Evaluation of Regression and Artificial Neural Network Models to Estimate the Saturated Hydraulic Conductivity in Mazandaran Province

Authors

1 Former MSc student of Sari Agricultural Sciences and Natural Resources University

2 Associate Professor, Sari Agricultural Sciences and Natural Resources University

3 Assistant Professor, Sari Agricultural Sciences and Natural Resources University

4 Assistant Professor, Sari University of Agricultural Sciences and Natural Resources

Abstract

Soil saturated hydraulic conductivity (Ks) is one of the important factors involved in water, soil, and agricultural sciences. Ks measurement is important for solute and water movement modeling and, in turn, is costly and time consuming. It is also impractical to spatially and temporarily measure the Ks in large scale studies. Therefore, it would be wise to predict Ks using indirect methods such as pedotransfer functions (PTFs). The objective of this study was to use the regression and artificial neural networks methods as an alternative method to estimate the saturated hydraulic conductivity. Therefore, 80 undisturbed soil samples in three replications were collected in Mazandaran province, northern Iran, and analyzed by laboratory methods. Data was divided into two categories including the training (80%) and testing dataset (20%). In order to predict the soil saturated hydraulic conductivity, the multiple linear regression models (MLR), multilayer perceptron (MLP) and radial basis function (RBF) methods were used. To test the performance of the three methods, the correlation (R2), mean square error (RMSE) and consistent correlation coefficient (CCC) statistics between actual and predicted values were measured. The results showed that MLP with two hidden layers by sigmoid activation function was the best method for Ks estimation. R2, RMSE and CCC statistics were 0.871, 1.02 cm/h [M1] and 0.869, respectively, for the best predicted method. The sensitivity analysis showed that the soil bulk density, pH and porosity had the highest impact on Ks, while soil salinity affected the Ks slightly. Therefore, use of MLP with two hidden layers efficiently can predict Ks in the study area and could be introduced as a promising method for Ks estimation. Considering the slightly low sampling data, this research can be considered as a starting step for future comprehensive studies with high intensive sampling sites that would enhance the reliability of these results.



 [M1]باید حذف شود چون سه عدد ذکر شده به ترتیب مربوط به   R2,RMSE,CCC  می باشد نه Ks
 
در چکیده فارسی هم حذف شود cm/h

Keywords

References

  1. نوروزیان ز. 1393. برآورد هدایت هیدرولیکی اشباع خاک با استفاده از روش­های رگرسیونی و شبکه عصبی مصنوعی. پایان نامه کارشناسی ارشد دانشگاه علوم کشاورزی و منابع طبیعی ساری، دانشکده علوم زراعی، گروه علوم خاک.
  2. Agyare, W.A., S.J. Park., and P.L.G. Vlek. 2007. Artificial neural network estimation of saturated hydraulic conductivity. Vadose Zone J. 6:423-431.
  3. Aimrun, W., and S.M.Amin. 2009. Pedo-transfer functions for saturated hydraulic conductivity of lowland paddy soils. Paddy Water Environ. 7:217-225.
  4. Blake, G.R., and K.H. Hartge. 1986. Bulk density. In: Klute, A. (Ed.). Methods of Soil Analysis. Part 1, second ed. Agron. Monogr. 9. ASA and SSSA, Madison, WI.
  5. Bouma, J. 1989. Using soil survey data for quantitative land evaluation. Adv Soil Sci. 9:177-213.
  6. Botulaa, Y.D., W.M. Cornelisa., G. Baertb., and E. Van Ranste. 2012. Evaluation of pedotransfer functions for predicting water retention of soils in Lower Congo. Agric Water Manag. 111:1-10.
  7. Braud I, A., C.Dantas-Antonino.,And M. Vauclin. 1995. A stochastic approach to studying the influence of the spatial variability of soil hydraulic properties on surface fluxes. J Hydrol. 165: 283–310.
  8. Donatelli, M., and M. Acutis. 2001. Soil par 2.00 beta-help. Research Institute for industrial Crops. Via corticella 133, 40128 Bbologna. Italy.
  9. Elrick, D.E., and W.D. Reynolds. 1992. Infiltration from constant-head well permeameters and infiltrometers. In: Topp, G.C., Reynolds, W.D., Green, R.E. (Eds.), Advances in Measurements of Soil Physical Properties: Bringing Theory into Practice. SSSA Spec. Publ. 30. SSSA, Madison, WI.
  10. Frate, F.D., P. Ferrazoli.,and G. Schiavon. 2003. Retrieving soil moisture and agricultural variables by microwave radiometry using neural network. Remote Sens. Environ. 84:174-183.
  11. Haghverdi, A., H.S. Ozturk., S. Ghodsi., and T. Tuncay. 2012. Estimating saturated hydraulic conductivity using different wellknownpedotransfer function. Instructions for Short Papers forThe 8th International Symposium Agro Environ, 2012 Conference, Wageningen, Ankara.
  12. Haverkamp, R., F.J. Leij., C. Fuentes., A. Sciortino., and P.J. Ross. 2005. Soil water retention: I. Introduction of a shape index. Soil Sci. Soc. Am. J. 69: 1881–1890.
  13. Hill, M. 1998. Methods and guidelines for effective model calibration. U.S. Geological survey Water- Resources Investigations Report,Denver, Colorado.
  14. Ghanbarian-Alavijeh, B., A.M. Liaghat., and S. Sohrabi. 2010. Estimating saturated hydraulic conductivity from soil physical properties using neural networks model. World Acad. Science. Engin.Technol. 62:131-136.
  15. GhorbaniDashtaki, S.M., M. Homaee., and H. Khodaverdiloo. 2010. Derivation and validation of pedotransferfunctions for estimating soil water retention curve using a variety of soil data. Soil Use and Mange. 26:68-74.
  16. Lin, L.I.K. 1989. A concordance correlation coefficient to evaluate reproducibility. Biometrics, 45:255-268.
  17. Lu, M., Abourizk, S.M. and Hermann, U.H.,Sensitivity Analysis of neural networks in spool fabrication productivity studies. J. Comput. Civ. Eng. 15:4(299), 299-308.
  18. Kianpoor-kalkhajeh, U., R. Rezaie-Arshad., H. Amerikhah., and M. Sami. 2012. multiplelinear regression, artificial neural network and ANFIS modelimg the saturated hydraulic conductivity. InterJAgric Res Review. 2(3):255-265.
  19. Kim, M., and J.E. Gilley. 2008. Artificial Neural Network estimation of soil erosion and nutrient concentrations in runoff from land application areas. Comput Electron Agric. 64:268–275.
  20. Klute, A. 1986. Methods of Soil Analysis. Part 1, physical and mineralogical methods, American Society of Agronomy, Agronomy Monographs 9(1), Madison, Wisconsin, USA.
  21. Klute, A., and C. Dirksen. 1986. Hydraulic conductivity and diffusivity: Laboratory methods. In: Methods of Soil Analysis Part 1: Physical and Mineralogical Methods, A. Klute, Ed. Soil Science Society of America, Madison, WI.
  22. Marcel, G.S., J.L. Feike., T. Martinus., and H. van Genuchten. 1998. Neural Network Analysis for Hierarchical Prediction of Soil Hydraulic Properties. Soil SciSoc Am J. 62: 847-855.
  23. Mallants, D., D. Jaques.,P.H. Tseng., H. Van Genuchten., And J. Feyen. 1997. Comparison of three hydraulic property measurement methods. J hydrol. 199: 295-318.
  24. Morgan, R.P.C. 2005. Soil erosion & Conservation. Third edition. Blackwell Publishing. United Kingdom.
  25. Nelson, D.W., and L.P. Sommers. 1986. Total carbon, organic carbon and organic matter. In: page. A.L. Ed. Methods of Analysis. Soil SciSoc Am J. 2:539-579.
  26. Osborne, J. 2010. Improving your data transformations: Applying the Box-Cox transformation. North Carolina State University, A peer-reviewed electronic journal. Prac Assess, Res Eval. 15(12):2.
  27. Pachepsky,Ya., A.D. Timlin., And G. Varallyay. 1996. Artificial neural networks to estimate soil water retention from easily measurable data. Soil SciSoc Am J. 60:727-733.
  28. Page, A., R. Miller., and D. Keeney. 1982. Methods of Soil Analysis.2th ed. Part2: Chemical and biological properties. Soil SciSoc Am J. Inc. Publisher.
  29. Rasoulzade, A. 2011. Estimating hydraulic conductivity using pedotransfer functions. Hydraulic Conductivity – Issues. Determination and Applications,Prof. LakshmananElango (Ed.), ISBN: 978-953-307-288-3, InTech, Available from: http://www.intechopen.com/books/hydraulic conductivity-issues-determinationand-applications/estimating-hydraulic-conductivity-using-pedotransfer-functions.
  30. Rogiers, B., D. Mallants., O. Batelaan., M. Gedeon., M. Huysmans., and A. Dassargues. 2012. Estimation of hydraulic conductivity and its uncertainty from grain-size data using GLUE and artificial neural networks. Inter Assoc Math Geosci. 44:739-763.
  31. Schaap, M.G., and F.J. Leij. 1998. Using neural networks to predict soil water retention and hydraulic conductivity. Soil TillRes.47: 37-42.
  32. Schaap, M.G., F.J. Leij.,And H. Van Genuchten. 2001. Rosetta: a computer program for estimating soil hydraulic parameters with hierarchical pedotransfer functions. J hydrol. 251: 163-176.
  33. Shirazi, M.A., and L. Boersma. 1984. A unifying quantitative analysis of soil texture. Soil SciSoc Am J. 48:142-147.
  34. Tang, L., G. Zeng., F. Nourbakhsh., L. Guoli.,And G.L. Shen. 2009. Artificial Neural Network Approach for Predicting Cation Exchange Capacity in Soil Based on Physico-Chemical Properties. Environ Eng Sci. 26(1): 137-146.
  35. Tekin, E., and S.O. Akbas. 2011. Artificial neural networks approach for estimating the groutability of granular soils with cement-based grouts. B EngGeol Environ. 70:153–161.
  36. Walkley, A., and I.A. Black. 1934. An examination of the degtjareff method fordetermining soil organic matter and a proposed modification of the chronic acid titration method. Soil SciSoc Am J. 37:29-39.
  37. Westeman, R.E.L. 1990. Soil testing and plant analysis. Soil Society Science America Jurnal. Madison, Wisconsin. USA.
  38. Wosten, J.H.M., P.A. Finke.,And M.J.W. Jansen. 1995. Comparison of class and continuous pedotransfer functions to generate soil hydraulic characteristics. Geoderma. 66:227–237.
  39. Wosten, J.H.M., Y.A. Pachepsky., and W.J. Rawls. 2001. Pedotransfer functions: bridging the gap between available basic soil data and missing soil hydraulic characteristics. JHydrol. 251: 123-150.
  40. Xiangsheng, Y., L. Guosheng., and Y. Yanyu. 2013. Comparison of three methods to develop pedotransfer functions for the saturated water content and field water capacity in permafrost region. Cold RegSci Technol. 88:10-16.
  41. Yetilmezsoy, K., and S. Demirel. 2008.  Artificial neural network (ANN) approach for modeling of Pb(II) adsorption from aqueous solution by Antep pistachio (Pistacia Vera L.) shells. J Hazard Mater. 153: 1288–1300.
  42. Yilmaz, I., and O. Kaynar. 2011. Multiple regression, ANN (RBF, MLP) and ANFIS models for prediction of swell potential of clayey soils. Expert Syst Appl. 38: 5958–5966.
  43. Zorluer, I., Y. Icaga., S. Yurtcu., and H. Tosun. 2010. Application of a fuzzy rule-based method for the determination of clay dispersibility. Geoderma. 160: 189–196.
Iranian Journal of Soil Research
Volume 31, Issue 1
June 2017
Pages 75-87

Files

Share

How to cite

Statistics