Intelligent Approaches to Analysing the Importance of Land Use Management in Soil Carbon Stock in a Semiarid Ecosystem, West of Iran

Authors
Y. Parvizi
M. Heshmati
M. Gheituri
Assistant Professor, Department of Soil Conservation and Watershed Management, Agriculture and Natural Resource Research Center of Kermanshah, AREEO, Kermanshah, Iran
Abstract
The effects of different climatic, soil, geometric, and management factors on soil organic carbon (SOC) degradation and sequestration potential was evaluated in the semi-arid zone of Mereg watershed, west of Iran. Two nonparametric methods, viz. Classification and Regression Tree (CART) and feed forward back propagation Artificial Neural Network (ANN) were compared with parametric Multivariate Linear Regression (MLR) in estimation of SOC content. Soil sampling was conducted using randomized systematic method in work unit map by overlying soil, aspect and slope maps. Results indicated that linear models had higher prediction errors. The CART with all variables (physical and management) and the ANN with 31-2-1 topology carried the highest predictive capability, explaining 81% and 76% of SOC variability, respectively. ANN models overestimated SOC content and showed a higher capability to detect the effects of management factors on SOC variations. In all the methods, management factors dominantly controlled SOC stock sequestration or degradation in different land use.
Keywords
CART
MLR
Neural Networks
Semi arid environment
Soil organic carbon
Amini, M., Abbaspour, K.C., Khademi, H., Fathianpour, N., Afyuni M. and Schulin, R. Neural network models to predict cation exchange capacity in arid regions of Iran. European  J. Soil Sci., 2005; 56: 551-559.
APERI. Mahidasht-Sanjabi plain study: (phase 1) volume 2, 3, 4 and 5:climate, topography, soil and soil study. TAM consulting engineers, Ministry of Agriculture, Iran. 2004; 325 P.
Attaeian, B. Estimation of aboveground biomass carbon sequestration potential in the rangeland ecosystems of Iran. ECOPERSIA, 2016; 4 (1): 1283-1294.
 Beers, T.W., Dress, P.E. and Wensel, L.C. Aspect transformation in site productivity research. J. Forestry. 1966; 64: 691–692.
Breiman, L., Friedman, J.H., Olshen, R.A. and Stone, C.J. Classification and regression trees. Wadsworth International Group, Belmont. 1984; 255 P.
Boellstorff, D.L. Estimated soil organic carbon change due to agricultural land management modifications in a semiarid cereal-growing region in Central Spain, J. Arid Environ., 2009; 73: 389-392.
Demuth, H., Beale, M., Hagan, M. Neural network toolbox 6: user’s guide. Version 6.0. 2. MathWorks. Inc; 2009; 452 P.
Evrendilek, F., Celik, I., Kilic, S. Changes in soil organic carbon and other physical soil properties along adjacent Mediterranean forest, grassland, and cropland ecosystems in Turkey, J. Arid Environ., 2004; 73: 389-392.
Han X., Atsushi, T., Mitsuru, T. Effects of land cover type and topography on soil organic carbon storage in northern loess plateau, china. Plant Soil Sci. first published on: 10july 2009.
Heshmati M., Gheitury M., Parvizi Y. and Hosseini M. 2015. Effect of Converting Forest to Rainfed Lands on Spatial Variability of Soil Chemical Properties in the Zagros Forest, Western Iran. ECOPERSIA, 2015; 3(4): 1161-1174.
Krenker, A., Bester, J. and Kos, A. Introduction to the artificial neural networks. Artificial neural networks: methodological advances and biomedical applications InTech, Rijeka ISBN 2011; 978-953.
Lal, R. The role of soil organic matter in the global carbon cycle. Soil and Environ. Pollut., 2008; 116: 353-362.
McBratney, A.B., Minasny, B., Cattle, S.R. and Vervoot, R.W. From pedotransfer function to soil inference system. Geoderma. 2002; 109: 41-73.
McCullagh, J. A modular neural network architecture for rainfall estimation, Artificial Intelligence and Applications, Innsbruck, Austria. 2005; 767-772.
Nelson, D.W., Sommers, L.E., Sparks, D., Page, A., Helmke, P., Loeppert, R., Soltanpour, P., Tabatabai, M., Johnston, C. and Sumner, M. Methods of soil analysis Part 3-chemical methods, 1996; 1010.
Park, S.J. and Vlek, P.L.G. Environmental correlation of three dimensional soil spatial variability: A comparison of three adaptive. Geoderma. 2002; 109:117-140.
Sarmadian, F., Taghizadeh, R. and Akbarzadeh, A. Modeling of some soil properties using artificial neural network and multivariate regression in Gorgan province, north of Iran. Aust. J. Basic Appl. Sci., 2009; 3(1): 323-329.
Sharma, U.C, Datta, M. and Sharma, V. Soil Fertility, erosion, runoff and crop productivity affected by different farming systems. Ecopersia, 2014; 2 (3): 629-650.
Somaratne, S., Seneviratne, G. and Coomaraswamy, U. Prediction of Soil Organic Carbon across Different Land-use Patterns:A Neural Network Approach, Soil Sci. Soc. of Am. J. 2005; 69: 1580-1589.
Sparling, G.P., Wheeler, D., Wesely, E.T. and Schipper, L.A. What is soil organic matter worth?, J. Environ. Qual. 2006; 35: 548-557.
Spencer, M.J., Whitfort, T. and McCullagh, J. 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; 275 P.
Tan, Z. and Lal, R. Carbon sequestration potential estimates with changes in land use and tillage practice in Ohio, USA. Agric., Ecosys. Environ., 2005; 126: 113-121.
Wilson, J.P. and Gallant, J.C. Terrain analysis: principles and applications: John Wiley and Sons; 2000; 1208.
Zhang, B., Zhang, Y., Chen, D. and White, R.E., Li, Y. A quantitative evaluation system of soil productivity for intensive agriculture in China. Geoderma, 2004; 123: 319-331
ECOPERSIA
Volume 5, Issue 1 - Serial Number 19
March 2017
Pages 1699-1709