Estimation of dissolved oxygen by using neural networks and neuro fuzzy computing techniques

Dissolved oxygen, one of the most important water quality parameters, is a crucial parameter for the aquatic ecosystems. In this study, some advanced chemometric techniques included in a multi-layer perceptron, radial basis neural network, and two different adaptive neuro-fuzzy inference system methods are developed to model dissolved oxygen concentration. Moreover the estimations of these models are compared with the multiple linear regression. In this context, monthly mean quantities of the temperature, pH, electrical conductivity, discharge and dissolved oxygen data recorded at Broad River near Carlisle, SC in USA are used. The accuracy of the models is compared with one other by using determination coefficient, mean absolute error, root mean square error and mean absolute relative error statistics. Results indicate that radial basis neural network method performs better than the other methods in modelling monthly mean dissolved oxygen concentration. The temperature, pH, electrical conductivity, and discharge are found to be effective on dissolved oxygen concentration.

[1]  Christian W. Dawson,et al.  An artificial neural network approach to rainfall-runoff modelling , 1998 .

[2]  William Ocampo-Duque,et al.  Assessing water quality in rivers with fuzzy inference systems: a case study. , 2006, Environment international.

[3]  Chuanqi Zhang,et al.  Artificial neural network modeling of dissolved oxygen in the Heihe River, Northwestern China , 2013, Environmental Monitoring and Assessment.

[4]  T. Ross.  Fuzzy Logic with Engineering Applications , 1994 .

[5]  D. Broomhead,et al.  Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks , 1988 .

[6]  Arash Adib,et al.  Prediction of suspended sediment load using ANN GA conjunction model with Markov chain approach at flood conditions , 2017 .

[7]  H. K. Cigizoglu,et al.  Depth-Integrated Estimation of Dissolved Oxygen in a Lake , 2011 .

[8]  Bernhard H. Schmid,et al.  Artificial Neural Network Modeling of Dissolved Oxygen in a Wetland Pond: The Case of Hovi, Finland , 2006 .

[9]  Lotfi A. Zadeh,et al.  Fuzzy Sets , 1996, Inf. Control..

[10]  B A Cox,et al.  A review of dissolved oxygen modelling techniques for lowland rivers. , 2003, The Science of the total environment.

[11]  V. Garg,et al.  Analysis of groundwater quality using fuzzy synthetic evaluation. , 2007, Journal of hazardous materials.

[12]  P. M. Berthouex,et al.  Statistics for Environmental Engineers, Second Edition , 2002 .

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

[14]  Chidchanok Lursinsap,et al.  Integration of unsupervised and supervised neural networks to predict dissolved oxygen concentration in canals , 2013 .

[15]  Michio Sugeno,et al.  Fuzzy identification of systems and its applications to modeling and control , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[16]  Shie-Yui Liong,et al.  An ANN application for water quality forecasting. , 2008, Marine pollution bulletin.

[17]  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..

[18]  Julio J. Valdés,et al.  Computational intelligence in earth sciences and environmental applications: Issues and challenges , 2006, Neural Networks.

[19]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[20]  Jasna Radulović,et al.  Neural network modeling of dissolved oxygen in the Gruža reservoir, Serbia , 2010 .

[21]  Ozgur Kisi,et al.  Modeling of Dissolved Oxygen Concentration Using Different Neural Network Techniques in Foundation Creek, El Paso County, Colorado , 2012 .

[22]  J. Downing,et al.  Limnology: Inland Water Ecosystems , 2016 .

[23]  Salim Heddam,et al.  Modeling hourly dissolved oxygen concentration (DO) using two different adaptive neuro-fuzzy inference systems (ANFIS): a comparative study , 2013, Environmental Monitoring and Assessment.

[24]  Muhammad Zeeshan,et al.  A comparison of Artificial Neural Networks (ANN) and Local Linear Regression (LLR) techniques for predicting monthly reservoir levels , 2015, KSCE Journal of Civil Engineering.

[25]  Darinka Brodnjak-Vončina,et al.  Chemometrics characterisation of the quality of river water , 2002 .

[26]  E. Doğan,et al.  Modeling biological oxygen demand of the Melen River in Turkey using an artificial neural network technique. , 2009, Journal of environmental management.

[27]  Yilmaz Icaga,et al.  Fuzzy evaluation of water quality classification , 2007 .

[28]  Dong-Hoon Park,et al.  Fuzzy expert system to determine stream water quality classification from ecological information , 1997 .

[29]  Linfield Brown,et al.  Statistics for Environmental Engineers , 2002 .

[30]  P P Mujumdar,et al.  An imprecise fuzzy risk approach for water quality management of a river system. , 2009, Journal of environmental management.

[31]  Ahmed El-Shafie,et al.  Performance of ANFIS versus MLP-NN dissolved oxygen prediction models in water quality monitoring , 2014, Environmental Science and Pollution Research.

[32]  A. Malik,et al.  Artificial neural network modeling of the river water quality—A case study , 2009 .

[33]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[34]  J. Hem.  Study and Interpretation of the Chemical Characteristics of Natural Water , 1989 .

[35]  T Poggio,et al.  Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks , 1990, Science.

[36]  Han Yan,et al.  Adaptive neuro fuzzy inference system for classification of water quality status. , 2010, Journal of environmental sciences.

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