Research on the Development and Application of a Deep Learning Model for Effective Management and Response to Harmful Algal Blooms

Harmful algal blooms (HABs) caused by harmful cyanobacteria adversely impact the water quality in aquatic ecosystems and burden socioecological systems that are based on water utilization. Currently, Korea uses the Environmental Fluid Dynamics Code-National Institute of Environmental Research (EFDC-NIER) model to predict algae conditions and respond to algal blooms through the HAB alert system. This study aimed to establish an additional deep learning model to effectively respond to algal blooms. The prediction model is based on a deep neural network (DNN), which is a type of artificial neural network widely used for HAB prediction. By applying the synthetic minority over-sampling technique (SMOTE) to resolve the imbalance in the data, the DNN model showed improved performance during validation for predicting the number of cyanobacteria cells. The R-squared increased from 0.7 to 0.78, MAE decreased from 0.7 to 0.6, and RMSE decreased from 0.9 to 0.7, indicating an enhancement in the model’s performance. Furthermore, regarding the HAB alert levels, the R-squared increased from 0.18 to 0.79, MAE decreased from 0.2 to 0.1, and RMSE decreased from 0.3 to 0.2, indicating improved performance as well. According to the results, the constructed data-based model reasonably predicted algae conditions in the summer when algal bloom-induced damage occurs and accurately predicted the HAB alert levels for immediate decision-making. The main objective of this study was to develop a new technology for predicting and managing HABs in river environments, aiming for a sustainable future for the aquatic ecosystem.

[1]  H. Paerl,et al.  Ancient DNA reveals potentially toxic cyanobacteria increasing with climate change. , 2023, Water research.

[2]  W. K. Ngui,et al.  Weather Impact on Solar Farm Performance: A Comparative Analysis of Machine Learning Techniques , 2022, Sustainability.

[3]  Chengsheng Pan,et al.  An oversampling method for imbalanced data based on spatial distribution of minority samples SD-KMSMOTE , 2022, Scientific Reports.

[4]  B. Deepanraj,et al.  A novel optimization approach for biohydrogen production using algal biomass , 2022, International Journal of Hydrogen Energy.

[5]  J. Ni,et al.  An Improved Attention-based Bidirectional LSTM Model for Cyanobacterial Bloom Prediction , 2022, International Journal of Control, Automation and Systems.

[6]  Ali El Bilali,et al.  A framework based on multivariate distribution-based virtual sample generation and DNN for predicting water quality with small data , 2022, Journal of Cleaner Production.

[7]  Jungwook Kim,et al.  Oscillation Flow Dam Operation Method for Algal Bloom Mitigation , 2022, Water.

[8]  Xia Li,et al.  Water quality forecasting based on data decomposition, fuzzy clustering and deep learning neural network. , 2022, Environmental pollution.

[9]  Mohamed A. Hamouda,et al.  Uncertainty quantification of granular computing-neural network model for prediction of pollutant longitudinal dispersion coefficient in aquatic streams , 2021, Scientific Reports.

[10]  Dibakar Rakshit,et al.  Artificial neural network coupled building-integrated photovoltaic thermal system for indian montane climate , 2021 .

[11]  Sanghyung Park,et al.  Cyanobacteria cell prediction using interpretable deep learning model with observed, numerical, and sensing data assemblage. , 2021, Water research.

[12]  Qingyu Xiong,et al.  A study on water quality prediction by a hybrid CNN-LSTM model with attention mechanism , 2021, Environmental Science and Pollution Research.

[13]  Sheila M. Olmstead,et al.  Protecting local water quality has global benefits , 2021, Nature Communications.

[14]  Ibrahim Demir,et al.  An ethical decision-making framework with serious gaming: a smart water case study on flooding , 2021 .

[15]  Taegu Kang,et al.  Predicting Cyanobacterial Harmful Algal Blooms (CyanoHABs) in a Regulated River Using a Revised EFDC Model , 2021, Water.

[16]  Taegu Kang,et al.  Predicting Cyanobacterial Blooms Using Hyperspectral Images in a Regulated River , 2021, Sensors.

[17]  R. Noori,et al.  Caspian Sea is eutrophying: the alarming message of satellite data , 2020, Environmental Research Letters.

[18]  Saahil Afaq,et al.  Significance Of Epochs On Training A Neural Network , 2020 .

[19]  Muhammed Sit,et al.  A Comprehensive Review of Deep Learning Applications in Hydrology and Water Resources , 2020, Water science and technology : a journal of the International Association on Water Pollution Research.

[20]  Jose Olmo,et al.  Optimal Deep Neural Networks by Maximization of the Approximation Power , 2020, Comput. Oper. Res..

[21]  Z. Hua,et al.  A combination method for multicriteria uncertainty analysis and parameter estimation: a case study of Chaohu Lake in Eastern China , 2020, Environmental Science and Pollution Research.

[22]  Inhyeok Yim,et al.  Deep learning-based retrieval of cyanobacteria pigment in inland water for in-situ and airborne hyperspectral data , 2020 .

[23]  Jenny L. Davis,et al.  Attributions of ethical responsibility by Artificial Intelligence practitioners , 2020 .

[24]  K. Crawford,et al.  Enchanted Determinism: Power without Responsibility in Artificial Intelligence , 2020 .

[25]  Richard Alan Peters,et al.  A Review of Deep Learning with Special Emphasis on Architectures, Applications and Recent Trends , 2019, Knowl. Based Syst..

[26]  Tarun Kumar Gupta,et al.  Optimizing Deep Feedforward Neural Network Architecture: A Tabu Search Based Approach , 2018, Neural Processing Letters.

[27]  Xinzhong Du,et al.  Developing a non-point source P loss indicator in R and its parameter uncertainty assessment using GLUE: a case study in northern China , 2018, Environmental Science and Pollution Research.

[28]  Yiping Li,et al.  Parameter uncertainty and sensitivity analysis of water quality model in Lake Taihu, China , 2018 .

[29]  D. Cressey.  Climate change is making algal blooms worse , 2017, Nature.

[30]  Miltiadis Petridis,et al.  On the Optimal Node Ratio between Hidden Layers: A Probabilistic Study , 2016 .

[31]  Yiping Li,et al.  Modeling the effects of external nutrient reductions on algal blooms in hyper-eutrophic Lake Taihu, China , 2016 .

[32]  A. Giani,et al.  Microcystin Production and Regulation under Nutrient Stress Conditions in Toxic Microcystis Strains , 2014, Applied and Environmental Microbiology.

[33]  T. Chai,et al.  Root mean square error (RMSE) or mean absolute error (MAE)? – Arguments against avoiding RMSE in the literature , 2014 .

[34]  Zongxue Xu,et al.  Prediction of algal blooming using EFDC model: Case study in the Daoxiang Lake , 2011 .

[35]  Juan Carlos Gutiérrez-Estrada,et al.  Artificial neural network approaches to one-step weekly prediction of Dinophysis acuminata blooms in Huelva (Western Andalucía, Spain) , 2007 .

[36]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[37]  Friedrich Recknagel,et al.  Ecological Informatics: Scope, Techniques and Applications , 2006 .

[38]  C. Willmott,et al.  Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance , 2005 .

[39]  Hui Han,et al.  Borderline-SMOTE: A New Over-Sampling Method in Imbalanced Data Sets Learning , 2005, ICIC.

[40]  H. Oh,et al.  Microcystin Production by Microcystis aeruginosa in a Phosphorus-Limited Chemostat , 2000, Applied and Environmental Microbiology.

[41]  Nguyen Thai-Nghe,et al.  Deep Learning Approach for Forecasting Water Quality in IoT Systems , 2020, International Journal of Advanced Computer Science and Applications.

[42]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[43]  S. Karsoliya,et al.  Approximating Number of Hidden layer neurons in Multiple Hidden Layer BPNN Architecture , 2012 .

[44]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[45]  Holger R. Maier,et al.  Use of artificial neural networks for modelling cyanobacteria Anabaena spp. in the River Murray, South Australia , 1998 .