Estimation of River Bedform Dimension Using Artificial Neural Network (ANN) and Support Vector Machine (SVM)

Authors
F. Javadi
M. M. Ahmadi
K. Qaderi
Department of Water Engineering, Faculty of Agriculture, Shahid Bahonar University of Kerman, Kerman, Islamic Republic of Iran.
Abstract
Movement of sediment in the river causes many changes in the river bed. These changes are called bedform. River bedform has significant and direct effects on bed roughness, flow resistance, and water surface profile. Thus, having adequate knowledge of the bedform is of special importance in river engineering. Several methods have been developed by researchers for estimation of bed form dimensions. In this investigation, bedform has been estimated using Artificial Neural Network (ANN) and Support Vector Machine (SVM) methods. The results obtained from these two methods were compared with empirical formulas of Van Rijn. The accuracy of the model was evaluated using (RMSE), (MSRE), (CE), (R2) and (RB) statistical parameters. Higher values of statistical parameters indicated that the SVM model with RBF kernel function predicted the bedform more accurately than the other method. The values calculated for R2, RMSE, MSRE, CE and RB parameters were 0.79, 0.024, 0.066, 0.786, -0.081, respectively. Comparison of the results of the SVM model with RBF kernel with other models indicated that SVM had a higher capability for estimating and simulating height of the bedform than Artificial Neural Networks.

Keywords

1. Azamathulla, H. Md., Chang, Ch. K., Ghani, A. AB., Ariffin, J. Zakaria, N. A. and Abu Hasan, Z. 2008. An ANFIS-Based Approach for Predicting the Bed Load for Moderately Sized Rivers. J. Hydro-environ Res., 3: 35-44.
2. Botsis D., Latinopulos P. and Diamantaras K., 2011. Rainfall-Runoff Modeling Using Support Vector Regression and Artificial Neural Networks. 12th International Conference on Environmental Science and Technology (CEST2011), 8 - 10 September, Rhodes, Greece, Ref No. XXX.
3. Brooks, N. H. 1958. Mechanics of Stream with Movable Bed of Fine Sand. Trans. Am. Soc. Civ. Eng. 123:536-549.
4. Chang, H. H. 1988. Fluvial Processes in River Engineering. John Wiley and Sons, Inc., USA, 432 PP.
5. Coleman, S. E. and Melville, B. 1996. Initiation of Bedforms on a Flat Sand Bed. J. Hydraulic Eng-ASCE, 122: 301-310.
6. Dibike, Y. B., Velickov, S., Sololatine, D. P. and Abbott, M. B., 2001. Model Induction with Support Vector Machine: Introduction and Application. ASCE Journal Computation Civil Eng. 15: 208–216.
7. Engelund, F. and Hansen, E. 1966. Investigations of Flow in A11uvial Streams. Acta Polytechnical Scandinavica. Civil Engineering and Building Construction Series No. 35, Copenhagen.
8. Gilbert, G. K. 1914. The Transportation of Débris by Running Water. US Geological Survey Professional Paper No. 86.
9. Goel A. and Pal M. 2012. Stage Discharge Modeling Using Support Vector Machines, IJE Transactions A: Basics,DOI:10.5829/idosi.ije, 25.01a.01.
10. Han, D., Cluckie, I., Kang, W., Xiong, Y., 2002. River Flow Modelling Using Reference Vector Machines. In: “Hydroinformatics Proceedings”, Cardiff, IWA Publishing, London, B, pp. 1429–1434.
11. Han, D., Yang, Z., 2001. River Flow Modeling Using Support Vector Machines. In: 29th IAHR Congress, Beijing, China, September, 17–21.
12. Julien, P. Y. & Klaassen, G. J. (1995). Sand–Dune Geometry of Large Rivers during Floods. J. Hydraulic Eng-ASCE, 121: 657–663.
13. Julien, P. Y. 1992. Study of Bed‌form Geometry in Large Rivers. PhD. Thesis, Colorado State University.
14. Julien, P. Y., Klaassen, G. J., Ten Brinke, W. B. M. and Wilbers, A. W. E. 2002. Case Study: Bed Resistance of Rhine River during 1998 Flood. J. Hydraulic Eng-ASCE, 128:1042-1050.
15. Kakaei Lafdani, E., Moghaddam. A. and Ahmadi, A. 2013. Daily Suspended Sediment Load Prediction Using Artificial Neural Networks and Support Vector Machines. J. Hydrol., 478: 50-62.
16. Karim, M. F. 1995. Bed Configuration and Hydraulic Resistance in Alluvial Channel Flows. J. Hydraulic Eng-ASCE, 121(1): 15–25.
17. Karamisheva. R. D., Lyness, J. F., Myers, W. R. C. and Sullivan, J. O. 2005. Prediction of Bedform height in Straight and Meandering Compound Channels. Water Resour. Manag. 80: 1743-3541.
18. Moharrampour, M., Mehrabi, A. and Katouzi, M. 2012. Daily Discharge Forecasting Using Support Vector Machine. Int. J. Info. Electronic Eng., 204(V2).
19. Riad, S. and Mania, J. 2004. Rainfall‌-runoff Model Using an Artificial Neural Network Approach. Math. Comput. Model., 40: 839-846.
20. Richards, K. J. 1980. The Formation of Ripples and Dunes on an Erodible Bed. J. Fluid Mech., 99: 597-618.
21. Simons, D. B., Richardson, E. V., and Albertson, M. L., 1961. Publishing, London, B, pp. 1429–1434.
22. Singh, A., Lanzoni, S., Wilcock, P. R. and Georgiou, E. F. 2011. Multiscale Statistical Characterization of Migrating Bed Forms in Gravel and Sand Bed Rivers. Water Resour. Res., 47: W12526.
23. Sivapragasam, C. and Liong, S. Y. 2000. Improving Higher Lead Period Runoff Forecasting Accuracy: the SVM Approach. 12th Congress of the Asia and Pacific Regional Division of the IAHR. Asian Institute of Technology, Bangkok, Vol 3: 855–861
24. Talebbeydokhti, N., Hekmatzadeh, A. A. and Rakhshanehroo. G. R. 2006. Experimental Modeling of Dune Bed Form in a Sand-bed Channel. Iranian Journal of Science and Technology, Transaction B, Engineering, 30(B4).
25. Tuijnder, A.P. and Ribberink, J.S. 2008. Bedform Dimensions under Supply Limited Conditions Morphology. Sedimentology, doi: 10.1111/j.1365-3091.2009.01054.x
26. Van Rijn, L. C. 1984. Sediment Transport. Part Ш. Bed Forms and Alluvial Roughness. J. Hydraulic Eng-ASCE, 110: 1733-1754.
27. Vapnik, V. 1995. The Nature of Statistical Learning Theory. Springer, New York.
28. Zhang, Y. 1999. Bed Form Geometry and Friction Factor of Flow over a Bed Covered by Dunes. PhD. Thesis, University of Windsor, Canada.
Journal of Agricultural Science and Technology
Volume 17, Issue 4
July and August 2015
Pages 859-868