Hydrology and Earth System Sciences www.hydrol-earth-syst-sci.net 1027-5606 1607-7938 14 7 2010 10.5194/hess-14-1309-2010 http://www.hydrol-earth-syst-sci.net/14/1309/2010/ http://www.hydrol-earth-syst-sci.net/14/1309/2010/hess-14-1309-2010.html http://www.hydrol-earth-syst-sci.net/14/1309/2010/hess-14-1309-2010.pdf 1309 1319 2010-07-16 Dynamic neural networks for real-time water level predictions of sewerage systems-covering gauged and ungauged sites Yen-Ming Chiang Li-Chiu Chang Meng-Jung Tsai Yi-Fung Wang Fi-John Chang Department of Bioenvironmental Systems Engineering, National Taiwan University, Taipei, Taiwan Department of Water Resources and Environmental Engineering, Tamkang University, Taipei, Taiwan Water Resources Agency, Ministry of Economic Affairs, Taipei, Taiwan In this research, we propose recurrent neural networks (RNNs) to build a relationship between rainfalls and water level patterns of an urban sewerage system based on historical torrential rain/storm events. The RNN allows signals to propagate in both forward and backward directions, which offers the network dynamic memories. Besides, the information at the current time-step with a feedback operation can yield a time-delay unit that provides internal input information at the next time-step to effectively deal with time-varying systems. The RNN is implemented at both gauged and ungauged sites for 5-, 10-, 15-, and 20-min-ahead water level predictions. The results show that the RNN is capable of learning the nonlinear sewerage system and producing satisfactory predictions at the gauged sites. Concerning the ungauged sites, there are no historical data of water level to support prediction. In order to overcome such problem, a set of synthetic data, generated from a storm water management model (SWMM) under cautious verification process of applicability based on the data from nearby gauging stations, are introduced as the learning target to the training procedure of the RNN and moreover evaluating the performance of the RNN at the ungauged sites. The results demonstrate that the potential role of the SWMM coupled with nearby rainfall and water level information can be of great use in enhancing the capability of the RNN at the ungauged sites. Hence we can conclude that the RNN is an effective and suitable model for successfully predicting the water levels at both gauged and ungauged sites in urban sewerage systems. Ackerman, D. and Schiff, K.: Modeling storm water mass emissions to the southern California bight, J. Environ. Eng-Asce, 129(4), 308–317, 2003. Akhtar, M. K., Corzo, G. A., van Andel, S. J., and Jonoski, A.: River flow forecasting with artificial neural networks using satellite observed precipitation pre-processed with flow length and travel time information: case study of the Ganges river basin, Hydrol. Earth Syst. Sci., 13, 1607–1618, doi:10.5194/hess-13-1607-2009, 2009. Baffaut, C. and Delleur, J. W.: Calibration of Swmm Runoff Quality Model with Expert System, J. Water Res. Pl-Asce, 116(2), 247–261, 1990. Besaw, L. E., Rizzo, D. M., Bierman, P. R., and Hackett, W. R.: Advances in ungauged streamflow prediction using artificial neural networks, J. Hydrol., 386(1–4), 27–37, 2010. Borah, D. K. and Bera, M.: Watershed-scale hydrologic and nonpoint-source pollution models: Review of mathematical bases, T. Asae, 46(6), 1553–1566, 2003. Bruen, M. and Yang, J. Q.: Combined hydraulic and black-box models for flood forecasting in urban drainage systems, J. Hydrol. Eng., 11(6), 589–596, 2006. Chandramouli, V. and Deka, P.: Neural network based decision support model for optimal reservoir operation, Water Resour. Manag., 19(4), 447–464, 2005. Chang, F. J., Chang, L. C., and Huang, H. L: Real-time recurrent learning neural network for stream-flow forecasting, Hydrol. Process., 16(13), 2577–2588, 2002. Chang, F. J. and Chang, Y. T.: Adaptive neuro-fuzzy inference system for prediction of water level in reservoir, Adv. Water Resour., 29(1), 1–10, 2006. Chang, L. C. and Chang, F. J.: Intelligent control for modelling of real-time reservoir operation, Hydrol. Process., 15(9), 1621–1634, 2001. Chang, L. C., Shen, H. Y., Wang, Y. F., Huang, J. Y., and Lin, Y. T. Clustering-based hybrid inundation model for forecasting flood inundation depths, J. Hydrol., 385(1–4), 257–268, 2010. Chaves, P. and Chang, F. J.: Intelligent reservoir operation system based on evolving artificial neural networks, Adv. Water Resour., 31(6), 926–936, 2008. Chiang, Y. M. and Chang, F. J.: Integrating hydrometeorological information for rainfall-runoff modelling by artificial neural networks, Hydrol. Process., 23(11), 1650–1659, 2009. Chiang, Y. M., Chang, F. J., Jou, B. J. D., and Lin, P. F.: Dynamic ANN for precipitation estimation and forecasting from radar observations, J. Hydrol., 334(1–2), 250–261, 2007a. Chiang, Y. M., Hsu, K. L., Chang, F. J., Hong, Y., and Sorooshian, S.: Merging multiple precipitation sources for flash flood forecasting, J. Hydrol., 340(3–4), 183–196, 2007b. Chiang, Y. M., Chang, L. C., and Chang, F. J.: Comparison of static-feedforward and dynamic-feedback neural networks for rainfall-runoff modeling, J. Hydrol., 290(3–4), 297–311, 2004. Coulibaly, P. and Baldwin, C. K.: Nonstationary hydrological time series forecasting using nonlinear dynamic methods, J. Hydrol., 307(1–4), 164–174, 2005. Coulibaly, P. and Evora, N. D.: Comparison of neural network methods for infilling missing daily weather records, J. Hydrol., 341(1–2), 27–41 , 2007. Denault, C., Millar, R. G., and Lence, B. J.:Assessment of possible impacts of climate change in an urban catchment, J. AM. Water Resour. As., 42(3), 685–697, 2006. Huber, W. C. and Dickinson, R. E.: Strom water management model, User's Manual Ver. IV, US Environmental Protection Agency, 1988. Hung, N. Q., Babel, M. S., Weesakul, S., and Tripathi, N. K.: An artificial neural network model for rainfall forecasting in Bangkok, Thailand, Hydrol. Earth Syst. Sci., 13, 1413-1425, doi:10.5194/hess-13-1413-2009, 2009. Kumar, D. N., Raju, K. S., and Sathish, T.: River flow forecasting using recurrent neural networks, Water Resour. Manag., 18(2), 143–161, 2004. Loke, E., Warnaars, E. A., Jacobsen, P., Nelen, F., and Almeida, M. D.: Artificial neural networks as a tool in urban storm drainage, Water Sci. Technol., 36(8–9), 101–109, 1997. Maharjan, M., Pathirana, A., Gersonius, B., and Vairavamoorthy, K.: Staged cost optimization of urban storm drainage systems based on hydraulic performance in a changing environment, Hydrol. Earth Syst. Sci., 13, 481–489, doi:10.5194/hess-13-481-2009, 2009. Maity, R. and Kumar, D. N.: Basin-scale stream-flow forecasting using the information of large-scale atmospheric circulation phenomena, Hydrol. Process., 22(5), 643–650, 2008. Mishra, A. K. and Desai, V. R.: Drought forecasting using feed-forward recursive neural network, Ecol. Model., 198(1–2), 127–138, 2006. Nasseri, M., Asghari, K., and Abedini, M. J.: Optimized scenario for rainfall forecasting using genetic algorithm coupled with artificial neural network, Expert Syst. Appl., 35(3), 1415–1421, 2008. Razavi, S. and Karamouz, M.: Adaptive neural networks for flood routing in river systems, Water Int., 32(3), 360–375, 2007. Sahoo, G. B., Schladow, S. G., and Reuter, J. E.: Forecasting stream water temperature using regression analysis, artificial neural network, and chaotic non-linear dynamic models, J. Hydrol., 378(3–4), 25–342, 2009. Sudheer, K. P., Srinivasan, K., Neelakantan, T. R., and Srinivas, V. V.: A nonlinear data-driven model for synthetic generation of annual streamflows, Hydrol. Process., 22(12), 1831–1845, 2008. Toth, E.: Classification of hydro-meteorological conditions and multiple artificial neural networks for streamflow forecasting, Hydrol. Earth Syst. Sci., 13, 1555–1566, doi:10.5194/hess-13-1555-2009, 2009. Tsihrintzis, V. A. and Hamid, R.: Runoff quality prediction from small urban catchments using SWMM, Hydrol. Process., 12(2), 311–329, 1998. Yazdani, M. R., Saghafian, B., Mahdian, M. H., and Soltani, S.: Monthly Runoff Estimation Using Artificial Neural Networks, J. Agri. Sci. Technol., 11(3), 355–362, 2009.