Multilayer perceptron neural network-based approach for modeling phycocyanin pigment concentrations: case study from lower Charles River buoy, USA

This paper proposes multilayer perceptron neural network (MLPNN) to predict phycocyanin (PC) pigment using water quality variables as predictor. In the proposed model, four water quality variables that are water temperature, dissolved oxygen, pH, and specific conductance were selected as the inputs for the MLPNN model, and the PC as the output. To demonstrate the capability and the usefulness of the MLPNN model, a total of 15,849 data measured at 15-min (15 min) intervals of time are used for the development of the model. The data are collected at the lower Charles River buoy, and available from the US Environmental Protection Agency (USEPA). For comparison purposes, a multiple linear regression (MLR) model that was frequently used for predicting water quality variables in previous studies is also built. The performances of the models are evaluated using a set of widely used statistical indices. The performance of the MLPNN and MLR models is compared with the measured data. The obtained results show that (i) the all proposed MLPNN models are more accurate than the MLR models and (ii) the results obtained are very promising and encouraging for the development of phycocyanin-predictive models.

[1]  R. Zurawell,et al.  Microcystin-LR concentration in aquatic food web compartments from lakes of varying trophic status , 1996 .

[2]  H. Maier,et al.  The Use of Artificial Neural Networks for the Prediction of Water Quality Parameters , 1996 .

[3]  G. David Garson,et al.  Interpreting neural-network connection weights , 1991 .

[4]  J. Nazuno.  Haykin, Simon. Neural networks: A comprehensive foundation, Prentice Hall, Inc. Segunda Edición, 1999 , 2000 .

[5]  P. Atkinson,et al.  Introduction Neural networks in remote sensing , 1997 .

[6]  T. Puzyn,et al.  Investigating the influence of data splitting on the predictive ability of QSAR/QSPR models , 2011 .

[7]  Karen M. Beaulieu,et al.  Environmental Factors that Influence Cyanobacteria and Geosmin Occurrence in Reservoirs , 2013 .

[8]  Russell G. Death,et al.  An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data , 2004 .

[9]  R. P. Stumpf,et al.  Relating spectral shape to cyanobacterial blooms in the Laurentian Great Lakes , 2008 .

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

[11]  Holger R. Maier,et al.  Forecasting cyanobacterium Anabaena spp. in the River Murray, South Australia, using B-spline neurofuzzy models , 2001 .

[12]  Lin Li,et al.  Using hyperspectral remote sensing to estimate chlorophyll‐a and phycocyanin in a mesotrophic reservoir , 2010 .

[13]  C. Willmott.  Some Comments on the Evaluation of Model Performance , 1982 .

[14]  Salim Heddam,et al.  Predicting Effluent Biochemical Oxygen Demand in a Wastewater Treatment Plant Using Generalized Regression Neural Network Based Approach: A Comparative Study , 2016, Environmental Processes.

[15]  Christian W. Dawson,et al.  Hydrological modelling using artificial neural networks , 2001 .

[16]  M. Gevrey,et al.  Review and comparison of methods to study the contribution of variables in artificial neural network models , 2003 .

[17]  E. Welch,et al.  Environmental factors associated with a toxic bloom of Microcystis aeruginosa , 2000 .

[18]  H. Kenneth Hudnell.  Comprar Cyanobacterial Harmful Algal Blooms · State of the Science and Research Needs | Hudnell, H. Kenneth | 9780387758640 | Springer , 2008 .

[19]  Holger R. Maier,et al.  Data transformation for neural network models in water resources applications , 2003 .

[20]  G. Boyer,et al.  Lake Erie Microcystis: Relationship between microcystin production, dynamics of genotypes and environmental parameters in a large lake , 2009 .

[21]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[22]  Yong Zha,et al.  Remote sensing of phycocyanin pigment in highly turbid inland waters in Lake Taihu, China , 2011 .

[23]  Mark Beale,et al.  Neural Network Toolbox™ User's Guide , 2015 .

[24]  E. Prepas,et al.  VARIABILITY OF THE HEPATOTOXIN MICROCYSTIN‐LR IN HYPEREUTROPHIC DRINKING WATER LAKES 1 , 1995 .

[25]  Seyoum Y. Gebremariam,et al.  A comprehensive approach to evaluating watershed models for predicting river flow regimes critical to downstream ecosystem services , 2014, Environ. Model. Softw..

[26]  Zongming Wang,et al.  Remote estimation of soil organic matter content in the Sanjiang Plain, Northest China: The optimal band algorithm versus the GRA-ANN model , 2016 .

[27]  Jeffrey G. Arnold,et al.  Model Evaluation Guidelines for Systematic Quantification of Accuracy in Watershed Simulations , 2007 .

[28]  I. Baudin,et al.  A phycocyanin probe as a tool for monitoring cyanobacteria in freshwater bodies. , 2008, Journal of environmental monitoring : JEM.

[29]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[30]  S. Heddam,et al.  ANFIS-based modelling for coagulant dosage in drinking water treatment plant: a case study , 2012, Environmental Monitoring and Assessment.

[31]  Deyong Sun,et al.  Specific absorption coefficient and the phytoplankton package effect in Lake Taihu, China , 2009, Hydrobiologia.

[32]  Robert E. Davis,et al.  Statistics for the evaluation and comparison of models , 1985 .

[33]  Stefan G. H. Simis,et al.  Remote sensing of the cyanobacterial pigment phycocyanin in turbid inland water , 2005 .

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

[35]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[36]  Mansoor Zoveidavianpoor,et al.  Adaptive neuro fuzzy inference system for compressional wave velocity prediction in a carbonate reservoir , 2013 .

[37]  Deyong Sun,et al.  A novel support vector regression model to estimate the phycocyanin concentration in turbid inland waters from hyperspectral reflectance , 2011, Hydrobiologia.

[38]  Salim Heddam,et al.  Secchi Disk Depth Estimation from Water Quality Parameters: Artificial Neural Network versus Multiple Linear Regression Models? , 2016, Environmental Processes.

[39]  Craig S. Tucker,et al.  HIGH‐RESOLUTION AIRBORNE REMOTE SENSING OF BLOOM‐FORMING PHYTOPLANKTON 1 , 1992 .

[40]  P. G. Thiel,et al.  Environmental factors affecting the production of peptide toxins in floating scums of the cyanobacterium Microcystis aeruginosa in a hypertrophic African reservoir , 1990 .

[41]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[42]  Julian D. Olden,et al.  Illuminating the “black box”: a randomization approach for understanding variable contributions in artificial neural networks , 2002 .

[43]  Jamie Bartram,et al.  Toxic Cyanobacteria in Water: a Guide to Their Public Health Consequences, Monitoring and Management Chapter 2. Cyanobacteria in the Environment 2.1 Nature and Diversity 2.1.1 Systematics , 2022 .

[44]  D. Legates,et al.  Evaluating the use of “goodness‐of‐fit” Measures in hydrologic and hydroclimatic model validation , 1999 .

[45]  Christian W. Dawson,et al.  Evaluation of artificial neural network techniques for flow forecasting in the River Yangtze , China 619 , 2002 .

[46]  Holger R. Maier,et al.  Forecasting chlorine residuals in a water distribution system using a general regression neural network , 2006, Math. Comput. Model..

[47]  Salim Heddam,et al.  Modelling hourly dissolved oxygen concentration (DO) using dynamic evolving neural-fuzzy inference system (DENFIS)-based approach: case study of Klamath River at Miller Island Boat Ramp, OR, USA , 2014, Environmental Science and Pollution Research.

[48]  J. Nash,et al.  River flow forecasting through conceptual models part I — A discussion of principles☆ , 1970 .

[49]  Martin F. Lambert,et al.  Calibration and validation of neural networks to ensure physically plausible hydrological modeling , 2005 .

[50]  Timothy Masters,et al.  Practical neural network recipes in C , 1993 .

[51]  Holger R. Maier,et al.  Optimal division of data for neural network models in water resources applications , 2002 .

[52]  R. Maccoll,et al.  Cyanobacterial phycobilisomes , 1998, Journal of structural biology.

[53]  K. P. Sudheer,et al.  Methods used for the development of neural networks for the prediction of water resource variables in river systems: Current status and future directions , 2010, Environ. Model. Softw..

[54]  P. Coulibaly,et al.  Two decades of anarchy? Emerging themes and outstanding challenges for neural network river forecasting , 2012 .

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

[56]  Grady Hanrahan,et al.  Artificial Neural Networks in Biological and Environmental Analysis , 2011 .

[57]  Peter Blomqvist,et al.  Factors determining cyanobacterial success in aquatic systems: A literature review , 1998 .