resources variables: a review of modelling issues and applications. Environmental Modelling and Software 15: 101-124. https://doi.org/10.1016/S1364-8152(99)00007-9
  26. Millie, D.F., G.R. Weckman, G.L. Fahnenstiel, H.J. Carrick, E. Ardjmand, W.A. Young II, M.J. Sayers and R.A. Shuchman. 2014. Using artificial intelligence for cyanoHAB niche modeling: discovery and visualization of Microcystis-environmental associations within western Lake Erie. Canadian Journal of Fisheries and Aquatic Sciences 71: 1642-1654. https://doi.org/10.1139/cjfas-2013-0654
  27. Ministry of Environment-National Institute of Environmental Research (MOE-NIER). 2020. A Manual of Algal Alert System. NIER-GP2020-019. Incheon, Republic of Korea.
  28. Mitrovic, S.M., L. Hardwick and F. Dorani. 2010. Use of flow management to mitigate cyanobacterial blooms in the Lower Darling River, Australia. Journal of Plankton Research 33: 229-241. https://doi.org/10.1093/plankt/fbq094
  29. Moe, S.J., S. Haande and R.M. Couture. 2016. Climate change, cyanobacteria blooms and ecological status of lakes: a Bayesian network approach. Ecological Modelling 337: 330-347. https://doi.org/10.1016/j.ecolmodel.2016.07.004
  30. Mooij, W.M., D. Trolle, E. Jeppesen, G. Arhonditsis, P.V. Belolipetsky, D.B.R. Chitamwebwa, A.G. Degermendzhy, D,L. DeAngelis, L.N.D. Domis, A.S. Downing, J.A. Elliott, C.R. Fragoso, U. Gaedke, S.N. Genova, R.D. Gulati, L. Hakanson, D.P. Hamilton, M.R. Hipsey, J. 't Hoen, S. Hulsmann, F.H. Los, V. Makler-Pick, T. Petzoldt, I.G. Prokopkin, K. Rinke, S.A. Schep, K. Tominaga, A.A. van Dam, E.H. van Nes, S.A. Wells and J.H. Janse. 2010. Challenges and opportunities for integrating lake ecosystem modelling approaches. Aquatic Ecology 44: 633-667. https://doi.org/10.1007/s10452-010-9339-3
  31. Nichols, S., R. Norris, W. Maher and M. Thoms. 2006. Ecological effects of serial impoundment on the Cotter River, Australia. Hydrobiologia 572: 255-273. https://doi.org/10.1007/s10750-005-0995-6
  32. O'Hara, R.B. and D.J. Kotze. 2010. Do not log-transform count data. Methods in Ecology and Evolution 1: 118-122. https://doi.org/10.1111/j.2041-210X.2010.00021.x
  33. Office of Science and Technology Policy (OSTP). 2016. Harmful Algal Blooms and Hypoxia Comprehensive Research Plan and Action Strategy: An Interagency Report. National Science and Technology Council Subcommittee on Ocean Science and Technology, USA. 94p.
  34. Ostfeld, A., A. Tubaltzev, M. Rom, L. Kronaveter, T. Zohary and G. Gal. 2015. Coupled data-driven evolutionary algorithm for toxic cyanobacteria (blue-green algae) forecasting in Lake Kinneret. Journal of Water Resources Planning and Management 141: 04014069-13
  35. Paerl, H.W. 2014. Mitigating harmful cyanobacterial blooms in a human- and climatically-impacted World. Life 4: 988-1012. https://doi.org/10.3390/life4040988
  36. Paerl, H.W. and D.F. Millie. 1996. Physiological ecology of toxic aquatic cyanobacteria. Phycologia 35: 160-167. https://doi.org/10.2216/i0031-8884-35-6S-160.1
  37. Paerl, H.W. and J. Huisman. 2009. Climate change: a catalyst for global expansion of harmful cyanobacterial blooms. Environmental Microbiology Reports 1: 27-37. https://doi.org/10.1111/j.1758-2229.2008.00004.x
  38. Paerl, H.W. and T.G. Otten. 2013. Harmful cyanobacterial blooms: causes, consequences and controls. Microbial Ecology 65: 995-1010. https://doi.org/10.1007/s00248-012-0159-y
  39. Page, T., P.J. Smith, K.J. Beven, I.D. Jones, J.A. Elliott, S.C. Maberly, E.B. Mackay, M. De Ville and H. Feuchtmayr. 2018. Adaptive forecasting of phytoplankton communities. Water Research 134: 74-85. https://doi.org/10.1016/j.watres.2018.01.046
  40. Peters, D.P., K.M. Havstad, J. Cushing, C. Tweedie, O. Fuenres and N. Villanueva-Rosales. 2014. Harnessing the power of big data: Infusing the scientific method with machine learning to transform ecology. Ecosphere 5: 1-15. https://doi.org/10.1890/ES13-00359.1
  41. Qin, B., J. Deng, K. Shi, J. Wang, J. Brookes, J. Zhou, Y. Zhang, G. Zhu, H.W. Pearl and L. Wu. 2021. Extreme climate anomalies enhancing cyanobacterial blooms in eutrophic Lake Taihu, China. Water Resources Research 57: e2020WR029371.
  42. Qin, B., W. Li, G. Zhu, Y. Zhang, T. Wu and G. Gao. 2015. Cyanobacterial bloom management through integrated monitoring and forecasting in large shallow eutrophic Lake Taihu (China). Journal of Hazardous Materials 287: 356-363. https://doi.org/10.1016/j.jhazmat.2015.01.047
  43. Raps, S., K. Wyman, H.W. Siegelman and P.G. Falkowski. 1983. Adaptation of the cyanobacterium Microcystis aeruginosa to light intensity. Plant Physiology 72: 829-832. https://doi.org/10.1104/pp.72.3.829
  44. Recknagel, F., M. French, P. Harkonen and K.I. Yabunaka. 1997. Artificial neural network approach for modelling and prediction of algal blooms. Ecological Modelling 96: 11-28. https://doi.org/10.1016/S0304-3800(96)00049-X
  45. Recknagel, F., P.T. Orr and H.Q. Cao. 2014. Inductive reasoning and forecasting of population dynamics of Cylindrospermopsis raciborskii in three sub-tropical reservoirs by evolutionary computation. Harmful Algae 31: 26-34. https://doi.org/10.1016/j.hal.2013.09.004
  46. Recknagel, F., P.T. Orr, M. Bartkow, A. Swanepoel and H. Cao. 2017. Early warning of limit-exceeding concentrations of cyanobacteria and cyanotoxins in drinking water reservoirs by inferential modelling. Harmful Algae 69: 18-27. https://doi.org/10.1016/j.hal.2017.09.003
  47. Recknagel, F., T. Fukushima, T. Hanazato, N. Takamura and H. Wilson. 1998. Modelling and prediction of phyto- and zooplankton dynamics in Lake Kasumigaura by artificial neural networks. Lakes and Reservoirs: Research and Management 3: 123-133. https://doi.org/10.1111/j.1440-1770.1998.tb00039.x
  48. Reynolds, C.S. and A.E. Walsby. 1975. Water-blooms. Biological Reviews 50: 437-481. https://doi.org/10.1111/j.1469-185X.1975.tb01060.x
  49. Reynolds, C.S., R.L. Oliver and A.E. Walsby. 1987. Cyanobacterial dominance: the role of buoyancy regulation in dynamic lake environments. New Zealand Journal of Marine and Freshwater Research 21: 379-390. https://doi.org/10.1080/00288330.1987.9516234
  50. Rousso, B.Z., E. Bertone, R. Stewart and D.P. Hamilton. 2020. A systematic literature review of forecasting and predictive models for cyanobacteria blooms in freshwater lakes. Water Research 182: 115959.
  51. Schindler, D.W. 2012. The dilemma of controlling cultural eutrophication of lakes. Proceedings of The Royal Society B 279: 4322-4333. https://doi.org/10.1098/rspb.2012.1032
  52. Schuwirth, N., F. Borgwardt, S. Domisch, M. Friedrichs, M. Kattwinkel, D. Kneis, M. Kuemmerlen, S.D. Langhans, J. Martinez-Lopez and P. Vermeiren. 2019. How to make ecological models useful for environmental management. Ecological Modelling 411: 108784.
  53. Sheng, H., H. Liu, C. Wang, H. Guo, Y. Liu and Y. Yang. 2012. Analysis of cyanobacteria bloom in the Waihai part of Dianchi lake, China. Ecological Informatics 10: 37-48. https://doi.org/10.1016/j.ecoinf.2012.03.007
  54. Shin, J.K. and Y. Park. 2018. Spatiotemporal and longitudinal variability of hydro-meteorology, basic water quality and dominant algal assemblages in the eight weir pools of regulated river (Nakdong). Korean Journal of Ecology and Environment 51: 268-286. https://doi.org/10.11614/KSL.2018.51.4.268
  55. Shin, J.K., B.G. Kang and S.J. Hwang. 2016. Water-blooms (green-tide) dynamics of algae alert system and rainfall-hydrological effects in Daecheong Reservoir, Korea. Korean Journal of Ecology and Environment 49: 153-175. https://doi.org/10.11614/KSL.2016.49.3.153
  56. Shin, J.K., Y. Park, N.Y. Kim and S.J. Hwang. 2022. Downstream transport of geosmin based on harmful cyanobacterial outbreak upstream in a reservoir cascade. International Journal of Environmnetal Research and Public Health 19: 9294.
  57. Sibanda, M., O. Mutanga, V.G. Chimonyo, A.D. Clulow, C. Shoko, D. Mazvimavi, T. Dube and T. Mabhaudhi. 2021. Application of drone technologies in surface water resources monitoring and assessment: A systematic review of progress, challenges, and opportunities in the global south. Drones 5: 84.
  58. Summers, E.J. and J.L. Ryder. 2023. A critical review of operational strategies for the management of harmful algal blooms (HABs) in inland reservoirs. Journal of Environmental Management 330: 117141.
  59. Teles, L.O., E. Pereira, M. Saker and V. Vasconcelos. 2008. Virtual experimentation on cyanobacterial bloom dynamics and its application to a temperate reservoir (Torrao, Portugal). Lakes and Reservoirs: Research and Management 13: 135-143. https://doi.org/10.1111/j.1440-1770.2008.00362.x
  60. Tromas, N., N. Fortin, L. Bedrani, Y. Terrat, P. Cardoso, D. Bird, C.W. Greer and B.J. Shapiro. 2017. Characterising and predicting cyanobacterial blooms in an 8-year amplicon sequencing time course. The ISME (International Society for Microbial Ecology) Journal 11: 1746-1763. https://doi.org/10.1038/ismej.2017.58
  61. van Eck, N.J. and L. Waltman. 2007. Bibliometric mapping of the computational intelligence field. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems 15: 625-645. https://doi.org/10.1142/S0218488507004911
  62. van Eck, N.J. and L.Waltman. 2009. VOSviewer: A Computer Program for Bibliometric Mapping. Technical Report ERS2009-005-LIS, Erasmus University Rotterdam, Erasmus Research Institute of Management. Rotterdam, The Netherlands. 19p. http://hdl.handle.net/1765/14841
  63. van Eck, N.J. and L. Waltman. 2010. Software survey: VOSviewer, a computer program for bibliometric mapping. Scientometrics 84: 523-538. https://doi.org/10.1007/s11192-009-0146-3
  64. van Eck, N.J., L.R.Waltman, E.C.M. Noyons and R.K. Buter. 2010a. Automatic term identification for bibliometric mapping. Scientometrics 82: 581-596. https://doi.org/10.1007/s11192-010-0173-0
  65. van Eck, N.J., L.Waltman, R. Dekker and J. van den Berg. 2010b. A comparison of two techniques for bibliometric mapping: Multidimensional scaling and VOS. Journal of the American Society for Information Science and Technology 61: 2405-2416. https://doi.org/10.1002/asi.21421
  66. Waaijer, C.J.F., C.A. van Bochove and N.J. van Eck. 2011. On the map: Nature and Science editorials. Scientometrics 86: 99-112. https://doi.org/10.1007/s11192-010-0205-9
  67. Waltman, L., N.J. van Eck and E.C.M. Noyons. 2010. A unified approach to mapping and clustering of bibliometric networks. Journal of Informetrics 4: 629-635. https://doi.org/10.1016/j.joi.2010.07.002
  68. Wang, H., R. Zhu, J. Zhang, L.Y. Ni, H. Shen and P. Xie. 2018. A novel and convenient method for early warning of algal cell density by chlorophyll fluorescence parameters and its application in a highland lake. Frontiers in Plant Science 9: 869.
  69. Watanabe, M.F., K. Harada, W.W. Carmichael and H. Fujiki. 1996. Toxic Microcystis. CRC Press, Boca Raton, London, U.K. 262p.
  70. Wei, B., N. Sugiura and T. Maekawa. 2001. Use of artificial neural network in the prediction of algal blooms. Water Research 35: 2022-2028. https://doi.org/10.1016/S0043-1354(00)00464-4
  71. Welk, A., F. Recknagel, H. Cao, W.S. Chan and A. Talib. 2008. Rule-based agents for forecasting algal population dynamics in freshwater lakes discovered by hybrid evolutionary algorithms. Ecological Informatics 3: 46-54. https://doi.org/10.1016/j.ecoinf.2007.12.002
  72. Wilkinson, G.M., S.R. Carpenter, J.J. Cole, M.L. Pace, R.D. Batt, C.D. Buelo and J.T. Kurtzweil. 2018. Early warning signals precede cyanobacterial blooms in multiple whole-lake experiments. Ecological Monographs 88: 188-203. https://doi.org/10.1002/ecm.1286
  73. World Health Organization (WHO). 2011. Management of Cyanobacteria in Drinking-water Supplies: Information for Regulators and Water Suppliers. Technical Brief WHO/FWC/WSH/15.03. 11p.
  74. Xiao, X., J. He, H. Huang, T.R. Miller, G. Christakos, E.S. Reichwaldt, A. Ghadouani, S. Lin, X. Xu and J. Shi. 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
  75. Yabunaka, K., M. Hosomi and A. Murakami. 1997. Novel application of a backpropagation artificial neural network model formulated to predict algal bloom. Water Science and Technology 36: 89-97. https://doi.org/10.2166/wst.1997.0172