Prediction of cyanobacterial blooms in the Dau Tieng Reservoir using an artificial neural network

An artificial neural network (ANN) model was used to predict the cyanobacteria bloom in the Dau Tieng Reservoir, Vietnam. Eight environmental parameters (pH, dissolved oxygen, temperature, total dissolved solids, total nitrogen (TN), total phosphorus, biochemical oxygen demand and chemical oxygen demand) were introduced as inputs, whereas the cell density of three cyanobacteria genera (Anabaena, Microcystis and Oscillatoria) with microcystin concentrations were introduced as outputs of the three-layer feed-forward back-propagation ANN. Eighty networks covering all combinations of four learning algorithms (Bayesian regularisation (BR), gradient descent with momentum and adaptive learning rate, Levenberg–Mardquart, scaled conjugate gradient) with two transfer functions (tansig, logsig) and 10 numbers of hidden neurons (6–16) were trained and validated to find the best configuration fitting the observed data. The result is a network using the BR learning algorithm, tansig transfer function and nine neurons in the hidden layer, which shows satisfactory predictions with the low values of error (root mean square error=0.108) and high correlation coefficient values (R=0.904) between experimental and predicted values. Sensitivity analysis on the developed ANN indicated that TN and temperature had the most positive and negative effects respectively on microcystin concentrations. These results indicate that ANN modelling can effectively predict the behaviour of the cyanobacteria bloom process.

[1]  C. Cerco,et al.  A practical application of Droop nutrient kinetics (WR 1883). , 2004, Water research.

[2]  W. Ye,et al.  Diversity and dynamics of microcystin―Producing cyanobacteria in China's third largest lake, Lake Taihu , 2009 .

[3]  Pradyut Kundu,et al.  Artificial Neural Network Modeling for Biological Removal of Organic Carbon and Nitrogen from Slaughterhouse Wastewater in a Sequencing Batch Reactor , 2013, Adv. Artif. Neural Syst..

[4]  B. Sapiyan.  Supervised and unsupervised artificial neural networks for analysis of diatom abundance in tropical Putrajaya Lake, Malaysia , 2012 .

[5]  K. Gin,et al.  The dynamics of cyanobacteria and microcystin production in a tropical reservoir of Singapore , 2011 .

[6]  Siddhartha Datta,et al.  Artificial neural network modelling for removal of chromium (VI) from wastewater using physisorption onto powdered activated carbon , 2016 .

[7]  Thomas Rohrlack,et al.  Cyanobacteria and Cyanotoxins: The Influence of Nitrogen versus Phosphorus , 2012, PloS one.

[8]  T. Maekawa,et al.  Use of artificial neural network in the prediction of algal blooms. , 2001, Water research.

[9]  H. Bui,et al.  The use of artificial neural network for modeling coagulation of reactive dye wastewater using Cassia fistula Linn. (CF) gum , 2016 .

[10]  Wenhuai Luo,et al.  Estimating Cyanobacteria Community Dynamics and its Relationship with Environmental Factors , 2014, International journal of environmental research and public health.

[11]  K. Shimizu,et al.  Isolation and characterization of microcystin-producing cyanobacteria from Dau Tieng Reservoir, Vietnam , 2015 .

[12]  Jan-Tai Kuo,et al.  USING ARTIFICIAL NEURAL NETWORK FOR RESERVOIR EUTROPHICATION PREDICTION , 2007 .

[13]  M. Starr,et al.  An application of artificial neural networks to carbon, nitrogen and phosphorus concentrations in three boreal streams and impacts of climate change , 2006 .

[14]  P. Pakravan,et al.  Process modeling and evaluation of petroleum refinery wastewater treatment through response surface methodology and artificial neural network in a photocatalytic reactor using poly ethyleneimine (PEI)/titania (TiO2) multilayer film on quartz tube , 2015, Applied Petrochemical Research.

[15]  Anthony E. Walsby,et al.  Cyanobacterial dominance: the role of buoyancy regulation in dynamic lake environments , 1987 .

[16]  Tzu-Yi Pai,et al.  Predicting effluent from the wastewater treatment plant of industrial park based on fuzzy network and influent quality , 2011 .

[17]  S. Lek,et al.  Predicting stream nitrogen concentration from watershed features using neural networks , 1999 .

[18]  A. Khataee,et al.  The use of artificial neural networks (ANN) for modeling of decolorization of textile dye solution containing C. I. Basic Yellow 28 by electrocoagulation process. , 2006, Journal of hazardous materials.

[19]  Hua-Se Ou,et al.  Sequential dynamic artificial neural network modeling of a full-scale coking wastewater treatment plant with fluidized bed reactors , 2015, Environmental Science and Pollution Research.

[20]  G. Sahoo,et al.  Application of artificial neural networks to assess pesticide contamination in shallow groundwater. , 2006, Science of the Total Environment.

[21]  H. Paerl,et al.  Climate change: links to global expansion of harmful cyanobacteria. , 2012, Water research.

[22]  Theodore D. Harris,et al.  Experimental manipulation of TN:TP ratios suppress cyanobacterial biovolume and microcystin concentration in large-scale in situ mesocosms , 2014 .

[23]  A. E. Irish,et al.  The ecological basis for simulating phytoplankton responses to environmental change (PROTECH) , 2001 .

[24]  M. He,et al.  Extracellular microcystin prediction based on toxigenic Microcystis detection in a eutrophic lake , 2016, Scientific Reports.

[25]  H. Oh,et al.  Correlations between environmental factors and toxic and non-toxic Microcystis dynamics during bloom in Daechung Reservoir, Korea , 2011 .

[26]  M. Hosomi,et al.  Novel application of a back-propagation artificial neural network model formulated to predict algal bloom , 1997 .

[27]  E. Baurès,et al.  State of knowledge and concerns on cyanobacterial blooms and cyanotoxins. , 2013, Environment international.

[28]  Ashwani Kumar Thukral,et al.  RSM and ANN modeling for electrocoagulation of copper from simulated wastewater: Multi objective optimization using genetic algorithm approach , 2011 .

[29]  J. Eloff,et al.  Effect of temperature and light on the toxicity and growth of the blue-green alga Microcystis aeruginosa (UV-006) , 2004, Planta.

[30]  R. Lim,et al.  Tropical cyanobacterial blooms: a review of prevalence, problem taxa, toxins and influencing environmental factors , 2014 .

[31]  J. Yu,et al.  MIB-producing cyanobacteria (Planktothrix sp.) in a drinking water reservoir: distribution and odor producing potential. , 2015, Water research.

[32]  Iván Machón,et al.  Simulation of a coke wastewater nitrification process using a feed-forward neuronal net , 2007, Environ. Model. Softw..

[33]  A. E. Irish,et al.  Modelling phytoplankton dynamics in lakes and reservoirs: the problem of in-situ growth rates , 1997, Hydrobiologia.

[34]  T. Felföldi,et al.  Appearance of Planktothrix rubescens Bloom with [D-Asp3, Mdha7]MC–RR in Gravel Pit Pond of a Shallow Lake-Dominated Area , 2013, Toxins.

[35]  H. Merdun,et al.  Artificial neural network and regression techniques in modelling surface water quality , 2010 .

[36]  A. Hosseinzadeh Colagar,et al.  Removal of Cd(II) from Aquatic System Using Oscillatoria sp. Biosorbent , 2012, TheScientificWorldJournal.

[37]  Mahmoud Nasr,et al.  Application of Artificial Neural Network (ANN) for the prediction of EL-AGAMY wastewater treatment plant performance-EGYPT , 2012 .

[38]  D. Wunderlin,et al.  Effects of Iron, Ammonium and Temperature on Microcystin Content by a Natural Concentrated Microcystis Aeruginosa Population , 2005 .

[39]  B. Beisner,et al.  Nitrogen Forms Influence Microcystin Concentration and Composition via Changes in Cyanobacterial Community Structure , 2014, PloS one.

[40]  K. Chau,et al.  A hybrid model coupled with singular spectrum analysis for daily rainfall prediction , 2010 .

[41]  Holger R. Maier,et al.  Neural networks for the prediction and forecasting of water resource variables: a review of modelling issues and applications , 2000, Environ. Model. Softw..