Skip to main content
SpringerLink
Log in

Suspended sediment load prediction of river systems: GEP approach

  • Original Paper
  • Published:
Arabian Journal of Geosciences Aims and scope Submit manuscript

Abstract

This study presents gene expression programming (GEP), an extension of genetic programming, as an alternative approach to modeling the suspended sediment load relationship for the three Malaysian rivers. In this study, adaptive neuro-fuzzy inference system (ANFIS), regression model, and GEP approaches were developed to predict suspended load in three Malaysian rivers: Muda River, Langat River, and Kurau River [ANFIS (R 2 = 0.93, root mean square error (RMSE) = 3.19, and average error (AE) = 1.12) and regression model (R 2 = 0.63, RMSE = 13.96, and AE = 12.69)]. Additionally, the explicit formulations of the developed GEP models are presented (R 2 = 0.88, RMSE = 5.19, and AE = 6.5). The performance of the GEP model was found to be acceptable compare to ANFIS and better than the conventional models.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  • Ab. Ghani A (1993) Sediment transport in sewers. PhD thesis, University of Newcastle upon Tyne, UK

  • Azamathulla HMd, Ab. Ghani A (2011) Genetic programming for longitudinal dispersion coefficients in streams, Water Resour Manag 25(6):1537–1544

  • Azamathulla HMd, Wu FC (2011) Support vector machine approach to for longitudinal dispersion coefficients in streams, Appl Soft Comput 11(2):2902–2905

  • Azamathulla H Md., Aminuddin Ab. Ghani, Nor Azazi Zakaria, Chun Kiat Chang, and Zorkeflee Abu Hasan (2010) Genetic approach to predict sediment concentration for Malaysian rivers. International Journal of Ecological Economics & Statistics (IJEES) 16, W10.

  • Azamathulla HMd, Ab. Ghani A, Zakaria NA (2007) An ANFIS based approach for predicting the scour below flip-bucket spillway, 2nd International Conference on Managing Rivers in 21st Century: solutions towards Sustainable River Basins (Rivers'07). Kuching, Sarawak, Malaysia, pp 522–525

    Google Scholar 

  • Azamathulla HMd, Ghani AAb, Zakaria NA, Chang CK, Hasan ZA (2010) Machine learning approach to predict sediment load—a case study, CLEAN—Soil, Air. Water12 38(10):969–976

    Google Scholar 

  • Azmathullah HMd, Deo MC, Deolalikar PB (2005) Neural networks for estimation of scour downstream of a ski-jump bucket. J Hydraul Eng 131(10):898–908

    Article  Google Scholar 

  • Bateni SM, Borghei SM, Jeng DS (2007a) Neural network and neuro-fuzzy assessments for scour depth around bridge piers. Eng Appl Artif Intel 20:401–414

    Article  Google Scholar 

  • Bateni SM, Jeng DS, Melville BW (2007b) Bayesian neural networks for prediction of equilibrium and time-dependent scour depth around bridge piers. Adv Eng Software 28(2):102–111

    Article  Google Scholar 

  • Baylar A, Unsal M, Ozkan F (2011) GEP modeling of oxygen transfer efficiency prediction in aeration cascades. KSCE J Civ Eng 15(5):799–804

    Article  Google Scholar 

  • Brooks NH (1963) Calculation of suspended load from velocity and concentration parameters, Symposium 2.—Sediment in Streams, 229–237.

  • Cevik A (2007) A new formulation for longitudinally stiffened webs subjected to patch loading. J Constr Steel Res 63(10):1328–1340

    Article  Google Scholar 

  • Chang FM, Simons DB and Richardson EV (1965) Total bed-material discharge in alluvial channels, U.S. Geol. Survey Water-Supply Paper, 1498-I, 23.

  • Dogan E, Yuksel I, Kisi O (2007) Estimation of total sediment load concentration obtained by experimental study using artificial neural networks. Environ Fluid Mech 7:271–288

    Article  Google Scholar 

  • Einstein HA (1950) The bed-load function for sediment transportation in open channel flows, United States Department of Agriculture, Technical Bulletin No. 1026.

  • Ferreira C (2001) Gene expression programming: a new adaptive algorithm for solving problems. Complex Systems 13(2):87–129

    Google Scholar 

  • Fung R, Chen Y, Chen L, Tiang J (2005) A fuzzy expected value-based goal programing model for product planning using quality function deployment. Eng Optim 37(6):633–645

    Article  Google Scholar 

  • Gandomi AH, Alavi AH, Mirzahosseini MR, Moqhadas Nejad F (2011a) Nonlinear genetic-based models for prediction of flow number of asphalt mixtures. J Mater Civ Eng ASCE 23(3):248–263

    Article  Google Scholar 

  • Gandomi AH, Tabatabaie SM, Moradian MH, Radfar A, Alavi AH (2011b) A new prediction model for load capacity of castellated steel beams. J Constr Steel Res Elsevier 67(7):1096–1105

    Article  Google Scholar 

  • Gandomi AH, Babanajad SK, Alavi AH, Farnam Y (2012) A novel approach to strength modeling of concrete under triaxial compression. J Mater Civ Eng, ASCE. doi:10.1061/(ASCE)MT.1943-5533.0000494

  • Guven A, Aytek A (2009) A new approach for stage-discharge relationship: Gene-expression programming, J Hydrol Eng 14(8):812–820

    Article  Google Scholar 

  • Guven A, Gunal M, (2008) A genetic programming approach for prediction of local scour downstream hydraulic structures. J Irrig and Drain Engrg 132(4):241

    Google Scholar 

  • Jang J-SR (1993) ANFIS: adaptive-network-based fuzzy inference system. Man Cybern 23(3):665–685

    Article  Google Scholar 

  • Kayadelen C, Gunaydin O, Fener M, Demir A, Ozvan A (2009) Modeling of the angle of shearing resistance of soils using soft computing systems. Expert Syst Appl 36(9):11814–11826

    Article  Google Scholar 

  • Kisi O, Emin KM, Sen Z (2006) River suspended sediment modeling using a fuzzy logic approach. Hydrol Process 20:4351–4362

    Article  Google Scholar 

  • Lane EW, Kalinske AA (1941) Engineering calculations of suspended sediment. Trans Am Geophys Union 22:603–607

    Article  Google Scholar 

  • Melesse AM, Ahmad S, McClain ME, Wang X, Lim YH (2011) Suspended sediment load prediction of river systems: an artificial neural network approach. Agr Water Manag 98(2011):855–866

    Article  Google Scholar 

  • Muñoz DG (2005) Discovering unknown equations that describe large data sets using genetic programming techniques, Master Thesis, Electronic Systems, Linköping Institute of Technology, LITH-ISY-EX-05/3697

  • Ozger M, Sen Z (2007) Prediction of wave parameters by using fuzzy logic approach. Ocean Eng 34(3–4):460–469

    Article  Google Scholar 

  • Rouse H (1937) Modern conceptions of the mechanics of sediment suspension. Trans ASCE 102:463–543

    Google Scholar 

  • Sinnakaudan SK, Ab. Ghani A, Ahmad MSS, Zakaria, NA (2006) Multiple linear regression model for total bed material load prediction, J Hydraul Eng 132(5):521–528

  • Teodorescu L, Sherwood D (2008) High energy physics event selection with gene expression programming. Comput Phys Commun 178(6):409–419

    Article  Google Scholar 

  • Turkmen I, Kerim G, Dervis K (2006) Genetic tracker with neural network for single and multiple target tracking. Neurocomputing 69(16–18):2309–2319

    Article  Google Scholar 

  • Van Rijn LC (1984) Sediment transport, part I: bed load transport. J Hydraul Eng 110(10):1431–1456

    Google Scholar 

  • Yang CT (1996) Sediment transport: theory and practice. McGraw-Hill, New York

    Google Scholar 

Download references

Acknowledgments

The authors wish to express their sincere gratitude to Universiti Sains Malaysia for funding a research university grant to conduct this on-going research (PRE.1001/PREDAC/811077).

Author information

Authors and Affiliations

  1. River Engineering and Urban Drainage Research Centre (REDAC), Universiti Sains Malaysia, Engineering Campus, Seri Ampangan, 14300, Nibong Tebal, Pulau Pinang, Malaysia

    H. Md. Azamathulla, Aminuddin Ab. Ghani & Chun Kiat Chang

  2. School of Civil Engineering, Universiti Sains Malaysia, Engineering Campus, Seri Ampangan, 14300, Nibong Tebal, Penang, Malaysia

    Yong Chong Cuan

Authors
  1. H. Md. Azamathulla
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yong Chong Cuan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Aminuddin Ab. Ghani
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Chun Kiat Chang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to H. Md. Azamathulla.

Appendix

Appendix

ANFIS rules

  1. 1.

    If (Q is Qmf1) and (B/Y 0 is B/Y 0mf1) and (R/d 50 is R/d 50mf1) and (V/(g[S s − 1]d 50)1/2 is V/(g[S s − 1]d 50)1/2mf1) and (Y 0/d 50 is Y 0/d 50mf1) then (Ts is Tsmf1)

  2. 2.

    If (Q is Qmf2) and (B/Y 0 is B/Y 0mf2) and (R/d 50 is R/d 50mf2) and (V/(g[S s − 1]d 50)1/2 is V/(g[S s − 1]d 50)1/2mf2) and (Y 0/d 50 is Y 0/d 50mf2) then (Ts is Tsmf2)

  3. 3.

    If (Q is Qmf3) and (B/Y 0 is B/Y 0mf3) and (R/d 50 is R/d 50mf3) and (V/(g[S s − 1]d 50)1/2 is V/(g[S s − 1]d 50)1/2mf3) and (Y 0/d 50 is Y 0/d 50mf3) then (Ts is Tsmf3)

  4. 4.

    If (Q is Qmf4) and (B/Y 0 is B/Y 0mf4) and (R/d 50 is R/d 50mf4) and (V/(g[S s − 1]d 50)1/2 is V/(g[S s − 1]d 50)1/2mf4) and (Y 0/d 50 is Y 0/d 50mf4) then (Ts is Tsmf4)

  5. 5.

    If (Q is Qmf5) and (B/Y 0 is B/Y 0mf5) and (R/d 50 is R/d 50mf5) and (V/(g[S s − 1]d 50)1/2 is V/(g[S s − 1]d 50)1/2mf5) and (Y 0/d 50 is Y 0/d 50mf5) then (Ts is Tsmf5)

  6. 6.

    If (Q is Qmf6) and (B/Y 0 is B/Y 0mf6) and (R/d 50 is R/d 50mf6) and (V/(g[S s − 1]d 50)1/2 is V/(g[S s − 1]d 50)1/2mf6) and (Y 0/d 50 is Y 0/d 50mf6) then (Ts is Tsmf6)

  7. 7.

    If (Q is Qmf7) and (B/Y 0 is B/Y 0mf7) and (R/d 50 is R/d 5050mf7) and (V/(g[S s − 1]d 50)1/2 is V/(g[S s − 1]d 50)1/2mf7) and (Y 0/d 50 is Y 0/d 50mf7) then (Ts is Tsmf7)

  8. 8.

    If (Q is Qmf8) and (B/Y 0 is B/Y 0mf8) and (R/d 50 is R/d 50mf8) and (V/(g[S s − 1]d 50)1/2 is V/(g[S s − 1]d 50)1/2mf8) and (Y 0/d 50 is Y 0/d 50mf8) then (Ts is Tsmf8)

  9. 9.

    If (Q is Qmf9) and (B/Y 0 is B/Y 0mf9) and (R/d 50 is R/d 50mf9) and (V/(g[S s − 1]d 50)1/2 is V/(g[S s − 1]d 50)1/2mf9) and (Y 0/d 50 is Y 0/d 50mf9) then (Ts is Tsmf9)

  10. 10.

    If (Q is Qmf10) and (B/Y 0 is B/Y 0mf10) and (R/d 50 is R/d 50mf10) and (V/(g[S s − 1]d 50)1/2 is V/(g[S s − 1]d 50)1/2mf10) and (Y 0/d 50 is Y 0/d 50mf10) then (Ts is Tsmf10)

  11. 11.

    If (Q is Qmf11) and (B/Y 0 is B/Y 0mf11) and (R/d 50 is R/d 50mf11) and (V/(g[S s − 1]d 50)1/2 is V/(g[S s − 1]d 50)1/2mf11) and (Y 0/d 50 is Y 0/d 50mf11) then (Ts is Tsmf11)

  12. 12.

    If (Q is Qmf12) and (B/Y 0 is B/Y 0mf12) and (R/d 50 is R/d 50mf12) and (V/(g[S s − 1]d 50)1/2 is V/(g[S s − 1]d 50)1/2mf12) and (Y 0/d 50 is Y 0/d 50mf12) then (Ts is Tsmf12)

  13. 13.

    If (Q is Qmf13) and (B/Y 0 is B/Y 0mf13) and (R/d 50 is R/d 50mf13) and (V/(g[S s − 1]d 50)1/2 is V/(g[S s − 1]d 50)1/2mf13) and (Y 0/d 50 is Y 0/d 50mf13) then (Ts is Tsmf13)

  14. 14.

    If (Q is Qmf14) and (B/Y 0 is B/Y 0mf14) and (R/d 50 is R/d 50mf14) and (V/(g[S s − 1]d 50)1/2 is V/(g[S s − 1]d 50)1/2mf14) and (Y 0/d 50 is Y 0/d 50mf14) then (Ts is Tsmf14)

  15. 15.

    If (Q is Qmf15) and (B/Y 0 is B/Y 0mf15) and (R/d 50 is R/d 50mf15) and (V/(g[S s − 1]d 50)1/2 is V/(g[S s − 1]d 50)1/2mf15) and (Y 0/d 50 is Y 0/d 50mf15) then (Ts is Tsmf15)

  16. 16.

    If (Q is Qmf16) and (B/Y 0 is B/Y 0mf16) and (R/d 50 is R/d 50mf16) and (V/(g[S s − 1]d 50)1/2 is V/(g[S s − 1]d 50)1/2mf16) and (Y 0/d 50 is Y 0/d 50mf16) then (Ts is Tsmf16)

  17. 17.

    If (Q is Qmf17) and (B/Y 0 is B/Y 0mf17) and (R/d 50 is R/d 50mf17) and (V/(g[S s − 1]d 50)1/2 is V/(g[S s − 1]d 50)1/2mf17) and (Y 0/d 50 is Y 0/d 50mf17) then (Ts is Tsmf17)

  18. 18.

    If (Q is Qmf18) and (B/Y 0 is B/Y 0mf18) and (R/d 50 is R/d 50mf18) and (V/(g[S s − 1]d 50)1/2 is V/(g[S s − 1]d 50)1/2mf18) and (Y 0/d 50 is Y 0/d 50mf18) then (Ts is Tsmf18)

  19. 19.

    If (Q is Qmf19) and (B/Y 0 is B/Y 0mf19) and (R/d 50 is R/d 50mf19) and (V/(g[S s − 1]d 50)1/2 is V/(g[S s − 1]d 50)1/2mf19) and (Y 0/d 50 is Y 0/d 50mf19) then (Ts is Tsmf19)

  20. 20.

    If (Q is Qmf20) and (B/Y 0 is B/Y 0mf20) and (R/d 50 is R/d 50mf20) and (V/(g[S s − 1]d 50)1/2 is V/(g[S s − 1]d 50)1/2mf20) and (Y 0/d 50 is Y 0/d 50mf20) then (Ts is Tsmf20)

  21. 21.

    If (Q is Qmf21) and (B/Y 0 is B/Y 0mf21) and (R/d 50 is R/d 50mf21) and (V/(g[S s − 1]d 50)1/2 is V/(g[S s − 1]d 50)1/2mf21) and (Y 0/d 50 is Y 0/d 50mf21) then (Ts is Tsmf21)

  22. 22.

    If (Q is Qmf22) and (B/Y 0 is B/Y 0mf22) and (R/d 50 is R/d 50mf22) and (V/(g[S s − 1]d 50)1/2 is V/(g[S s − 1]d 50)1/2mf22) and (Y 0/d 50 is Y 0/d 50mf22) then (Ts is Tsmf22)

  23. 23.

    If (Q is Qmf23) and (B/Y 0 is B/Y 0mf23) and (R/d 50 is R/d 50mf23) and (V/(g[S s − 1]d 50)1/2 is V/(g[S s − 1]d 50)1/2mf23) and (Y 0/d 50 is Y 0/d 50mf23) then (Ts is Tsmf23)

Rights and permissions

Reprints and permissions

About this article

Cite this article

Azamathulla, H.M., Cuan, Y.C., Ghani, A.A. et al. Suspended sediment load prediction of river systems: GEP approach. Arab J Geosci 6, 3469–3480 (2013). https://doi.org/10.1007/s12517-012-0608-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12517-012-0608-4

Keywords

Search

Navigation