Evaluating the Efficiency of Bayesian Networks in River Quality Management: Application of the Trading-Ratio System

Document Type : Research Paper


1 Ph.D Student of Civil Engineering, University of Tehran

2 Assoc. Prof., and Member of Center of Excellence for Infrastructure Engineering and Management, Civil Engineering Dept., University of Tehran


In recent decades, river quality management has received enormous attention by researchers as an important water resources management issue. The main reason for this is saving in wastewater treatment costs by optimal allocation of the assimilative capacity of the river system to dischargers. Regarding the unidirectionality of the river flow toward the lowest level, the Trading Ratio System (TRS) and Bayesian Networks are utilized in this paper to develop new, real-time operating policies for discharge permit trading in rivers. TRS is used in a Monte Carlo Analysis to provide the required data for training and validating a Bayesian Network (BN). The trained BN are then used for real time river water quality management to provide probability distribution functions of treatment levels and trading discharge permit policies. The methodology is successfully applied to a case study and its results are compared with those of the TRS. The comparisons show the usefulness of the methodology as a cost-effective and probabilistic decision-making tool in real-time river water quality management.


1- Dales, J. H. (1968). “Land, water and ownership.” the Canadian J. of Economics / Revue Canadienne d'Economique, 1(4), 791-804.
 2- Eheart, J. W. (1980). “Cost efficiency of transferable discharge permits for the control of BOD discharges.” Water Resource Res., 16, 980-989.
 3- Brill, E. D., Eheart, J. W., Kshirsagar, S. R., and Lence, B. J. (1984).“Water quality impacts of biochemical oxygen demand under transferable discharge permit programs.” Water Resource Res., 20 (4), 445-455.
 4- Eheart, J.W., and Ng, T.L. (2004). “Role of effluent permit trading in total maximum daily load programs: Overview and uncertainty and reliability Implications.” J. of Environmental Engineering, 130 (6), 615-621.
5- Hung M.F., and Shaw, D. (2005). “A trading-ratio system for trading water pollution discharge permits.” J. of Environmental Economics and Management, 49, 83-102.
 6- Ng, T.L., and Eheart, J.W. (2005). “Effects of discharge permit trading on water quality reliability.” J. of Water Resources Planning and Management, 131 (2), 81-88.
7- Mesbah, S. H., Kerachian, R., and Torabian, A. (2007). “Trading water pollution discharge permits in river systems using fuzzy nonlinear cost functions.” Proc. of CEMEPE/SECOTOX Conference,Skiathos Island,Greece, 1-10.
8- Mesbah, S.M., Kerachian, R., and Nikoo, M.R. (2009). “Developing real time operating rules for trading discharge permits in rivers: application of bayesian networks.” Environmental Modelling and Software, Elsevier, 24 (2), 238-246.
 9- Varis, O. (1998). “A belief network approach to optimization and parameter estimation: application to resource and environmental management.” Artificial Intelligence, 101 (1-2), 135-163.
 10- Poulakis, Z., Valougeorgis, D., and Papadimitriou, C. (2003). “Leakage detection in water pipe networks using a Bayesian probabilistic framework.” Probabilistic Engineering Mechanics, 18, 315-327.
 11- Borsuk, M., Stow, C., and Reckhow, K. (2004). “A bayesian network of eutrophication models for synthesis, prediction, and uncertainty analysis.” Ecological Modeling, 173, 219-239.
 12- Castelletti, A., and Soncini-Sessa, R. (2007). “Coupling real time control and socioeconomic issues in participatory river basin planning.” Environmental Modelling and Software, 22 (8), 1114-1128.
13- Neapolitan, R. E. (2003). Learning bayesian networks, 1st Ed.,Prentice Hall,New York,USA.