Comparison of Artificial Neural Network and Multivariate Regression Methods in Prediction of Soil Cation Exchange Capacity
Investigation of soil properties like Cation Exchange
Capacity (CEC) plays important roles in study of environmental
reaserches as the spatial and temporal variability of this property
have been led to development of indirect methods in estimation of
this soil characteristic. Pedotransfer functions (PTFs) provide an
alternative by estimating soil parameters from more readily available
soil data. 70 soil samples were collected from different horizons of
15 soil profiles located in the Ziaran region, Qazvin province, Iran.
Then, multivariate regression and neural network model (feedforward
back propagation network) were employed to develop a
pedotransfer function for predicting soil parameter using easily
measurable characteristics of clay and organic carbon. The
performance of the multivariate regression and neural network model
was evaluated using a test data set. In order to evaluate the models,
root mean square error (RMSE) was used. The value of RMSE and
R2 derived by ANN model for CEC were 0.47 and 0.94 respectively,
while these parameters for multivariate regression model were 0.65
and 0.88 respectively. Results showed that artificial neural network
with seven neurons in hidden layer had better performance in
predicting soil cation exchange capacity than multivariate regression.
[1] M. Amini, K.C. Abbaspour, H. Khademi, N. Fathianpour, M. Afyuni and
R. Schulin, "Neural network models to predict cation exchange capacity
in arid regions of Iran", Eur. J. Soil Sci., Vol. 53, pp 748-757, 2005.
[2] L. Baker and D. Ellison, "Optimisation of pedotransfer functions using
an artificial neural network ensemble method", Geoderma, Vol.144, pp
212-224, 2008.
[3] M. Banimahd, S.S. Yasrobi and P.K. Woodward, "Artificial neural
network for stress-strain behavior of sandy soils: Knowledge based
verification", Comput. Geotech., Vol. 32, pp 377-386, 2005.
[4] M.A. Bell and J. Van keulen, "Soil pedotransfer functions for four
Mexican soils", Soil Sci Soc. Am. J., Vol. 59, pp 865-871, 1995.
[5] J. Bouma, "Using soil survey data for quantitative land evaluation",
Advances in Soil Science., Vol. 9, pp 177-213, 1989.
[6] A. Breeuwsma, J.H.M. Wosten, J.J. Vleeshouwer, A.M. Van slobbe and
J. Bouma, "Derivation of land qualities to assess environmental
problems from soil surveys", Soil Sci Soc. Am. J., Vol. 50, pp 186-190,
1986.
[7] O. Carpena, A. Lux and K. vahtras, "Determination of exchangeable
calcareous soils". Soil Sci., Vol. 33, pp 194-199, 1972.
[8] E.H. Drake and H.L. Motto, "An analysis of the effect of clay and
organic matter content on the cation exchange capacity of New Jersey
soils". Soil. Sci., Vol. 133, pp 281-288, 1982.
[9] M.J. Fernando, R.G. Burau and K. Arulanandam, "A new approach to
determination of cation exchange capacity", Soil Sci.Amer. J., Vol. 41,
pp 818-820, 1977.
[10] S.A. Heusher, C.C. Brandt and P.M. Jardin, "Using soil physical and
chemical properties to estimate bulk density", Soil Sci. Soc. Am. J., Vol.
69, pp 51-56, 2005.
[11] A. Jain and A. Kumar, "An evaluation of artificial neural network
technique for the determination of infiltration model parameters", Appl.
Soft Comput., Vol. 6, pp 272-282, 2006.
[12] F. Karaca and B. Ozkaya, "NN-LEAP: A neural network-based model
for controlling leachate flow-rate in a municipal solid waste landfill
site", Environ. Modell. Software., Vol. 21, pp 1190-1197, 2006.
[13] R. Kaur, S. Kumar and H.P. Gurung, "A pedotransfer function soil data
and its comparison with existing PTFs", Aust. J. Soil Res., Vol. 40, pp
847- 857, 2002.
[14] A. Keller, B. Von Steiger, S.T. Vander Zee and R. Schulin, "A
stochastic empirical model for regional heavy metal balances in
agroecosystems". Journal of Environmental Quality., Vol. 30, pp 1976-
1989, 2001.
[15] E.J.W. Koekkoek and H. Booltink, "Neural network models to predict
soil water retention", Eur. J. Soil Sci., Vol. 50, pp 489-495, 1999.
[16] H.R. Lake, A. Akbarzadeh and R. Taghizadeh Mehrjardi, "Development
of pedotransfer functions (PTFs) to predict soil physico-chemical and
hydrological characteristics in southern coastal zones of the Caspian
Sea", Journal of Ecology and the Natural Environment., Vol. 1, No.7, pp
160-172, 2009.
[17] L.A. Manrique, C.A. Jones and P.T. Dyke, "Predicting cation exchange
capacity from soil physical and chemical properties", Soil Science
Society of America Journal., Vol. 50, pp 787-794, 1991.
[18] C. Manyame, C.L. Morgan, J.L. Heilman, D. Fatondji, B. Gerard and
W.A. Payne, "Modeling hydraulic properties of sandy soils of Niger
using pedotransfer functions", Geoderma., Vol. 141, pp 407-415, 2007.
[19] A.B. McBratney, B. Minasny, S.R. Cattle and R.W. Vervoort, "From
pedotransfer function tosoil inference system", Geoderma., Vol. 109, pp
41-73, 2002.
[20] H. Merdun, O. C─▒nar, R. Meral and M. Apan, "Comparison of artificial
neural network and regression pedotransfer functions for prediction of
soil water retention and saturated hydraulic conductivity", Soil Till.Res.,
Vol. 90, pp 108-116, 2006.
[21] A. Mermoud and D. Xu, "Comparative analysis of three methods to
generate soil hydraulic functions", Soil Till. Res., Vol. 87, pp 89-100,
2006.
[22] B. Minasny and A.B. McBratney, "The neuro-m methods for fitting
neural network parametric pedotransfer functions", Soil Sci. Soc. Am. J.,
Vol. 66, pp 352-361, 2002.
[23] B. Minasny, A.B. McBratney and K.L. Bristow, "Comparison of
different approaches to the development of pedotransfer functions for
water retention curves", Geoderma., Vol. 93, pp 225- 253, 1999.
[24] M. Najafi and J. Givi, "Evaluation of prediction of bulk density by
artificial neural network and PTFs", 10th Iranian Soil Science Congress,
Karaj., pp 680-681, 2006.
[25] D.W. Nelson and L.E. Sommers, "Total carbon, organic carbon, and
organic matter". In: A.L. Page, R.H. Miller and D.R. Keeney (Eds.),
Methods of Soil Analysis. Part II, 2nd ed. American Society of
Agronomy, Madison, WI, USA, pp: 539-580, 1982.
[26] F. Noorbakhsh, A. Jalalian and H. Shariatmadari, "Prediction of cation
exchange capacity with using some soil properties", Iranian Journal of
Science and Technology of Agriculture and Natural Resources., Vol. 3,
pp 107-117, 2005.
[27] Y.A. Pachepsky, D. Timlin and G. Varallyay, "Artificial neural networks
to estimate soil water retention from easily measurable data", Soil Sci.
Soc. Am. J., Vol. 60, pp 727-733, 1996.
[28] K.L. Sahrawat, "An analysis of the contribution of organic matter and
clay to cation exchange capacity of some Philippine soils", Commun.
Soil Sci. Plant Anal., Vol.14, pp 803-809, 1983.
[29] F. Sarmadian, R. Taghizadeh Mehrjardi and A. Akbarzadeh, "Modeling
of some soil properties using artificial neural network and multivariate
regression in Gorgan province, north of Iran", Australian J. of Basic and
Applied Sci., Vol. 3, No. 1, pp 323-329, 2009.
[30] M.G. Schaap and F.J. Leij, "Using neural networks to predict soil water
retention and soil hydraulic conductivity", Soil Till. Res., Vol. 47, pp
37-42, 1998.
[31] M.G. Schaap, F.J. Leij and M.Th. Van Genuchten, "Neural network
analysis for hierarchical prediction of soil hydraulic properties", Soil
Sci. Soc. Am. J., Vol. 62, pp 847-855, 1998.
[32] C.A. Seybold, R.B. Grossman and T.G. Reinsch, "Predicting Cation
Exchange Capacity for soil survey using linear models", Soil Sci. Soc.
Am. J., Vol. 69, pp 856-863, 2005.
[33] D.L. Sparks, A.L. Page, P.A. Helmke, R.H. Leoppert, P.N. Soltanpour,
M.A. Tabatabai, G.T. Johnston and M.E. Summer, "Methods of soil
analysis", Soil Sci. Soc. of Am. Madison, Wisconsin, 1996.
[34] S. Tamari, J.H.M. Wosten and J.C. Ruiz-Suarez, "Testing an artificial
neural network for predicting soil hydraulic conductivity", Soil Sci. Soc.
Am. J., Vol. 60, pp 1732-1741, 1996.
[35] USDA, "Soil Survey Staff, Keys to Soil Taxonomy", 11th edition, 2010.
[36] B.D. Vos, M.V. Meirvenne, P. Quataert, J. Deckers and B. Muys,
"Predictive quality of pedotransfer functions for estimating bulk density
of forest soils", Soil Sci. Soc. Am. J., Vol. 69, pp 500-510, 2005.
[37] B. Wagner, V.R. Tarnawski, V. Hennings, U. Muller, G. Wessolek and
R. Plagge, "Evaluation of pedo-transfer functions for unsaturated soil
hydraulic conductivity using an independent data set", Geoderma.,
Vol.102, pp 275-279, 2001.
[38] L.P. Wilding and E.M. Rutledge, "Cation exchange capacity as a
function of organic matter, total clay, and various clay fractions in a soil
toposequence", Soil Sci. Soc. Am. Proc., Vol. 30, pp 782-785, 1966.
[39] J.H.M. Wösten, A. Lilly, A. Nemes and C. Le Bas, "Development and
use of a database of hydraulic properties of European soils", Geoderma.,
Vol. 90, pp 169-185, 1999.
[1] M. Amini, K.C. Abbaspour, H. Khademi, N. Fathianpour, M. Afyuni and
R. Schulin, "Neural network models to predict cation exchange capacity
in arid regions of Iran", Eur. J. Soil Sci., Vol. 53, pp 748-757, 2005.
[2] L. Baker and D. Ellison, "Optimisation of pedotransfer functions using
an artificial neural network ensemble method", Geoderma, Vol.144, pp
212-224, 2008.
[3] M. Banimahd, S.S. Yasrobi and P.K. Woodward, "Artificial neural
network for stress-strain behavior of sandy soils: Knowledge based
verification", Comput. Geotech., Vol. 32, pp 377-386, 2005.
[4] M.A. Bell and J. Van keulen, "Soil pedotransfer functions for four
Mexican soils", Soil Sci Soc. Am. J., Vol. 59, pp 865-871, 1995.
[5] J. Bouma, "Using soil survey data for quantitative land evaluation",
Advances in Soil Science., Vol. 9, pp 177-213, 1989.
[6] A. Breeuwsma, J.H.M. Wosten, J.J. Vleeshouwer, A.M. Van slobbe and
J. Bouma, "Derivation of land qualities to assess environmental
problems from soil surveys", Soil Sci Soc. Am. J., Vol. 50, pp 186-190,
1986.
[7] O. Carpena, A. Lux and K. vahtras, "Determination of exchangeable
calcareous soils". Soil Sci., Vol. 33, pp 194-199, 1972.
[8] E.H. Drake and H.L. Motto, "An analysis of the effect of clay and
organic matter content on the cation exchange capacity of New Jersey
soils". Soil. Sci., Vol. 133, pp 281-288, 1982.
[9] M.J. Fernando, R.G. Burau and K. Arulanandam, "A new approach to
determination of cation exchange capacity", Soil Sci.Amer. J., Vol. 41,
pp 818-820, 1977.
[10] S.A. Heusher, C.C. Brandt and P.M. Jardin, "Using soil physical and
chemical properties to estimate bulk density", Soil Sci. Soc. Am. J., Vol.
69, pp 51-56, 2005.
[11] A. Jain and A. Kumar, "An evaluation of artificial neural network
technique for the determination of infiltration model parameters", Appl.
Soft Comput., Vol. 6, pp 272-282, 2006.
[12] F. Karaca and B. Ozkaya, "NN-LEAP: A neural network-based model
for controlling leachate flow-rate in a municipal solid waste landfill
site", Environ. Modell. Software., Vol. 21, pp 1190-1197, 2006.
[13] R. Kaur, S. Kumar and H.P. Gurung, "A pedotransfer function soil data
and its comparison with existing PTFs", Aust. J. Soil Res., Vol. 40, pp
847- 857, 2002.
[14] A. Keller, B. Von Steiger, S.T. Vander Zee and R. Schulin, "A
stochastic empirical model for regional heavy metal balances in
agroecosystems". Journal of Environmental Quality., Vol. 30, pp 1976-
1989, 2001.
[15] E.J.W. Koekkoek and H. Booltink, "Neural network models to predict
soil water retention", Eur. J. Soil Sci., Vol. 50, pp 489-495, 1999.
[16] H.R. Lake, A. Akbarzadeh and R. Taghizadeh Mehrjardi, "Development
of pedotransfer functions (PTFs) to predict soil physico-chemical and
hydrological characteristics in southern coastal zones of the Caspian
Sea", Journal of Ecology and the Natural Environment., Vol. 1, No.7, pp
160-172, 2009.
[17] L.A. Manrique, C.A. Jones and P.T. Dyke, "Predicting cation exchange
capacity from soil physical and chemical properties", Soil Science
Society of America Journal., Vol. 50, pp 787-794, 1991.
[18] C. Manyame, C.L. Morgan, J.L. Heilman, D. Fatondji, B. Gerard and
W.A. Payne, "Modeling hydraulic properties of sandy soils of Niger
using pedotransfer functions", Geoderma., Vol. 141, pp 407-415, 2007.
[19] A.B. McBratney, B. Minasny, S.R. Cattle and R.W. Vervoort, "From
pedotransfer function tosoil inference system", Geoderma., Vol. 109, pp
41-73, 2002.
[20] H. Merdun, O. C─▒nar, R. Meral and M. Apan, "Comparison of artificial
neural network and regression pedotransfer functions for prediction of
soil water retention and saturated hydraulic conductivity", Soil Till.Res.,
Vol. 90, pp 108-116, 2006.
[21] A. Mermoud and D. Xu, "Comparative analysis of three methods to
generate soil hydraulic functions", Soil Till. Res., Vol. 87, pp 89-100,
2006.
[22] B. Minasny and A.B. McBratney, "The neuro-m methods for fitting
neural network parametric pedotransfer functions", Soil Sci. Soc. Am. J.,
Vol. 66, pp 352-361, 2002.
[23] B. Minasny, A.B. McBratney and K.L. Bristow, "Comparison of
different approaches to the development of pedotransfer functions for
water retention curves", Geoderma., Vol. 93, pp 225- 253, 1999.
[24] M. Najafi and J. Givi, "Evaluation of prediction of bulk density by
artificial neural network and PTFs", 10th Iranian Soil Science Congress,
Karaj., pp 680-681, 2006.
[25] D.W. Nelson and L.E. Sommers, "Total carbon, organic carbon, and
organic matter". In: A.L. Page, R.H. Miller and D.R. Keeney (Eds.),
Methods of Soil Analysis. Part II, 2nd ed. American Society of
Agronomy, Madison, WI, USA, pp: 539-580, 1982.
[26] F. Noorbakhsh, A. Jalalian and H. Shariatmadari, "Prediction of cation
exchange capacity with using some soil properties", Iranian Journal of
Science and Technology of Agriculture and Natural Resources., Vol. 3,
pp 107-117, 2005.
[27] Y.A. Pachepsky, D. Timlin and G. Varallyay, "Artificial neural networks
to estimate soil water retention from easily measurable data", Soil Sci.
Soc. Am. J., Vol. 60, pp 727-733, 1996.
[28] K.L. Sahrawat, "An analysis of the contribution of organic matter and
clay to cation exchange capacity of some Philippine soils", Commun.
Soil Sci. Plant Anal., Vol.14, pp 803-809, 1983.
[29] F. Sarmadian, R. Taghizadeh Mehrjardi and A. Akbarzadeh, "Modeling
of some soil properties using artificial neural network and multivariate
regression in Gorgan province, north of Iran", Australian J. of Basic and
Applied Sci., Vol. 3, No. 1, pp 323-329, 2009.
[30] M.G. Schaap and F.J. Leij, "Using neural networks to predict soil water
retention and soil hydraulic conductivity", Soil Till. Res., Vol. 47, pp
37-42, 1998.
[31] M.G. Schaap, F.J. Leij and M.Th. Van Genuchten, "Neural network
analysis for hierarchical prediction of soil hydraulic properties", Soil
Sci. Soc. Am. J., Vol. 62, pp 847-855, 1998.
[32] C.A. Seybold, R.B. Grossman and T.G. Reinsch, "Predicting Cation
Exchange Capacity for soil survey using linear models", Soil Sci. Soc.
Am. J., Vol. 69, pp 856-863, 2005.
[33] D.L. Sparks, A.L. Page, P.A. Helmke, R.H. Leoppert, P.N. Soltanpour,
M.A. Tabatabai, G.T. Johnston and M.E. Summer, "Methods of soil
analysis", Soil Sci. Soc. of Am. Madison, Wisconsin, 1996.
[34] S. Tamari, J.H.M. Wosten and J.C. Ruiz-Suarez, "Testing an artificial
neural network for predicting soil hydraulic conductivity", Soil Sci. Soc.
Am. J., Vol. 60, pp 1732-1741, 1996.
[35] USDA, "Soil Survey Staff, Keys to Soil Taxonomy", 11th edition, 2010.
[36] B.D. Vos, M.V. Meirvenne, P. Quataert, J. Deckers and B. Muys,
"Predictive quality of pedotransfer functions for estimating bulk density
of forest soils", Soil Sci. Soc. Am. J., Vol. 69, pp 500-510, 2005.
[37] B. Wagner, V.R. Tarnawski, V. Hennings, U. Muller, G. Wessolek and
R. Plagge, "Evaluation of pedo-transfer functions for unsaturated soil
hydraulic conductivity using an independent data set", Geoderma.,
Vol.102, pp 275-279, 2001.
[38] L.P. Wilding and E.M. Rutledge, "Cation exchange capacity as a
function of organic matter, total clay, and various clay fractions in a soil
toposequence", Soil Sci. Soc. Am. Proc., Vol. 30, pp 782-785, 1966.
[39] J.H.M. Wösten, A. Lilly, A. Nemes and C. Le Bas, "Development and
use of a database of hydraulic properties of European soils", Geoderma.,
Vol. 90, pp 169-185, 1999.
@article{"International Journal of Earth, Energy and Environmental Sciences:61874", author = "Ali Keshavarzi and Fereydoon Sarmadian", title = "Comparison of Artificial Neural Network and Multivariate Regression Methods in Prediction of Soil Cation Exchange Capacity", abstract = "Investigation of soil properties like Cation Exchange
Capacity (CEC) plays important roles in study of environmental
reaserches as the spatial and temporal variability of this property
have been led to development of indirect methods in estimation of
this soil characteristic. Pedotransfer functions (PTFs) provide an
alternative by estimating soil parameters from more readily available
soil data. 70 soil samples were collected from different horizons of
15 soil profiles located in the Ziaran region, Qazvin province, Iran.
Then, multivariate regression and neural network model (feedforward
back propagation network) were employed to develop a
pedotransfer function for predicting soil parameter using easily
measurable characteristics of clay and organic carbon. The
performance of the multivariate regression and neural network model
was evaluated using a test data set. In order to evaluate the models,
root mean square error (RMSE) was used. The value of RMSE and
R2 derived by ANN model for CEC were 0.47 and 0.94 respectively,
while these parameters for multivariate regression model were 0.65
and 0.88 respectively. Results showed that artificial neural network
with seven neurons in hidden layer had better performance in
predicting soil cation exchange capacity than multivariate regression.", keywords = "Easily measurable characteristics, Feed-forwardback propagation, Pedotransfer functions, CEC.", volume = "4", number = "12", pages = "684-6", }
