Modelling Phytoplankton Behaviour in the North and Irish Sea with Transformer Networks


  • Onatkut Dagtekin University of Hull
  • Nina Dethlefs University of Hull



deep learning, algal bloom, time series, explainability


Climate change will affect how water sources are managed and monitored. Continuous monitoring of water quality is crucial to detect pollution, to ensure that various natural cycles are not disrupted by anthropogenic activities and to assess the effectiveness of beneficial management measures taken under defined protocols. One such disruption is algal blooms in which population of phytoplankton increase rapidly affecting biodiversity in marine environments. The frequency of algal blooms will increase with climate change as it presents favourable conditions for reproduction of phytoplankton. Machine learning has been used for early detection of algal blooms previously, with the focus mostly on single closed bodies of water in Far East Asia with short time ranges. In this work, we study four locations around the North Sea and the Irish Sea with different characteristics predicting activity with longer time-spans and explaining the importance of the input with regard to the output of the prediction model. This work aids domain experts to monitor potential changes to the ecosystem over longer time ranges and to take action when necessary.


D. M. Anderson, E. Fensin, C. J. Gobler, A. E. Hoeglund, K. A. Hubbard, D. M. Kulis, J. H. Landsberg, K. A. Lefebvre, P. Provoost, M. L. Richlen, et al. Marine harmful algal blooms (habs) in the united states: history, current status and future trends. Harmful Algae, 102:101975, 2021. doi:10.1016/j.hal.2021.101975.

A. Bechard. The economic impacts of harmful algal blooms on tourism: an examination of southwest florida using a spline regression approach. Natural Hazards, 104(1):593– 609, 2020. doi:10.1007/s11069-020-04182-7.

A. N. Blauw, E. Beninca, R. W. Laane, N. Greenwood, and J. Huisman. Dancing with the tides: fluctuations of coastal phytoplankton orchestrated by different oscillatory modes of the tidal cycle. PLoS One, 7(11), 2012. doi:10.1371/journal.pone.0049319.

H. Cho and H. Park. Merged-lstm and multistep prediction of daily chlorophyll-a concentration for algal bloom forecast. In IOP Conference Series: Earth and Environmental Science, volume 351, page 012020. IOP Publishing, 2019. doi: 10.1088/1755-1315/351/1/012020.

H. Cho, U. Choi, and H. Park. Deep learning application to time-series prediction of daily chlorophyll-a concentration. WIT Trans. Ecol. Environ., 215:157–63, 2018. doi:10.2495/EID180141.

S. Cho, B. Lim, J. Jung, S. Kim, H. Chae, J. Park, S. Park, and J. K. Park. Factors affecting algal blooms in a man-made lake and prediction using an artificial neural network. Measurement, 53:224–233, 2014. doi:10.1016/j.measurement.2014.03.044.

W. K. Dodds, W. W. Bouska, J. L. Eitzmann, T. J. Pilger, K. L. Pitts, A. J. Riley, J. T. Schloesser, and D. J. Thornbrugh. Eutrophication of us freshwaters: analysis of potential economic damages, 2009. doi:10.1021/es801217q.

I. R. Falconer, M. D. Burch, D. A. Steffensen, M. Choice, and O. R. Coverdale. Toxicity of the blue-green alga (cyanobacterium) microcystis aeruginosa in drinking water to growing pigs, as an animal model for human injury and risk assessment. Environmental toxicology and Water quality, 9(2):131–139, 1994. doi:10.1002/tox.2530090209.

H. E. Garcia and L. I. Gordon. Oxygen solubility in seawater: Better fitting equations. Limnology and oceanography, 37(6):1307–1312, 1992. doi:10.4319/lo.1992.37.6.1307.

A. N. Blauw, E. Beninca, R. W. Laane, N. Greenwood, and J. Huisman. Predictability and environmental drivers of chlorophyll fluctuations vary across different time scales and regions of the north sea. Progress in Oceanography, 161:1–18, 2018. doi:10.1016/j.pocean.2018.01.005.

M. F. Chislock, E. Doster, R. A. Zitomer, and A. E. Wilson. Eutrophication: causes, consequences, and controls in aquatic ecosystems. Nature Education Knowledge, 4(4): 10, 2013.

H. Gu, Y. Wu, S. Lu, D. Lu, Y. Z. Tang, and Y. Qi. Emerging harmful algal bloom species over the last four decades in china. Harmful Algae, page 102059, 2021. doi:10.1016/j.hal.2021.102059.

J. Heffernan, J. Barry, M. Devlin, and R. Fryer. A simulation tool for designing nutrient monitoring programmes for eutrophication assessments. Environmetrics: The official journal of the International Environmetrics Society, 21 (1):3–20, 2010. doi:10.1002/env.980.

M. Kahru and B. G. Mitchell. Ocean color reveals increased blooms in various parts of the world. Eos, Transactions American Geophysical Union, 89(18):170–170, 2008. doi:10.1029/2008EO180002.

B. Karlson, P. Andersen, L. Arneborg, A. Cembella, W. Eikrem, U. John, J. J. West, K. Klemm, J. Kobos, S. Lehtinen, et al. Harmful algal blooms and their effects in coastal seas of northern europe. Harmful Algae, page 101989, 2021. doi:10.1016/j.hal.2021.101989.

S. M. Kazemi, R. Goel, S. Eghbali, J. Ramanan, J. Sahota, S. Thakur, S. Wu, C. Smyth, P. Poupart, and M. Brubaker. Time2vec: Learning a vector representation of time. arXiv preprint arXiv:1907.05321, 2019.

D. P. Kingma and J. Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.

J. R. Lepock. How do cells respond to their thermal environment? International journal of hyperthermia, 21(8): 681–687, 2005. doi:10.1080/02656730500307298.

X. Li, J. Yu, Z. Jia, and J. Song. Harmful algal blooms prediction with machine learning models in tolo harbour. In 2014 International Conference on Smart Computing, pages 245–250. IEEE, 2014. doi:10.1109/SMARTCOMP.2014.7043865.

M. L. Wells, V. L. Trainer, T. J. Smayda, B. S. Karlson, C. G. Trick, R. M. Kudela, A. Ishikawa, S. Bernard, A. Wulff, D. M. Anderson, et al. Harmful algal blooms and climate change: Learning from the past and present to forecast the future. Harmful algae, 49:68–93, 2015. doi:10.1016/j.hal.2015.07.009.

H. Yajima and J. Derot. Application of the random forest model for chlorophyll-a forecasts in fresh and brackish water bodies in japan, using multivariate long-term databases. Journal of Hydroinformatics, 20(1):206–220, 2018. doi:10.2166/hydro.2017.010.

Y. Yang, Y. Bai, X. Wang, L. Wang, X. Jin, and Q. Sun. Group decision-making support for sustainable governance of algal bloom in urban lakes. Sustainability, 12(4):1494, 2020. doi:10.3390/su12041494.

H.-S. Yi, S. Park, K.-G. An, and K.-C. Kwak. Algal bloom prediction using extreme learning machine models at artificial weirs in the nakdong river, korea. International journal of environmental research and public health, 15 (10):2078, 2018. doi:10.3390/ijerph15102078.

Z. Yu, K. Yang, Y. Luo, and C. Shang. Spatial-temporal process simulation and prediction of chlorophyll-a concentration in dianchi lake based on wavelet analysis and long-short term memory network. Journal of Hydrology, 582:124488, 2020. doi:10.1016/j.jhydrol.2019.124488.

N. Mellios, S. J. Moe, and C. Laspidou. Machine learning approaches for predicting health risk of cyanobacterial blooms in northern european lakes. Water, 12(4):1191, 2020. doi:10.3390/w12041191.

Y. Park, K. H. Cho, J. Park, S. M. Cha, and J. H. Kim. Development of early-warning protocol for predicting chlorophyll-a concentration using machine learning models in freshwater and estuarine reservoirs, korea. Science of the Total Environment, 502:31–41, 2015. doi:10.1016/j.scitotenv.2014.09.005.

M.-T. Sebastia-Frasquet, J.-A. Aguilar-Maldonado, I. Herrero-Dura, E. Santamarıa-del Angel, S. Morell-Monzo, and J. Estornell. Advances in the monitoring of algal blooms by remote sensing: A bibliometric analysis. Applied Sciences, 10(21):7877, 2020. doi:10.3390/app10217877.

S. Shamshirband, E. Jafari Nodoushan, J. E. Adolf, A. Abdul Manaf, A. Mosavi, and K.-w. Chau. Ensemble models with uncertainty analysis for multi-day ahead forecasting of chlorophyll a concentration in coastal waters. Engineering Applications of Computational Fluid Mechanics, 13(1): 91–101, 2019. doi:10.1080/19942060.2018.1553742.

A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin. Attention is all you need. In Advances in neural information processing systems, pages 5998–6008, 2017. 06.03762.

K. Von Schuckmann, P.-Y. Le Traon, N. Smith, A. Pascual, S. Djavidnia, J.-P. Gattuso, M. Gregoire, G. Nolan, S. Aaboe, E. A. Fanjul, et al. Copernicus marine service ocean state report, issue 4. Journal of Operational Oceanography, 13(sup1):S1–S172, 2020. doi:10.1080/1755876X.2020.1785097.

X. Wang and L. Xu. Unsteady multi-element time series analysis and prediction based on spatial-temporal attention and error forecast fusion. Future Internet, 12(2):34, 2020. doi:10.3390/fi12020034.