Neural Computing and Applications

, Volume 28, Supplement 1, pp 207–216 | Cite as

Estimation of soil dispersivity using soft computing approaches

  • Samad EmamgholizadehEmail author
  • Kiana Bahman
  • S. Mohyeddin Bateni
  • Hadi Ghorbani
  • Isa Marofpoor
  • Jeffrey R. Nielson
Original Article


The accurate estimation of soil dispersivity (α) is required for characterizing the transport of contaminants in soil. The in situ measurement of α is costly and time-consuming. Hence, in this study, three soft computing methods, namely adaptive neuro-fuzzy inference system (ANFIS), artificial neural network (ANN), and gene expression programming (GEP), are used to estimate α from more readily measurable physical soil variables, including travel distance from source of pollutant (L), mean grain size (D 50), soil bulk density (ρ b), and contaminant velocity (V c). Based on three statistical metrics [i.e., mean absolute error, root-mean-square error (RMSE), and coefficient of determination (R 2)], it is found that all approaches (ANN, ANFIS, and GEP) can accurately estimate α. Results also show that the ANN model (with RMSE = 0.00050 m and R 2 = 0.977) performs better than the ANFIS model (with RMSE = 0.00062 m and R 2 = 0.956), and the estimates from GEP are almost as accurate as those from ANFIS. The performance of ANN, ANFIS, and GEP models is also compared with the traditional multiple linear regression (MLR) method. The comparison indicates that all of the soft computing methods outperform the MLR model. Finally, the sensitivity analysis shows that the travel distance from source of pollution (L) and bulk density (ρ b) have, respectively, the most and the least effect on the soil dispersivity.


Soil dispersivity Adaptive neuro-fuzzy inference system Artificial neural network Genetic expression programming Multiple linear regression 


  1. 1.
    Dominguez JB (2008) Soil contamination research trends. Nova Publishers, New York. ISBN-13: 978-1604563191Google Scholar
  2. 2.
    Fried JJ, Combarnous MA (1971) Dispersion in porous media. In: Chow VT (ed) Advances in hydroscience. Academic Press, New York, pp 169–282Google Scholar
  3. 3.
    Bruggeman GA (1999) Analytical solutions of geohydro-logical problems. New York. Elsevier. ISBN 0-444-81829-4Google Scholar
  4. 4.
    Perfect E, Sukop MC, Haszler GR (2002) Prediction of dispersivity for undisturbed soil columns from water retention parameters. Soil Sci Soc Am J 66(3):696–701. doi: 10.2136/sssaj2002.6960 CrossRefGoogle Scholar
  5. 5.
    Ujfaludi L (1986) Longitudinal dispersion tests in non-uniform porous media. Hydrol Sci J 31(4):467–474. doi: 10.1080/02626668609491067 CrossRefGoogle Scholar
  6. 6.
    Freeze RA, Cherry JA (1979) Groundwater. Prentice-Hall. Englewood Cliffs, NJ. ISBN-13: 978-0133653120Google Scholar
  7. 7.
    Gillham RW, Cherry JA (1982) Contaminant migration in saturated unconsolidated geological deposits. Geol Soc Spec Pap 189:31–62. doi: 10.1130/SPE189-p31GSA Google Scholar
  8. 8.
    Cal Y (1995) Soil classification by neural network. Adv Eng Softw 22(2):95–97. doi: 10.1016/0965-9978(94)00035-H CrossRefGoogle Scholar
  9. 9.
    Mukhlisin M, El-Shafie A, Taha MR (2012) Regularized versus non-regularized neural network model for prediction of saturated soil-water content on weathered granite soil formation. Neural Comput Appl 21(3):543–553. doi: 10.1007/s00521-011-0545-2 CrossRefGoogle Scholar
  10. 10.
    Taghavifar H, Mardani A (2014) Use of artificial neural networks for estimation of agricultural wheel traction force in soil bin. Neural Comput Appl 24(6):1249–1258. doi: 10.1007/s00521-013-1360-8 CrossRefGoogle Scholar
  11. 11.
    Yusof MF, Azamathulla HM, Abdullah R (2014) Prediction of soil erodibility factor for Peninsular Malaysia soil series using ANN. Neural Comput Appl 24(2):383–389. doi: 10.1007/s00521-012-1236-3 CrossRefGoogle Scholar
  12. 12.
    Rowinski PM, Piotrowski A, Napiorkowski JJ (2005) Are artificial neural network techniques relevant for the estimation of longitudinal dispersion coefficient in rivers? Hydrol Sci J 50(1):175–187. doi: 10.1623/hysj. CrossRefGoogle Scholar
  13. 13.
    Toprak ZF, Cigizoglu HK (2008) Predicting longitudinal dispersion coefficient in natural streams by artificial intelligence methods. Hydrol Process 22(20):4106–4129. doi: 10.1002/hyp.7012 CrossRefGoogle Scholar
  14. 14.
    Toprak ZF (2004) Determination of longitudinal dispersion coefficient in natural channel using fuzzy logic method. Ph.D. thesis, ITU, Institute of Science and TechnologyGoogle Scholar
  15. 15.
    Tayfur G, Singh VP (2005) Predicting longitudinal dispersion coefficient in natural streams by artificial neural network. J Hydraul Eng ASCE 131(11):991–1000. doi: 10.1061/(ASCE)0733-9429(2005)131:11(991) CrossRefGoogle Scholar
  16. 16.
    Piotrowski A (2005) Application of neural networks for longitudinal dispersion coefficient assessment. Geophys Res Abstr 7:00976 (Hs1-1th5p-0003) Google Scholar
  17. 17.
    Madvar HR, Ayyoubzadeh SA, Khadangi E, Ebadzadeh MM (2009) An expert system for predicting longitudinal coefficient in natural streams by using ANFIS. Expert Syst Appl 36(4):8589–8596. doi: 10.1016/j.eswa.2008.10.043 CrossRefGoogle Scholar
  18. 18.
    Sattar A (2013) Gene expression models for the prediction of longitudinal dispersion coefficients in transitional and turbulent pipe flow. J Pipeline Syst Eng Pract. doi: 10.1061/(ASCE)PS.1949-1204.0000153 Google Scholar
  19. 19.
    Noori R, Karbassi A, Farokhnia A, Dehghani M (2009) Predicting the longitudinal dispersion coefficient using support vector machine and adaptive neuro-fuzzy inference system techniques. Environ Eng Sci 26(10):1503–1510. doi: 10.1089/ees.2008.0360 CrossRefGoogle Scholar
  20. 20.
    Kashi H, Emamgholizadeh S, Ghorbani H (2014) Estimation of soil infiltration and cation exchange capacity based on multiple regression, ANN (RBF, MLP), and ANFIS models. Commun Soil Sci Plant 45(9):1195–1213. doi: 10.1080/00103624.2013.874029 CrossRefGoogle Scholar
  21. 21.
    Haykin S (1994) Neural networks. A comprehensive foundation. IEEE press, MacMillan, New York. ISBN: 0023527617Google Scholar
  22. 22.
    Emamgholizadeh S, Parsaeian M, Baradaran M (2015) Seed yield prediction of sesame using artificial neural network. Eur J Agron 68:89–967. doi: 10.1016/j.eja.2015.04.010 CrossRefGoogle Scholar
  23. 23.
    Azamathulla HM (2013) A review on application of soft computing methods in water resources engineering. Metaheuristics Water Geotech Transp Eng. doi: 10.1016/B978-0-12-398296-4.00002-7 Google Scholar
  24. 24.
    Rumelhart DE, Mcclelland JL, PDP research group (1986) Parallel recognition in modern computers. In: Proceeding: explorations in the microstructure of cognition. Foundations, MIT Press/Bradford Book, Cambridge MassGoogle Scholar
  25. 25.
    Azamathulla HM, Deo MC, Deolalikar PB (2005) Neural networks for estimation of scour downstream of a ski-jump bucket. ASCE J Hydraul Eng ASCE 131(10):898–908. doi: 10.1061/(ASCE)0733-9429(2005)131:10(898) CrossRefGoogle Scholar
  26. 26.
    Jang JSR (1993) ANFIS-Adaptive-network-based fuzzy inference system. IEEE Trans Syst Sci Cybern 23(3):665–685. doi: 10.1109/21.256541 CrossRefGoogle Scholar
  27. 27.
    Adewuyi PA (2012) Performance evaluation of Mamdani-type and Sugeno-type fuzzy inference system based controllers for computer fan. Int J Info Technol Comput Sci 5(1):26–36. doi: 10.5815/ijitcs.2013.01.03 Google Scholar
  28. 28.
    User’s Guide of MATLAB (2002) Fuzzy logic toolbox for use with MATLAB. The MathWorks, Inc. Version 2.1.2, 1-244Google Scholar
  29. 29.
    Emamgholizadeh S, Kashi H, Marofpoor I, Zalaghi E (2014) Prediction of water quality parameters of Karoon River (Iran) by artificial intelligence-based models. Int J Environ Sci Technol (IJEST) 11(3):645–656. doi: 10.1007/s13762-013-0378-x CrossRefGoogle Scholar
  30. 30.
    Mitchell M (1996) An introduction to genetic algorithms. MIT press, LondonzbMATHGoogle Scholar
  31. 31.
    Ferreira C (2001) Gene expression programming: a new adaptive algorithm for solving problems. Complex Syst J 13(2):87–129MathSciNetzbMATHGoogle Scholar
  32. 32.
    Ferreira C (2001) Gene expression programming in problem solving. In: Invited tutorial of the 6th online world conference on soft computing in industrial applications, September 10–24Google Scholar
  33. 33.
    Zahiri R, Azamathulla HM, Ghorbani KH (2014) Prediction of local scour depth downstream of bed sills using soft computing models. Comput Intell Tech Earth Environ Sci. doi: 10.1007/978-94-017-8642-3_11 Google Scholar
  34. 34.
    Ferreira C (2006) Gene expression programming: mathematical modeling by an artificial intelligence, 2nd edn. Springer, Berlin. ISBN: 3540327967Google Scholar
  35. 35.
    Brigham WE (1974) Mixing equations in short laboratory columns. Soc Pet Eng J 14:91–99CrossRefGoogle Scholar
  36. 36.
    Liu CCK, Loague K, Feng JS (1991) Fluid flow and solute transport processes in unsaturated heterogeneous soils: preliminary numerical experiments. J Contam Hydrol 7(3):261–283. doi: 10.1016/0169-7722(91)90031-U CrossRefGoogle Scholar
  37. 37.
    Reinsch TG, Grossman RB (1995) A method to predict bulk density of tilled Ap horizons. Soil Tillage Res 34(2):95–104. doi: 10.1016/0167-1987(95)00458-5 CrossRefGoogle Scholar
  38. 38.
    Bromly M, Hinz C, Aylmore LAG (2007) Relation of dispersivity to properties of homogeneous saturated repacked soil columns. Eur J Soil Sci 58(1):293–301. doi: 10.1111/j.1365-2389.2006.00839.x CrossRefGoogle Scholar
  39. 39.
    Alipour R, Kamanbedast AA (2011) Investigation of vertical transmission of pollution at laboratory model and it's vitalizing for determination of dispersion coefficient at homogenous sandy soil. World Appl Sci J 14(2): 351–355. ISSN: 1818-4952Google Scholar
  40. 40.
    Xu M, Eckstein Y (1997) Statistical analysis of the relationships between dispersivity and other physical properties of porous media. Hydrogeol J 5(4):4–20. doi: 10.1007/s100400050254 CrossRefGoogle Scholar
  41. 41.
    Gelhar LW, Axness CL (1983) Three dimensional stochastic analysis of macrodispersion in aquifers. Water Resour Res 19(1):161–180. doi: 10.1029/WR019i001p00161 CrossRefGoogle Scholar
  42. 42.
    Neuman SP (1990) Universal scaling of hydraulic conductivities and dispersivities in geologic media. Water Resour Res 26(8):1749–1758. doi: 10.1029/WR026i008p01749 CrossRefGoogle Scholar
  43. 43.
    Singh KP, Basant A, Malik A, Jain G (2009) Artificial neural network modeling of the river water quality, a case study. Ecol Model 220(6):888–895. doi: 10.1016/j.ecolmodel.2009.01.004 CrossRefGoogle Scholar
  44. 44.
    Bateni SM, Borghei SM, Jeng DS (2007) Neural network and neuro-fuzzy assessments for scour depth around bridge piers. Eng Appl Artif Intell 20(3):401–414. doi: 10.1016/j.engappai.2006.06.012 CrossRefGoogle Scholar
  45. 45.
    Emamgholizadeh S, Moslemi K, Karami G (2014) Prediction the groundwater level of bastam plain (Iran) by artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS). Water Resour Manag 28(15):5433–5446. doi: 10.1007/s11269-014-0810-0 CrossRefGoogle Scholar
  46. 46.
    Emamgholizadeh S, Bateni SM, Shahsavani D, Ashrafi T, Ghorbani H (2015) Estimation of soil cation exchange capacity using Genetic Expression Programming (GEP) and Multivariate Adaptive Regression Splines (MARS). J Hydrol. doi: 10.1016/j.jhydrol.2015.08.025 Google Scholar
  47. 47.
    Azamathulla HM, Ahmad Z (2012) Gene-expression programming for transverse mixing coefficient. J Hydrol 434–435:142–148. doi: 10.1016/j.jhydrol.2012.02.018 CrossRefGoogle Scholar
  48. 48.
    Zahiri R, Dehghani AA, Azamathulla HM (2015) Application of gene-expression programming in hydraulic engineering. In: Gandomi AH et al (eds) Handbook of genetic programming applications. Springer International Publishing, Switzerland. doi: 10.1007/978-3-319-20883-1_4 Google Scholar
  49. 49.
    Guven A, Talu NE (2010) Gene expression programing for estimating suspended sediment yield in Middle Euphrates Basin, Turkey. Clean Soil Air Water 38(12):1159–1168. doi: 10.1002/clen.201000003 CrossRefGoogle Scholar
  50. 50.
    Parhizkar S, Ajdari K, Kazemi GA, Emamgholizadeh S (2015) Predicting water level drawdown and assessment of land subsidence in Damghan aquifer by combining GMS and GEP models. Geopersia 5(1):63–80Google Scholar
  51. 51.
    Hashmi MZ, Shamseldin AY, Melville BW (2011) Statistical downscaling of watershed precipitation using gene expression programming (GEP). Environ Model Softw 26:1639–1646. doi: 10.1016/j.envsoft.2011.07.007 CrossRefGoogle Scholar
  52. 52.
    Azamathulla HM, Jarrett RD (2013) Use of gene-expression programming to estimate manning’s roughness coefficient for high gradient streams. Water Resour Manag 27(3):715–729. doi: 10.1007/s11269-012-0211-1 CrossRefGoogle Scholar
  53. 53.
    SPSS Inc (2007) SPSS Base 16.0 applications guide. SPSS Inc., ChicagoGoogle Scholar

Copyright information

© The Natural Computing Applications Forum 2016

Authors and Affiliations

  • Samad Emamgholizadeh
    • 1
    Email author
  • Kiana Bahman
    • 1
  • S. Mohyeddin Bateni
    • 2
  • Hadi Ghorbani
    • 1
  • Isa Marofpoor
    • 3
  • Jeffrey R. Nielson
    • 2
  1. 1.Department of Water and Soil EngineeringShahrood University of TechnologyShahroodIran
  2. 2.Department of Civil and Environmental Engineering and Water Resource Research CenterUniversity of Hawaii at ManoaHonoluluUSA
  3. 3.Department of Water EngineeringUniversity of KurdistanSanandajIran

Personalised recommendations