Sensitivity Analysis for Determining Priority of Factors Controlling SOC Content in Semiarid Condition of West of Iran

Soil organic carbon (SOC) plays a key role in soil fertility, hydrology, contaminants control and acts as a sink or source of terrestrial carbon content that can affect the concentration of atmospheric CO2. SOC supports the sustainability and quality of ecosystems, especially in semi-arid region. This study was conducted to determine relative importance of 13 different exploratory climatic, soil and geometric factors on the SOC contents in one of the semiarid watershed zones in Iran. Two methods canonical discriminate analysis (CDA) and feed-forward back propagation neural networks were used to predict SOC. Stepwise regression and sensitivity analysis were performed to identify relative importance of exploratory variables. Results from sensitivity analysis showed that 7-2-1 neural networks and 5 inputs in CDA models output have highest predictive ability that explains %70 and %65 of SOC variability. Since neural network models outperformed CDA model, it should be preferred for estimating SOC.

Authors:

• Y. Parvizi
• M. Gorji
• M.H. Mahdian
• M. Omid

Keywords:

• Soil organic carbon
• modeling
• neural networks
• CDA.

References:

[1] M. Amini, K.C.Abbaspour, H.vKhademi, N.vFathianpour, M. Afyuni,,
R. Schulin, Neural network models to predict cation exchange capacity
in arid regions of Iran. Europ. J. of Soil Sci. vol. 56, pp. 551-559,
2005.
[2] J.A. Anderson.. Introduction to neural networks. Prentice-Hall of India,
New Delhi. 2001
[3] APERI, Mahidasht-Sanjabi plain study :phase 1: climate study. TAM
consulting engineers, Ministry of Agriculture, Iran. ) vol. 2, 2004.
[4] T.W. Beers, Dress, P.E., Wensel, Aspect transformation in site
productivity research. J. of Forertry, vol. 64, pp. 691-692. 1966.
[5] C.E.P. Cerri, M. Easter, K. Paustian, K. Killian, K. Coleman, M.
Bernoux, P. Falloon, D.S. Powlson, N.H. Batjes, E. Milne, C.C. Cerri,
Predicted soil organic carbon stocks and changes in the Brazilian
Amazon between 2000 and 2030. Agric., Ecosys. and Environ. Vol. 122,
pp. 58-72, 2007.
[6] IPCC, Land-use, land-use change, and forestry. In: Watson, R.T.,
Noble, I.R., Bolin, B., Ravindranath, N.H., Verardo, D.J., Dokken, D.J.
(Eds.), A Special Report of the Intergovernmental Panel on Climate
Change. Cambridge University Press, Cambridge. 2000.
[7] M. Kim, T. Kim, A neural classifier with fraud density map for effective
credit card fraud detection. IDEAL, pp. 378-383. 2002.
[8] Lal, R.,. Soil carbon dynamics in cropland and rangeland. Environ.
Pollut. Vol. 116, pp. 353-362, 2002.
[9] E.R. Levine, D.S. Kimes, Predicting soil carbon in Mollisols using
neural networks. pp. 473-484. In R. Lal et al. (ed.) Soil process and the
carbon cycle, CRC Press, Boca Raton, FL. 1997.
[10] E.R. Levine, D.S. Kimes, V.G. Sigilitto, Modeling soil structure using
artificial neural network. Ecol. Modell. Vol. 92, pp. 101-108, 1996.
[11] D. Liu, Z. Wang, B. Zhang, K. Song, X. Li, J. Li, F. Li, H. Duan, Spatial
distribution of soil organic carbon and analysis of related factors in
croplands of the black soil region, Northeast China. Agric., Ecosys. and
Environ. Vol. 113, pp. 73-81, 2006.
[12] A.B. McBratney, B. Minasny, S.R. Cattle, R.W. Vervoot, From
pedotransfer function to soil inference system. Geoderma vol. 109, pp.
41-73, 2002.
[13] J. McCullagh, A modular neural network architecture for rainfall
estimation, Artificial Intelligence and Applications. Innsbruck, Austria,
pp. 767-772, 2005.
[14] K. McVay, C. Rice, Soil organic carbon and the global carbon cycle.
Technical Report MF-2548, Kansas State University, Kansas. 2002.
[15] B. Minasny, A.B. McBratney, The neuron-m method for fitting neuralnetwork
parametric pedotransfer functions. Soil Sci. Soc. Am. J. vol. 66,
pp. 352-361, 2002.
[16] A. Nemes, M.G. Shaap, J.H. Wo, M. Sten, Functional evaluation of
pedotransfer functions derived from different scales of data collection.
Soil Sci. Soc. Am. J. vol. 67, pp. 1093-1193, 2003.
[17] M. Omid, A. Baharlooei, H. Ahmadi, Modeling Drying Kinetics of
Pistachio Nuts with Multilayer Feed-Forward Neural Network. Drying
Tech. vol. 27, no.10, pp. 1-9, 2009.
[18] S.J. Park, P.L.G. Vlek, Environmental correlation of three dimensional
soil spatial variability: A comparison of three adaptive. Geoderma , vol.
109, pp. 117-140, 2002.
[19] F. Sarmadian, R. Taghizadeh Mehrjardi, A. Akbarzadeh, Modeling of
some soil properties using artificial neural network and multivariate
regression in Gorgan province, north of Iran. Austral. J. of Basic and
Applied Sci. vol. 3, no. 1, 323-329, 2009.
[20] S. Somaratne, G. Seneviratne, U. Coomaraswamy, Prediction of Soil
Organic Carbon across Different Land-use Patterns:A Neural Network
Approach. Soil Sci. Soc. Am. J. vol. 69, pp. 1580-1589, 2005.
[21] G.P. Sparling, D. Wheeler, E.T. Wesely, L.A. Schipper, What is soil
organic matter worth?. J. Environ. Qual. Vol. 35, pp. 548-557, 2006.
[22] M.J. Spencer, T. Whitfort, J. McCullagh, Dynamic ensemble approach
for estimating organic carbon using computational intelligence.
Proceedings of the 2nd IASTED international conference on Advances in
computer science and technology. Puerto Vallarta, Mexico, 2006.
[23] Z. Tan, R. Lal, Carbon Sequestration Potential Estimates with Changes
in Land Use and Tillage Practice in Ohio, USA. Agric., Ecosys. and
Environ., vol. 126, pp. 113-121, 2005.
[24] Z. Tan, R. Lal, N. Smeck, F. Calhoun, Relationships between surface soil
organic carbon pool and site variables, Geoderma, vol. 121, pp. 187-
195, 2004.
[25] P.J. Werbos, Backpropagation, basic and new developments. pp. 134-
139. In Arbib, M.A., (ed.) The handbook of brain behavior and neural
networks. The MIT Press, Cambridge, MA. 1995.
[26] B. Wolf, G.H. Snyder, Sustainable Soils: the place of organic matter in
sustaining soil and their productivity. Food Products Press. New York,
2003.
[27] G. Zhang, Neural Networks in Business Forecasting, IRM Press,
Hershey, PA., 2004.