References

HESS

Hydrology and Earth System Sciences

HESS

Hydrol. Earth Syst. Sci.

1607-7938

Copernicus Publications

Göttingen, Germany

10.5194/hess-11-1883-2007

Evaluation of 1-D tracer concentration profile in a small river by means of Multi-Layer Perceptron Neural Networks

Piotrowski

¹ Wallis

S. G.

² Napiórkowski

J. J.

¹ Rowiński

P. M.

Institute of Geophysics, Polish Academy of Sciences, Warsaw, Poland

Heriot-Watt University, Edinburgh, UK

07 12 2007

11 6 1883 1896

2007

This work is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 2.5 Generic License. To view a copy of this licence, visit https://creativecommons.org/licenses/by-nc-sa/2.5/

This article is available from https://hess.copernicus.org/articles/11/1883/2007/hess-11-1883-2007.html

The full text article is available as a PDF file from https://hess.copernicus.org/articles/11/1883/2007/hess-11-1883-2007.pdf

The prediction of temporal concentration profiles of a transported pollutant in a river is still a subject of ongoing research efforts worldwide. The present paper is aimed at studying the possibility of using Multi-Layer Perceptron Neural Networks to evaluate the whole concentration versus time profile at several cross-sections of a river under various flow conditions, using as little information about the river system as possible. In contrast with the earlier neural networks based work on longitudinal dispersion coefficients, this new approach relies more heavily on measurements of concentration collected during tracer tests over a range of flow conditions, but fewer hydraulic and morphological data are needed. The study is based upon 26 tracer experiments performed in a small river in Edinburgh, UK (Murray Burn) at various flow rates in a 540 m long reach. The only data used in this study were concentration measurements collected at 4 cross-sections, distances between the cross-sections and the injection site, time, as well as flow rate and water velocity, obtained according to the data measured at the 1st and 2nd cross-sections. <br><br> The four main features of concentration versus time profiles at a particular cross-section, namely the peak concentration, the arrival time of the peak at the cross-section, and the shapes of the rising and falling limbs of the profile are modeled, and for each of them a separately designed neural network was used. There was also a variant investigated in which the conservation of the injected mass was assured by adjusting the predicted peak concentration. The neural network methods were compared with the unit peak attenuation curve concept. <br><br> In general the neural networks predicted the main features of the concentration profiles satisfactorily. The predicted peak concentrations were generally better than those obtained using the unit peak attenuation method, and the method with mass-conservation assured generally performed better than the method that did not account for mass-conservation. Predictions of peak travel time were also better using the neural networks than the unit peak attenuation method. Including more data into the neural network training set clearly improved the prediction of the shapes of the concentration profiles. Similar improvements in peak concentration were less significant and the travel time prediction appeared to be largely unaffected.

References 1

Burke, N. J.: Travel time and flow characteristics of a small stream system, PhD Thesis, Heriot-Watt University, Edinburgh (unpublished), 2002.

Cheong, T. S. and Seo, I. W.: Parameter estimation of the transient storage model by a routing method for river mixing processes, Water Resour. Res., 39(4), 1074–1084, 2003.

Czernuszenko, W. and Rowi\'nski, P.M.:, Properties of the dead-zone model of longitudinal dispersion in rivers, J. Hydraul. Res., 35(4), 491–504, 1997.

Czernuszenko, W., Rowi\'nski, P. M., and Sukhodolov, A.: Experimental and numerical validation of the dead-zone model for longitudinal dispersion in rivers, J. Hydraul. Res., 36(2), 269–280, 1998.

De Smedt, F., Brevis, W., and Debels, P.: Analytical solution for solute transport resulting from instantaneous injection in streams with transient storage, J. Hydrol., 315, 25–39, 2005.

Fischer, H. B., List, E. J., Koh, R. C. Y., Imberger, J., and Brooks, N.H.: Mixing in Inland and Coastal Waters, Academic Press, London, UK, 1979.

Guymer, I. and Dutton, R.: Application of a transient storage model to meandering channel studies of solute transport and dispersion, in: Water Quality Hazards and Dispersion of Pollutants, edited by: Czernuszenko, W. and Rowi\'nski, P. M., Springer, New York, USA, 85–107, 2005.

Hart, D. R.: Parameter estimation and stochastic interpretation of the transient storage model for solute transport in streams, Water Resour. Res., 31(2), 323–328, 1995.

Haykin, S.: Neural Networks: A Comprehensive Foundation, Macmillan College Publishing Co., New York, USA, 1999.

Jobson, H. E.: Predicting travel time and dispersion in rivers and streams, J. Hydraul. Eng.-ASCE, 123(11), 971–978, 1997.

Kashefipour, S. M., Falconer, R. A., and Lin, B.: Modelling longitudinal dispersion in natural flows using ANNs, in: Proceedings of River Flow 2002, Louvain-la-Neuve, Belgium, 111–116, 2002.

Kashefipour, S. M. and Falconer, R. A.: Longitudinal dispersion coefficients in natural channels, Water Res., 36(7), 1596–1608, 2002.

Manson, J. R.: Predicting stream transient storage zone characteristics from tracer data, Water Resour. Res., 36(2), 629–631, 2000.

Press, W. H., Flannery, B. P., Teukolsky, S. A., and Vetterling, W. T.: Numerical Recipes in C, The Art of Scientific Computing, Cambridge University Press, Cambridge, UK, 1990.

Rowi\'nski P. M., Napiórkowski J.J., and Owczarczyk A.: Transport of passive admixture in a multi-channel river system - the Upper Narew case study, Part 2, Application of dye tracer method, Ecohydrology and Hydrobiology, 3(4), 381–388, 2003.

Rowi\'nski, P. M., Piotrowski, A., and Napiórkowski, J. J.: Are artificial neural network techniques relevant for the estimation of longitudinal dispersion coefficient in rivers?, Hydrolog. Sci. J., 50(1), 175–187, 2005.

Rutherford, J. C.: River Mixing, Wiley, Chichester, UK, 1994.

Taylor, G. I.: The dispersion of matter in turbulent flow through a pipe, Proceedings of the Royal Society of London, A223, 446–468, 1954.

Thackston, E. L. and Schnelle, K. B. J.: Predicting effects of dead zones on stream mixing, Journal of the Sanitary Engineering Division, Proceedings of the American Society of Civil Engineering, 96(SA2), 319–331, 1970.

Wallis, S. G.: Experimental study of travel times in a small stream, in: Water Quality Hazards and Dispersion of Pollutants, edited by: Czernuszenko, W. and Rowi\'nski, P. M., Springer, New York, USA, 109–120, 2005.

Wallis, S. G., Piotrowski, A., Rowi\'nski, P. M. and Napiórkowski, J. J.: Prediction of dispersion coefficients in a small stream using Artificial Neural Networks, Proceedings of the 32nd IAHR Congress, Venice, paper B2b-083-O, 2007.

Wagener, T., Camacho, L. A. and Wheater, H. S.: Dynamic identyfiability analysis of the transient storage model for solute transport in rivers, J. Hydroinform., 4(3), 199–211, 2002.

Wörman, A., Klove, B., Wachniew, P., Czuprynski, P. and Packman, A.: Tracer test in Hobol creek, Norway, under different flow conditions, Acta Geophysica Polonica, 53(4), 517–526, 2005.

Wörman, A. and Wachniew, P.: Reach scale and evaluation methods as limitations for transient storage properties in streams and rivers, Water Resour. Res., 43, W10405, https://doi.org/10.1029/2006WR005808, 2007.