Combined Sewer Overflow forecasting with Feed-forward Back-propagation Artificial Neural Network

Authors: Achela K. Fernando, Xiujuan Zhang, Peter F. Kinley

Abstract:

A feed-forward, back-propagation Artificial Neural Network (ANN) model has been used to forecast the occurrences of wastewater overflows in a combined sewerage reticulation system. This approach was tested to evaluate its applicability as a method alternative to the common practice of developing a complete conceptual, mathematical hydrological-hydraulic model for the sewerage system to enable such forecasts. The ANN approach obviates the need for a-priori understanding and representation of the underlying hydrological hydraulic phenomena in mathematical terms but enables learning the characteristics of a sewer overflow from the historical data. The performance of the standard feed-forward, back-propagation of error algorithm was enhanced by a modified data normalizing technique that enabled the ANN model to extrapolate into the territory that was unseen by the training data. The algorithm and the data normalizing method are presented along with the ANN model output results that indicate a good accuracy in the forecasted sewer overflow rates. However, it was revealed that the accurate forecasting of the overflow rates are heavily dependent on the availability of a real-time flow monitoring at the overflow structure to provide antecedent flow rate data. The ability of the ANN to forecast the overflow rates without the antecedent flow rates (as is the case with traditional conceptual reticulation models) was found to be quite poor.

Keywords: Artificial Neural Networks, Back-propagationlearning, Combined sewer overflows, Forecasting.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1330365

References:

[1] R. H. Dwight, J. C. Semenza, D. B. Baker and B. H. Olson, "Association of urban runoff with coastal water quality in Orange County, California" Water Environment Research, Water Environment Federation, pp. 82- 90, Jan/Feb 2002
[2] Water Environment Research Foundation, "WERF Project Investigates Sanitary Sewer Overflow Prediction Technologies", Available http://www.werf.org/press/fall99/page6.cfm.
[3] S. Birikundavyi, R. Labib, T. Trung and J. Rousselle, "Performance of neural networks in daily streamflow forecasting, Journal of Hydrological Engineering, Vol. 7, No. 5, pp. 392-398, 2002
[4] A. Jain and S. Srinivasulu, "Development of effective and efficient rainfall-runoff models using integration of deterministic, real-coded genetic algorithms and artificial neural networks techniques", Water Resources Research, Vol. 40, doi:10.1029/2003 WR002355, (2004) Americal Geophysical Union, 2004.
[5] D. A. K. Fernando and A.W. Jayawardena, "Runoff forecasting using RBF networks with OLS Algorithm", Journal of Hydrologic Engineering, ASCE Water resources Engineering division, Vol. 3, No. 3, pp. 203- 209, July 1998.
[6] M. Tomasino, D. Zunchettin and P. Traverso, "Long term forecasts of River Po discharges based on predictable solar activity and a fuzzy neural network model, Hydrological Sciences Journal, Vol. 49, No. 4, pp. 673-684, August 2004.
[7] Y. Lin, Y. Wang, Y. Li, B. Zhang and G. Wu, "Earthquake prediction by RBF neural network ensemble", Advances in Neural Networks, Proc. of the International Symposium on Neural networks, China, Ed. F. Yin, J. Wang, and C. Guo, pp. 962-969, Springer, August 2004.
[8] D. E. Rumelhart, R. Durbin, R. Golden, and Chauvin, "Backpropagation: The Basic Theory, In Mathematical Perspectives on Neural Networks", Eds. P. Smolensky, M. C.Mozer, and D. E. Rumelhart, Lawrence Erlbaum Associates, Mahwah, NJ., pp. 533-566, 1996.
[9] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, Learning internal representations by error propagation, In Parallel Distributed Processing, Vol. 1, Eds., D. E. Rumelhart, and J. L. McClelland, MIT Press, Cambridge, MA. pp. 318-362, 1986.
[10] Wasserman, P.D., Advanced methods in neural computing, Van Nostrand Reinhold, New York, 1993.
[11] M. A. Rao, J. Srinivas, Neural networks: algorithms and applications, Pangbourne, Eng.; Alpha Science International, 2003.
[12] Fernando, A.K. and Kerr, T., "Runoff forecasting with Artificial Neural Network Model", The 3rd Pacific Conference on stormwater and aquatic resource protection, Auckland, New Zealand Water and Wastes Association publication of conference proceedings in CD-ROM, 2003.
[13] H. K. Cigizoglu "Estimation, forecasting and extrapolation of river flows by artificial neural networks" Hydrological Science, Journal, Vol. 48, No. 3, pp. 349-361, June 2003.
[14] M. Campolo, A. Soldati, P. Acdreussi, "Artificial Neural Network approach to flood forecasting in the River Arno" Hydrological Sciences Journal, 48(3), pp. 381-398, June 2003
[15] H. R. Maier and G.C. Dandy, "Determining inputs for neural network models of multivariate time series", Microcomputers in Civil Engineering, Vol. 12, pp. 353-368, 1997.
[16] S. Amari, N. Murata, K. R. Muller, M. Finke and H.H. Yang, "Asymptotic statistical theory of overtratining and cross-validation" IEEE Transactions on Neural Networks, Vol. 8, No. 5, pp. 985-996, 1997.
[17] W. Wang, P.H.A.J.M. Van Gelder and J.K. Vrijling, "Some issues about the generalization of neural networks for time series prediction" in Advances in Neural Networks, Proc. of the International Symposium on Neural networks, August 2004, China, Ed. F. Yin, J. Wang, and C. Guo, Springer, pp. 559-564, 2004
[18] L. Prechelt, 1998, Early stopping - but when? In G. B. Orr, K-R Mueller, Eds. Neural networks: Tricks of the trade, Berlin, Springer, pp. 55-99, 1998..