Selection of a suitable model for the prediction of soil water content in north of Iran

  • Leila Esmaeelnejad University of Tehran, College of Agriculture and Natural Resources, Faculty of Agricultural Engineering and Technology, Soil Science Department. Karaj
  • Hassan Ramezanpour University of Guilan, Agriculture Faculty, Soil Science Department. Rasht
  • Javad Seyedmohammadi University of Tabriz, Agriculture Faculty, Soil Science Department, Tabriz
  • Mahmood Shabanpour University of Guilan, Agriculture Faculty, Soil Science Department. Rasht
Keywords: multiple linear regression, neural networks, pedotransfer function, Rosetta, soil moisture curve

Abstract

Multiple Linear Regression (MLR), Artificial Neural Network (ANN) and Rosetta model were employed to develop pedotransfers functions (PTFs) for soil moisture prediction using available soil properties for northern soils of Iran. The Rosetta model is based on ANN works in a hierarchical approach to predict water retention curves. For this purpose, 240 soil samples were selected from the south of Guilan province, Gilevan region, northern Iran. The data set was divided into two subsets for calibration and testing of the models. The general performance of PTFs was evaluated using coefficient of determination (R2), root mean square error (RMSE) and mean biased error between the observed and predicted values. Results showed that ANN with two hidden layers, Tan-sigmoid and linear functions for hidden and output layers respectively, performed better than the others in predicting soil moisture. In the other hand, ANN can model non-linear functions and showed to perform better than MLR. After ANN, MLR had better accuracy than Rosetta. The developed PTFs resulted in more accurate estimation at matric potentials of 100, 300, 500, 1000, 1500 kPa. Whereas, Rosetta model resulted in slightly better estimation than derived PTFs at matric potentials of 33 kPa. This research can provide the scientific basis for the study of soil hydraulic properties and be helpful for the estimation of soil water retention in other places with similar conditions, too.

Downloads

Download data is not yet available.

References

References

Abbasi Y, Ghanbarian-Alavijeh B, Liaghat AM, Shorafa M, 2011. Evaluation of pedotransfer functions for estimating soil water retention curve of saline and saline-alkali soils of Iran. Pedosphere 21(2): 230-237. http://dx.doi.org/10.1016/S1002-0160(11)60122-7

Aina PO, Periaswamy SP, 1985. Estimating available water-holding capacity of western Nigerian soils from soil texture and bulk density, using core and sieved samples. Soil Sci 140(1): 55-58. http://dx.doi.org/10.1097/00010694-198507000-00007

Amini M, Abbaspour KC, Khademi H, Fathianpour N, Afyuni M, Schulin R, 2005. Neural network models to predict cation exchange capacity in arid regions of Iran. Eur J Soil Sci 56: 551-559. http://dx.doi.org/10.1111/j.1365-2389.2005.0698.x

Baker L, Ellison D, 2008. The wisdom of crowds. Ensembles and modules in environmental modelling. Geoderma 147: 1-7. http://dx.doi.org/10.1016/j.geoderma.2008.07.003

Bell MA, vanKeulen H, 1995. Soil pedotransfer functions for four Mexican soils. Soil Sci Soc Am J 59: 865-871. http://dx.doi.org/10.2136/sssaj1995.03615995005900030034x

Bouma J, 1989. Using soil survey data for quantitative land evaluation. Adv Soil Sci 9: 177-213. http://dx.doi.org/10.1007/978-1-4612-3532-3_4

Brooks RH, Corey AT, 1964. Hydraulic properties of porous media. Hydrology Paper No. 3. Colorado Sta. Univ., Fort Collins, CO, USA.

Burt R(ed), 2004. Soil survey laboratory methods manual. Soil survey investigations report No. 42, V. 4.US Dept. Agr. Nat. Resour. Conserv. Serv. Nat. Soil Surv. Cent.

Chang YM, Chang LC, Chang FJ, 2004. Comparison of static feed forward and dynamic-feedback neural networks for rainfall runoff modeling. Hydrology 290: 297−311. http://dx.doi.org/10.1016/j.jhydrol.2003.12.033

Christopher T, Beckett S, Charles E, Augarde E, 2013. Prediction of soil water retention properties using pore-size distribution and porosity. Can Geo tech J 50(4): 435-450. http://dx.doi.org/10.1139/cgj-2012-0320

Cornelis WM, Ronsyn J, Meirvenne MV, 2001. Evaluation of pedotransfer functions for predicting the soil moisture retention curve. Soil Sci Soc Am J 65: 638-648. http://dx.doi.org/10.2136/sssaj2001.653638x

Demuth H, Beale M, 2004. Neural network toolbox for use with Matlab. User's guide v. 4. The Math Works Inc., Natick, MA, USA.

Dexter AR, Czy EA, Richard G, 2008. A user-friendly water retention function that takes account of the textural and structural pore spaces in soil. Geoderma 143: 243–253. http://dx.doi.org/10.1016/j.geoderma.2007.11.010

Ghanbarian-Alavijeh B, Millán H, 2010. Point pedotransfer functions for estimating soil water retention curve. Int Agro phys 24: 243-251.

Givi J, Prasher SO, Patel RM, 2004. Evaluation of pedotransfer functions in predicting the soil water contents at field capacity and wilting point. Agr Water Manage 70: 83-96. http://dx.doi.org/10.1016/j.agwat.2004.06.009

Gupta SC, Larson WE, 1979. Estimating soil water characteristic from particle size distribution, organic matter percent, and bulk density. Water Resour Res 15: 1633-1635. http://dx.doi.org/10.1029/WR015i006p01633

Hamblin A, 1991. Sustainable agricultural systems, what are the appropriate measures for soil structure? Aust J Soil Res 29: 709-715. http://dx.doi.org/10.1071/SR9910709

Heikki NK, 2008. Neural networks: basics using MATLAB. Neural Network Toolbox.

Huang MB, Fredlund DG, Fredlund MD, 2010.Comparison of measured and PTF predictions of SWCCs for Loess soils in China. Geo tech Geol Eng 28: 105-117. http://dx.doi.org/10.1007/s10706-009-9284-x

Huang W, Foo S, 2002. Neural network modelling of salinity variation in Apalachicola River. Water Res 36(1): 356−362. http://dx.doi.org/10.1016/S0043-1354(01)00195-6

Hutson JL, Cass A, 1987. A retentivity function for use in soil-water simulation models. Soil Sci 38:105-113. http://dx.doi.org/10.1111/j.1365-2389.1987.tb02128.x

Jain A, Kumar A, 2006. An evaluation of artificial neural network technique for the determination of infiltration model parameters. Appl Soft Comput 6(3): 272-282. http://dx.doi.org/10.1016/j.asoc.2004.12.007

Kern JS, 1995. Evaluation of soil water retention models based on basic soil physical properties. Soil Sci Soc Am J 59: 1134-1141. http://dx.doi.org/10.2136/sssaj1995.03615995005900040027x

Khodaverdiloo H, Homaee M, 2004. Pedotransfer functions of some calcareous soils. In: Int Conf (Whrle N, Sheurer M, Eds.), September 4-12, Freiburg, Germany. EuroSoil 10(27): 1-11.

Kumar K, Kumar Y, Venkatesh V, 2010. Estimation of liquid and plastic limit using artificial neural network models. Indian Geotechnical Conference, December 16–18, pp: 873-876.

McKeague JA (ed), 1978.Manual on soil sampling and methods of analysis. Can Soc Soil Sci (CSSC), Ottawa, Canada.

Medina H, Tarawally M, del Valle A, Ruiz ME, 2002. Estimating soil water retention curve in Rhodic Ferralsols from basic soil data. Geoderma 108: 277-285. http://dx.doi.org/10.1016/S0016-7061(02)00135-0

Merdun H, 2010. Alternative methods in the development of pedotransfer functions for soil hydraulic characteristics. Euras Soil Sci 43: 62-71. http://dx.doi.org/10.1134/S1064229310010084

Merdun H, Cinar O, Meral R, Apan M, 2006. Comparison of artificial neural network and regression pedotransfer functions for prediction of soil water retention and saturated hydraulic conductivity. Soil Till Res 90: 108-116. http://dx.doi.org/10.1016/j.still.2005.08.011

Mermoud A, Xu D, 2006. Comparative analysis of three methods to generate soil hydraulic functions. Soil Till Res 87: 89-100. http://dx.doi.org/10.1016/j.still.2005.02.034

Minasny B, Hopmans JW, Harter T, 2004. Neural networks prediction of soil hydraulic functions for alluvial soils using multistep outflow data. Soil Sci Soc Am J 68: 417-429. http://dx.doi.org/10.2136/sssaj2004.4170

Moghimi S, Mahdian, M Parvizi, Y Masihabadi M, 2014. Estimating effects of terrain attributes on local soil organic carbon content in a semi-arid pastureland. J Biodivers Environ Sci 5(2): 97-106.

Mualem Y, 1976. A new model for predicting the hydraulic conductivity of unsaturated porous media. Water Resour Res 12: 513-522. http://dx.doi.org/10.1029/WR012i003p00513

Mukhlisin M, Abd Rahman ASB, 2014. Prediction of Atterberg limits via ANN and ANFIS: a comparison. Proc Int Conf on Environmental Science and Geoscience (ESG '14), Venice, Italy. pp: 69-74. Available in http://www.europment.org/library/2014/venice/ENVIR.pdf.

Najafi M, Givi J, 2006. Evaluation of prediction of bulk density by artificial neural network and PTFs. 10th Iranian Soil Sci Conf, Karaj, 26-28 Aug., pp: 680-681. [In Persian].

Nemes A, Rawls WJ, 2006. Evaluation of different representations of the particle-size distribution to predict soil water retention. Geoderma 132:47-58. http://dx.doi.org/10.1016/j.geoderma.2005.04.018

Nemes A, Schaap MG, Wösten JHM, 2003. Functional evaluation of pedotransfer functions derived from different scales of data collection. Soil Sci Soc Am J 67: 1093-1102. http://dx.doi.org/10.2136/sssaj2003.1093

Rajkai K, Varallyay G, 1992. Estimating soil water retention from simpler properties by regression techniques. In: Methods for estimating the hydraulic properties of unsaturated soils (Van Genuchten MTh, Leij FJ, Lund LJ, eds.). Riverside, CA, USA, 11-13 October, pp: 417-426.

Rawls WJ, Pachepsky YA, Ritchie JC, 2003. Effect of soil organic carbon on soil water retention. Geoderma 116: 61-76. http://dx.doi.org/10.1016/S0016-7061(03)00094-6

Rezaei-Arshad R, Sayyad Gh, Mosaddeghi M, Gharabaghi B, 2013. Predicting Saturated Hydraulic Conductivity by Artificial Intelligence and Regression Models. Hindawi Publishing Corporation, ISRN Soil Science.http://dx.doi.org/10.1155/2013/308159

Rezaeianzadeh M, Tabari H, ArabiYazdi A, Isik S, Kalin L, 2014. Flood flow forecasting using ANN, ANFIS and regression models. Neural Comput Applic 25:25-37. http://dx.doi.org/10.1007/s00521-013-1443-6

Santra P, Das BS, 2008. Pedotransfer functions for soil hydraulic properties developed from a hilly watershed of Eastern India. Geoderma 146: 439-448. http://dx.doi.org/10.1016/j.geoderma.2008.06.019

Sarmadian F, Mehrjardi RT, 2008.Modeling of some soil properties using artificial neural network and multivariate regression in Gorgan province, north of Iran. Global J Environ Res 2: 30-35.

Schaap MG, Leij FJ, 2000.Improved prediction of unsaturated hydraulic conductivity with the Mualem-Van Genuchten model. Soil Sci Soc Am J 64: 843-851. http://dx.doi.org/10.2136/sssaj2000.643843x

Schaap MG, Leij FJ, Van Genuchten MTh, 2001. Rosetta, a computer program for estimating soil hydraulic parameters with hierarchical pedotransfer functions. Hydrology 251: 163-176. http://dx.doi.org/10.1016/S0022-1694(01)00466-8

Stumpp C, Engelhardt S, Hofmann M, 2009. Evaluation of pedotransfer functions for estimating soil hydraulic properties of prevalent soils in a catchment of the Bavarian Alps. Eur J Forest Res 128: 609-620. http://dx.doi.org/10.1007/s10342-008-0241-7

Tomasella J, Hodnett MG, 2004. Pedotransfer functions for tropical soils. In: Development of Pedotransfer Functions in Soil Hydrology (Pachepsky YA, Rawls WJ, Eds.). Elsevier, Amsterdam, pp: 415-429. http://dx.doi.org/10.1016/S0166-2481(04)30021-8

Tomasella J, Pachepsky Y, Crestana S, Rawls WJ, 2003. Comparison of two techniques to develop pedotransfer functions for water retention. Soil Sci Soc Am J 67: 1085-1092. http://dx.doi.org/10.2136/sssaj2003.1085

Van Genuchten MTh, 1980. A closed-form equation for predicting the hydraulic conductivity of unsaturated soils. Soil Sci Soc Am J 44: 892-898. http://dx.doi.org/10.2136/sssaj1980.03615995004400050002x

Venkatesan P, Anitha S, 2006. Application of a radial basis function neural network for diagnosis of diabetes mellitus. Curr Sci 91(9): 1195-1199.

Vereecken H, Weynants M, Javaux M, Pachepsky Y, Schaap MG, Van Genuchten MTh, 2010. Using pedotransfer functions to estimate the van Genuchten-Mualem soil hydraulic properties: a review. Vadose Zone 9: 1-26. http://dx.doi.org/10.2136/vzj2010.0045

Wagner B, Tarnawski VR, Hennings V, 2001. Evaluation of pedo-transfer functions for unsaturated soil hydraulic conductivity using an independent data set. Geoderma 102: 275-297. http://dx.doi.org/10.1016/S0016-7061(01)00037-4

Yi X, Li G, Yin Y, 2013. Comparison of three methods to develop pedotransfer functions for the saturated water content and field water capacity in permafrost region. Cold Region Sci Technol 88: 10-16. http://dx.doi.org/10.1016/j.coldregions.2012.12.005

Published
2015-02-13
How to Cite
EsmaeelnejadL., RamezanpourH., SeyedmohammadiJ., & ShabanpourM. (2015). Selection of a suitable model for the prediction of soil water content in north of Iran. Spanish Journal of Agricultural Research, 13(1), e1202. https://doi.org/10.5424/sjar/2015131-6111
Section
Water management