Modelling constructed wetland treatment system performance

Multiple regression analysis (MRA) and two artificial neural networks (ANN) – multilayer perceptron (MLP) and radial basis function network (RBF) – were compared in terms of their accuracy and efficiency when applied to prediction of the biochemical oxygen demand (BOD) concentration at effluent and intermediate points of subsurface flow constructed treatment wetlands (CTW). The data used in this work was obtained from various hydraulic and BOD loading of a pilot CTW located in India and comprised of 91 patterns. The dataset was normalized and transformed using principal component analysis (PCA) in order to increase the efficiency of the modelling. At the modelling stage the most adequate models were determined by using systematic approach. The candidate ANN models were cross-validated to find optimal network architectures and values of training algorithm parameters. MRA performance was maximized by utilizing 14-fold cross-validation. MRA as well as ANN models were found to provide an efficient and robust tool in predicting CTW performance. MLP and RBF produced the most accurate results indicating strong potential for modelling of wastewater treatment processes.

[1]  A. E. Greenberg,et al.  Standard methods for the examination of water and wastewater : supplement to the sixteenth edition , 1988 .

[2]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[3]  S. Ayaz,et al.  Treatment of wastewater by constructed wetland in small settlements. , 2000 .

[4]  Jan Vymazal,et al.  The use of sub-surface constructed wetlands for wastewater treatment in the Czech Republic: 10 years experience , 2002 .

[5]  Michael C. Kemp,et al.  Subsurface flow constructed wetlands treating municipal wastewater for nitrogen transformation and removal , 1997 .

[6]  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..

[7]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[8]  Chris C. Tanner,et al.  Treatment of Dairy Farm Wastewaters in Horizontal and Up-Flow Gravel-Bed Constructed Wetlands , 1994 .

[9]  Jean-Philippe Steyer,et al.  Hybrid fuzzy neural network for diagnosis - application to the anaerobic treatment of wine distillery wastewater in a fluidized bed reactor , 1997 .

[10]  D McNevin,et al.  Alternative analysis of BOD removal in subsurface flow constructed wetlands employing Monod kinetics. , 2001, Water research.

[11]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[12]  Harry Wechsler,et al.  From Statistics to Neural Networks: Theory and Pattern Recognition Applications , 1996 .

[13]  T. M. Wynn,et al.  Development of a constructed subsurface-flow wetland simulation model , 2001 .

[14]  Werner Hegemann,et al.  Combined oxidative and biological treatment for separated streams of tannery wastewater , 1997 .

[15]  Mohamed F. Hamoda,et al.  Integrated wastewater treatment plant performance evaluation using artificial neural networks , 1999 .

[16]  S. T. Buckland,et al.  Computer Intensive Statistical Methods: Validation, Model Selection, and Bootstrap , 1993 .

[17]  Mogens Henze,et al.  Activated sludge models ASM1, ASM2, ASM2d and ASM3 , 2015 .

[18]  S. Green.  How Many Subjects Does It Take To Do A Regression Analysis. , 1991, Multivariate behavioral research.

[19]  Sherwood C. Reed,et al.  Natural Systems for Waste Management and Treatment , 1994 .

[20]  Armando Freitas da Rocha,et al.  Neural Nets , 1992, Lecture Notes in Computer Science.

[21]  Dimitar Filev,et al.  Generation of Fuzzy Rules by Mountain Clustering , 1994, J. Intell. Fuzzy Syst..

[22]  W. C. Chen,et al.  Advanced Hybrid Fuzzy-Neural Controller for Industrial Wastewater Treatment , 2001 .

[23]  Robert H. Kadlec,et al.  The inadequacy of first-order treatment wetland models , 2000 .

[24]  L. Breiman,et al.  Submodel selection and evaluation in regression. The X-random case , 1992 .

[25]  N. Singh,et al.  Horizontal Subsurface Flow Gravel Bed Constructed Wetland with Phragmites Karka in Central India , 1999 .

[26]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[27]  Anil K. Jain,et al.  Algorithms for Clustering Data , 1988 .

[28]  Maged M. Hamed,et al.  Prediction of wastewater treatment plant performance using artificial neural networks , 2004, Environ. Model. Softw..

[29]  Chris C. Tanner,et al.  Effect of loading rate and planting on treatment of dairy farm wastewaters in constructed wetlands—I. Removal of oxygen demand, suspended solids and faecal coliforms , 1995 .

[30]  Günter Langergraber,et al.  Simulation of the treatment performance of outdoor subsurface flow constructed wetlands in temperate climates. , 2007, The Science of the total environment.

[31]  Sherwood C. Reed,et al.  Subsurface flow wetlands : a performance evaluation , 1995 .

[32]  J. S. Urban Hjorth,et al.  Computer Intensive Statistical Methods: Validation, Model Selection, and Bootstrap , 1993 .

[33]  Peter A. Vanrolleghem,et al.  Constructed wetlands in Flanders: a performance analysis , 2004 .

[34]  Roberto Guardani,et al.  Modeling the kinetics of a photochemical water treatment process by means of artificial neural networks , 1999 .

[35]  A. Wood.  CONSTRUCTED WETLANDS FOR WASTEWATER TREATMENT — ENGINEERING AND DESIGN CONSIDERATIONS , 1990 .

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

[37]  Jerome H. Friedman,et al.  An Overview of Predictive Learning and Function Approximation , 1994 .