Abstract
The Chézy roughness coefficient provides an empirical link between the impelling force and the unaccelerated velocity of the flowing water. This coefficient is hydraulic resistance’s universal integral empirical characteristic because it depends on the Reynolds number and channel roughness. Chézy’s coefficient enables to control of a majority of factors and parameters determining the hydraulic resistance to open flows in river channels. A challenge is that the Chézy coefficient may not be determined directly using field measurements or experimentally. To compute the Chézy roughness coefficient, a large number of empirical and semi-empirical formulas have been developed by various authors. However, as practice shows, there is no ideal way or method to determine the Chézy roughness coefficient. Often, the appropriate formula choosing can become a challenge for researchers. Supporting the comprehensive and holistic approach to hydraulic resistance research, this article presents preliminary results of solving the problem using an artificial neural network. The problem is solved with the example of a neural network of direct propagation with one hidden layer and a sigmoid logistic activation function. The Python object-oriented programming environment was applied to build and train the neural network. The neural network training was carried out according to the actual data of hydro-morphological observations in rivers. The network testing was performed with a comparison of the observed (gauged) and computed (predicted) water discharges. The Nash-Sutcliffe model efficiency coefficient was used to assess the predictive skill of the network.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abbott, P.L.: Natural Disasters. Wm. C. Brown Publishing Co. (1996)
Schmutz, S., Sendzimir, J. (eds.): Riverine Ecosystem Management. AES, vol. 8. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-73250-3
Kummu, M., de Moel, H., Ward, P.J., Varis, O.: How close do we live to water? A global analysis of population distance to freshwater bodies. PLoS ONE 6(6), e20578 (2011)
Chow, V.T.: Open-Channel Hydraulics. McGraw-Hill, N.Y. (1959)
Liang, D., Falconer, R.A., Lin, B.: Linking one- and two-dimensional models for free surface flows. Water Manag. 160(3), 145–151 (2007)
HEC-RAS River Analysis System: User’s Manual V. 6.0. US Army Corps of Engineers. Institute for Water Resources. Hydrologic Engineering Center (2021)
Kasvi, E., et al.: Two-dimensional and three-dimensional computational models in hydrodynamic and morphodynamic reconstructions of a river bend: sensitivity and functionality. Hydrol. Processes (2014)
Stefanyshyn, D.V., Korbutiak, V.M., Stefanyshyna-Gavryliuk, Y.D.: Situational predictive modelling of the flood hazard in the Dniester river valley near the town of Halych. Environ. Saf. Nat. Resour. 29(1), 16–27 (2019)
Leopold, L.B., Bagnold, R.A., Wolman, M.G., Brush, L.M. Jr.: Flow resistance in sinuous or irregular channels. In: Physiographic and Hydraulic Studies of Rivers. Geological Survey Professional Paper 283-D (1960)
Stefanyshyn, D.V., Khodnevich, Y.V., Korbutiak, V.M.: Estimating the Chezy roughness coefficient as a characteristic of hydraulic resistance to flow in river channels: a general overview, existing challenges, and ways of their overcoming. Environ. Saf. Nat. Resour. 39(3), 16–43 (2021)
Stewart, M.T., Cameron, S.M., Nikora, V.I., Zampiron, A., Marusic, I.: Hydraulic resistance in open-channel flows over self-affine rough beds. J. Hydraul. Res. 57(2), 183–196 (2019)
Khodnevych, Y.V., Stefanyshyn, D.V.: Data arrangements to train an artificial neural network within solving the tasks for calculating the Chézy roughness coefficient under uncertainty of parameters determining the hydraulic resistance to flow in river channels. Environ. Saf. Nat. Resour. 42(2), 59–85 (2022)
Sellier, M.: Inverse problems in free surface flows: a review. Acta Mech. 227(3), 913–935 (2015). https://doi.org/10.1007/s00707-015-1477-1
Coon, W.F.: Estimation of roughness coefficients for natural stream channels with vegetated banks. Prepared in Cooperation with the New York State Department of Transportation (1998)
De Rocquigny, E.: Modelling Under Risk and Uncertainty: An Introduction to Statistical, Phenomenological and Computational Methods. Wiley Series in Probability and Statistics (2012)
Altman, M.: A holistic approach to empirical analysis: the insignificance of P, hypothesis testing and statistical significance*. In: Bailey, D.H., et al. (eds.) From Analysis to Visualization. SPMS, vol. 313, pp. 233–253. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-36568-4_16
Haikin, S.: Neural Networks and Learning Machines. 3rd edn. Prentice Hall (2008)
Suzuki, K. (ed.): Artificial Neural Networks - Architectures and Applications. Janeza Trdine 9, 51000 Rijeka, Croatia (2013)
Chollet, F.: Deep Learning with Python. Manning Publications Co. (2018)
Keim, R.: How Many Hidden Layers and Hidden Nodes Does a Neural Network Need? (2020). https://www.allaboutcircuits.com/technical-articles/how-many-hidden-layers-and-hidden-nodes-does-a-neural-network-need/. Accessed 27 Mar 2023
Muller, A., Guido, S.: Introduction to Machine Learning with Python, Published by O’Reilly Media (2016)
Khodnevych, Ya.: The software implementation of a neural network computational algorithm for predicting the Chézy roughness coefficient. https://github.com/yakhodnevych/ANN_approximation_C. Accessed 27 Mar 2023
Nash, J.E., Sutcliffe, J.V.: River flow forecasting through conceptual models part I - a discussion of principles. J. Hydrol. 10(3), 282–290 (1970)
Ritter, A., Muñoz-Carpena, R.: Performance evaluation of hydrological models: statistical significance for reducing subjectivity in goodness-of-fit assessments. J. Hydrol. 480(1), 33–45 (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Khodnevych, Y., Stefanyshyn, D., Korbutiak, V. (2023). The Chézy Roughness Coefficient Computing Using an Artificial Neural Network to Support the Mathematical Modelling of River Flows. In: Dovgyi, S., Trofymchuk, O., Ustimenko, V., Globa, L. (eds) Information and Communication Technologies and Sustainable Development. ICT&SD 2022. Lecture Notes in Networks and Systems, vol 809. Springer, Cham. https://doi.org/10.1007/978-3-031-46880-3_26
Download citation
DOI: https://doi.org/10.1007/978-3-031-46880-3_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-46879-7
Online ISBN: 978-3-031-46880-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)