Acta Geophysica

, Volume 67, Issue 6, pp 1649–1660 | Cite as

Suspended sediment discharge modeling during flood events using two different artificial neural network algorithms

  • Hamza BouguerraEmail author
  • Salah-Eddine Tachi
  • Oussama Derdous
  • Abderrazak Bouanani
  • Kamel Khanchoul
Research Article - Hydrology


This paper presents modeling of artificial neural network (ANN) to forecast the suspended sediment discharges (SSD) during flood events in two different catchments in the Seybouse basin, northeastern Algeria. This study was carried out on hourly SSD and water discharge data during flood events from a period of 31 years in the Ressoul catchment and of 28 years in the Mellah catchment. The ANNs were trained according to two different algorithms: the Levenberg–Marquardt algorithm (LM) and the Quasi-Newton algorithm (BFGS). Seven input combinations were trained for the SSD prediction. The performance results indicated that both algorithms provided satisfactory simulations according to the determination coefficient (R2) and root mean squared error (RMSE) performance criteria, with priority to the BFGS algorithm; the coefficient of determination using the LM algorithm varies between 51.0 and 90.2%, whereas using the BFGS algorithm it varies between 54.3 and 93.5% in both studied catchments, with calculated improvement for all seven developed networks with the best improvement in the Ressoul catchment presented in ANN06 with \(\Delta_{{R^{2} }}\) 4.23% and \(\Delta_{{{\text{RMSE}}}}\) 1.74‰, and with the best improvement presented in ANN05 with \(\Delta_{{R^{2} }}\) 6.07% and \(\Delta_{{{\text{RMSE}}}}\) 0.71‰ in the Mellah catchment. The analysis showed that the use of Quasi-Newton method performed better than the Levenberg–Marquardt in both studied areas.


Suspended sediment discharges Flood events Modeling Artificial neural network Levenberg–Marquardt algorithm Quasi-Newton algorithm 


  1. Afan HA, El-Shafie A, Yaseen ZM, Hameed MM, Mohtar WHMW, Hussain A (2015) ANN based sediment prediction model utilizing different input scenarios. Water Resour Manag 29:1231–1245CrossRefGoogle Scholar
  2. Ahmed F, Hassan M, Hashmi HN (2018) Developing nonlinear models for sediment load estimation in an irrigation canal. Acta Geophys 66:1485–1494CrossRefGoogle Scholar
  3. Alizadeh MJ, Nodoushan EJ, Kalarestaghi N, Chau KW (2017) Toward multi-day-ahead forecasting of suspended sediment concentration using ensemble models. Environ Sci Pollut Res 24:28017–28025CrossRefGoogle Scholar
  4. Alp M, Cigizoglu HK (2007) Suspended sediment load simulation by two artificial neural network methods using hydrometeorological data. Environ Model softw 22:2–13CrossRefGoogle Scholar
  5. Bae DH, Jeong DM, Kim G (2007) Monthly dam inflow forecasts using weather forecasting information and neuro-fuzzy technique. Hydrol Sci J 52:99–113CrossRefGoogle Scholar
  6. Bouguerra H, Bouanani A, Khanchoul K, Derdous O, Tachi SE (2017) Mapping erosion prone areas in the Bouhamdane watershed (Algeria) using the Revised Universal Soil Loss Equation through GIS. J Water Land Dev 32:13–23CrossRefGoogle Scholar
  7. Bouhadeb CHE, Menani MR, Bouguerra H, Derdous O (2018) Assessing soil loss using GIS based RUSLE methodology, case of the Bou Namoussa watershed – North-East of Algeria. J Water Land Dev 36:27–35CrossRefGoogle Scholar
  8. Bouzeria H, Ghenim AN, Khanchoul K (2017) Using artificial neural network (ANN) for prediction of sediment loads, application to the Mellah catchment, northeast Algeria. J Water Land Dev 33:47–55CrossRefGoogle Scholar
  9. Broyden CG (1970) The convergence of single-rank quasi-newton methods. Math Comput 24:365–382CrossRefGoogle Scholar
  10. Clair TA, Ehrman JM (1998) Using neural networks to assess the influence of changing seasonal climates in modifying discharge, dissolved organic carbon and nitrogen export in eastern Canadian rivers. Water Resour Res 34:447–455CrossRefGoogle Scholar
  11. Dennis J, More J (1977) Quasi-Newton methods, motivation and theory. SIAM Rev Soc Ind Appl Math 19:46–89Google Scholar
  12. Fletcher R (1970) A new approach to variable metric algorithms. Comput J 13:317–322CrossRefGoogle Scholar
  13. Goldfarb D (1970) A family of variable-metric methods derived by variational means. Math Comput 24:23–26CrossRefGoogle Scholar
  14. Golob R, Štokelj T, Grgič D (1998) Neural-network-based water inflow forecasting. Control Eng Pract 6:593–600CrossRefGoogle Scholar
  15. Hagan MT, Menhaj MB (1994) Training multilayer networks with the Marquardt algorithm. IEEE Trans Neural Netw 5:989–993CrossRefGoogle Scholar
  16. Halff AH, Halff HM, Azmoodeh M (1993) Predicting runoff from rainfall using neural networks. In: Engineering hydrology. ASCE, pp 760–765Google Scholar
  17. Hassan M, Shamim MA, Sikandar A, Mehmood I, Ahmed I, Ashiq SZ, Khitab A (2015) Development of sediment load estimation models by using artificial neural networking techniques. Environ Monit Assess 187(11):686CrossRefGoogle Scholar
  18. Hassan M, Zaffar H, Mehmood I, Khitab A (2018) Development of streamflow prediction models for a weir using ANN and step-wise regression. Model Earth Syst Environ 4:1021–1028CrossRefGoogle Scholar
  19. Jain SK, Das A, Srivastava DK (1999) Application of ANN for reservoir inflow prediction and operation. J Water Resour Plan Manag 125:263–271CrossRefGoogle Scholar
  20. Kisi Ö (2004) Multi-layer perceptrons with Levenberg–Marquardt training algorithm for suspended sediment concentration prediction and estimation. Hydrol Sci J 49:1025–1040Google Scholar
  21. Melesse AM, Ahmad S, McClain ME, Wang X, Lim YH (2011) Suspended sediment load prediction of river systems: An artificial neural network approach. Agric Water Manag 98:855–866CrossRefGoogle Scholar
  22. Mustafa MR, Rezaur RB, Saiedi S, Isa MH (2012) River suspended sediment prediction using various multilayer perceptron neural network training algorithms—a case study in Malaysia. Water Resour Manage 26:1879–1897CrossRefGoogle Scholar
  23. Nagy HM, Watanabe KAND, Hirano M (2002) Prediction of sediment load concentration in rivers using artificial neural network model. J Hydraul Eng 128:588–595CrossRefGoogle Scholar
  24. Partal T (2009) River flow forecasting using different artificial neural network algorithms and wavelet transform. Can J Civ Eng 36:26–39CrossRefGoogle Scholar
  25. Piasecki A, Jurasz J, Adamowski JF (2018) Forecasting surface water-level fluctuations of a small glacial lake in Poland using a wavelet-based artificial intelligence method. Acta Geophys 66:1093–1107CrossRefGoogle Scholar
  26. Riad S, Mania J, Bouchaou L, Najjar Y (2004) Rainfall-runoff model using an artificial neural network approach. Math Comput Model 40:839–846CrossRefGoogle Scholar
  27. Rowinski PM, Czernuszenko W (1998) Experimental study of river turbulence under unsteady conditions. Acta Geophysica Polonica 46:461–480Google Scholar
  28. Sahoo GB, Ray C, De-Carlo EH (2006) Use of neural network to predict flash flood and attendant water qualities of a mountainous stream on Oahu. Hawaii J Hydrol 327:525–538CrossRefGoogle Scholar
  29. Shamim MA, Hassan M, Ahmad S, Zeeshan M (2016) A Comparison of artificial neural networks (ANN) and local linear regression (LLR) techniques for predicting monthly reservoir levels. KSCE J Civ Eng 20:971–977CrossRefGoogle Scholar
  30. Shanno DF (1970) Conditioning of Quasi-Newton methods for function minimization. Math Comput 24:647–656CrossRefGoogle Scholar
  31. Sudheer KP, Jain A (2004) Explaining the internal behaviour of artificial neural network river flow models. Hydrol Process 18:833–844CrossRefGoogle Scholar
  32. Tachi SE, Ouerdachi L, Remaoun M, Derdous O, Boutaghane H (2016) Forecasting suspended sediment load using regularized neural network: case study of the Isser River (Algeria). J Water Land Dev 29:75–81CrossRefGoogle Scholar
  33. Wang WC, Chau KW, Cheng CT, Qiu L (2009) A comparison of performance of several artificial intelligence methods for forecasting monthly discharge time series. J Hydrol 374:294–306CrossRefGoogle Scholar
  34. Wilamowski BM, Yu H (2010) Improved computation for Levenberg–Marquardt training. IEEE Trans Neural Netw 21:930–937CrossRefGoogle Scholar
  35. Zealand CM, Burn DH, Simonovic SP (1999) Short term streamflow forecasting using artificial neural networks. J Hydrol 214:32–48CrossRefGoogle Scholar
  36. Zhu YM, Lu XX, Zhou Y (2007) Suspended sediment flux modeling with artificial neural network: an example of the Longchuanjiang River in the Upper Yangtze Catchment, China. Geomorphology 84:111–125CrossRefGoogle Scholar
  37. Zou R, Lung WS, Wu J (2007) An adaptive neural network embedded genetic algorithm approach for inverse water quality modeling. Water Resour Res 43:W08427CrossRefGoogle Scholar

Copyright information

© Institute of Geophysics, Polish Academy of Sciences & Polish Academy of Sciences 2019

Authors and Affiliations

  1. 1.Department of Hydraulic, Faculty of TechnologyUniversity of Abu Baker BelkaidTlemcenAlgeria
  2. 2.Laboratoire de Recherche Science de L’eauNational Polytechnic SchoolAlgiersAlgeria
  3. 3.Department of Civil and Hydraulic Engineering, Faculty of Applied SciencesUniversity of OuarglaOuarglaAlgeria
  4. 4.Department of Geology, Faculty of Earth SciencesUniversity of Badji MokhtarAnnabaAlgeria

Personalised recommendations