Point estimation of soil moisture characteristic curve using artificial neural networks and its optimizing by genetic algorithm in Agro-Industries of Khouzestan

Document Type : Research

Authors

1 Department of Soil Science, Ramin Agriculture and Natural Resources University of Khuzestan, Ahvaz, Iran

2 Prof., Department of Soil Science, Ramin Agriculture and Natural Resources University of Khuzestan, Ahvaz, Iran

3 Associate Prof., Department of Soil Science, Ramin Agriculture and Natural Resources University of Khuzestan, Ahvaz, Iran

4 Prof., Department of Soil Science, Shahrekord University, Shahrekord, Iran

Abstract

Soil hydraulic properties have key role in sugar cane cultivation management. The purpose of this study is to estimate soil moisture characteristic curve using an artificial neural network and its optimization with genetic algorithm. Therefore, based on the cultivation operations management and soil properties included: organic matter content, soil texture, electrical conductivity, sodium adsorption ratio, 4 land unit tracts in Debel-Khozaii, Amir-Kabir, Karoon and Haft-Tapeh agro-industries were selected. A total of 310 soil samples from both 0-40 and 40-80 cm of soil profiles were collected. In this study, five models were arranged in hierarchy to estimate soil hydraulic properties with ANNs. The performances of the models were evaluated using Spearman's correlation coefficient (r) between the observed and the estimated values, normalized mean square error (NMSE), and mean absolute error (MAE). Owing to the fact that the selection of each of the variable parameters of neural network necessitated recurring trails and errors, and consequently teaching a large number of networks with various topologies, genetic algorithm method was utilized for finding the optimization of these parameters and the efficiency of this method was examined in terms of the optimization of neural network. Results showed that the neural network has a high degree of accuracy in modeling and estimating soil moisture characteristic curve (R =0.943, MAE=0.019, NMSE=0.054). Also, combining artificial neural networks with genetic algorithm for optimizing the conditions of the artificial neural networks implementation was positive and combining approach indicated its superiority over non-optimized implementation of artificial neural networks in all cases (R=0.985, MAE=0.01, NMSE =0.0151).

Keywords

References

  1. Borgesen, C. D., Iversen, B. V., Jacobsen, O. H., and Schaap, M. G. (2008). Pedotransfer functions estimating soil hydraulic properties using different soil parameters. Hydrological Processes. Vol, 22. pp: 1630-1639.

    Chakraborty, D., Mazundar, S. P., Garg, R. N., Banerjee, S., Santra, P., Singh, R., and Tomar, R. K. (2011). Pedotransfer functions for predicting points on the moisture retention curve of Indian soils. Indian Journal of Agricultural Sciences. Vol, 81. pp: 1030–1036.

    Deb, K. 2009. Genetic algorithm approach to multi-objective optimization issue. Translator: Rezaei, J. Vali-Asr University. Rafsanjan. pp. 624.

    Dilkova, R., Jokova, M., Kerchev, G., and Kercheva, M. (1998). Aggregate stability as a soil quality criterion. Soil science, agrochemistry and ecology. pp: 305-312.

    Faghih, H. 2010. Assess the application of artificial neural networks and optimization it with the genetic algorithm approach to estimate the monthly precipitation (The Case of study: the Kurdistan region). Science and Technology of Agriculture and Natural Resources. Soil and Water Science. Vol, 51. pp: 27-42.

    Fauconnier, R. 2004. Sugarcane cultivation and production principles. Translators: Hamid Madani and Ghoaban Noormohammadi. Islamic Azad University. Arak. pp. 150.

    Ghorbani Dashtaki, S., Homaee, M., and Khodaverdiloo, H. (2010). Derivation and validation of pedotransfer functions for estimating soil water retention curve using a variety of soil data. Soil Use and Management. Vol, 26. pp: 68-74.

    Johari, A., Javadi, A. A., and habibagahi, G. (2011). modeling the mecanical behavior of unsaturated soils using a genetic algorithm-based neural network. Computer and Geotecnic. Vol, 38. pp: 2-13.

    Keshavarzi, A., Sarmadian, F., Labbafi, R., and Ahmadi, A. (2011). Developing Pedotransfer Functions for Estimating Field Capacity and Permanent Wilting Point Using Fuzzy Table Look-up Scheme. Computer and Information Science. Vol, 4. pp: 130-141.

    Kianpoor Kalkhajeh, Y., Rezaie Arshad, R., Amerikhah, H.,  and Sami, M. (2012).  Multiple Linear Regression, Artificial Neural Network (Mlp, Rbf) and ANFIS Models for Modeling the Saturated Hydraulic Conductivity of Tropical Region Soils (A case study: Khuzestan Province: Southwest Iran). International Journal of Agriculture. Research and Review. Vol, 2. pp: 255-265.

    Majdalani, S., Angulo-Jaramillo, R., and Di Pietro, L. (2008). Estimating preferential water flow parameters using a binary genetic algorithm inverse metgod. Environmental Modeling & Software. Vol, 23. pp: 950-956.

    Matlabi, A., Homaee, M., Zarei, Gh., and Mahmoudi, Sh. (2010). Studying effect of Lime on hydraulic properties using pedotransfer functions in Garmsar. Irrigation and Drainage. Vol, 3. pp: 426-439.

    Matthews, J. (2000). Using Genetic Algorithm with Neural Networks. Generation 5, May 2000.

    Menhaj, M. B. (2002). Fundamentals of Neural Networks. Amirkabir University Press. pp. 715.

    Mermoud, A., and Xu, D. (2006). Comparative analysis of three methods to generate soil hydraulic functions. Soil and Tillage Research. Vol, 87. pp: 89-100.

    Michalewicz, Z. (1996). Genetic Algorithms+Data Structure =evolutionary Program. Third edition. Springer-Verlag. Berlin.

    Montana. D. J. (2001). Training Feed Forward Neural Network using Genetic Algorithm. Cambridge. Ma. 02138.

    Musy, A., and Soutter, M. (1991). Physique du sol. In: Collection gerer lenvironnement. Presses Polytechniques et Universitaires Romandes. Lausanne. p. 335.

    Naseri, A. A., Jafari, S., and Alimohammadi, M. (2007). Soil compaction due to sugarcane (Saccharum officinarum) mechanical harvesting and the effects of sub soiling on the improvement of soil physical properties. Applied Scientific Information, ISSN 1812-5654.

    Otto, R., Silva, A. P., Franco, H. C. J., Oliveira, E. C. A.  and Trivelin, P. C. O. (2011). High soil penetration resistance reduces sugarcane root system development.Soil and Tillage Research. Vol, 117. pp: 201-210.

    Ouattara, K., Ouattara, B., Assa, A., and Sedogo, P. M. (2006). Long-term effect of ploughing and organic matter input on soil moisture characteristics of a Ferric Lixisol in Burkina Faso. Soil and Tillage Research. Vol, 88. pp: 217-224.

    Parasuraman, K., Elshorbagy, A., and Cheng Si, B. (2007). Estimating Saturated Hydraulic Conductivity Using Genetic Programming. Soil Science Society of American Journal. Vol, 71. pp: 1676-1684.

    Parvareshrizi, A., Koochakzade, S., and Omid, M. H. (2006). Estimating moving hydraulic jump profile using artificial neural networks and integrated neural networks - genetic algorithm. Agricultural Sciences. Vol, 37. pp: 187- 196.

    Patil,N. G., Pal, D. K., Mandal, C.,and Mandal, D. K. (2012). Soil Water Retention Characteristics of Vertisols and Pedotransfer Functions Based on Nearest Neighbor and Neural Networks Approaches to Estimate available water capacity. Irrigation and Drainage Engineering. Vol, 138. pp: 138-177.

    Pedroso, D. M., and Williams, D. J. (2011). Automatic calibration of soil- water characteristic curve using genetic algorithms. Computers and Geotecnics. Vol, 38. pp: 330-340.

    Sarmadian, F., Taghizadeh Mehrjui, R. A., and Akbarzadeh, A. (2009). Optimization of Pedotransfer Functions Using an Artificial Neural Network. Australian Journal of Basic and Applied Sciences. Vol, 3. pp: 323-329.

    SAS Institute Inc. (1999). SAS/STAT User’s Guide. Ver. 8.0. SAS Institute Inc., Cary, NC.

    Schaap, M. G., Leij, F. J.,  and Van Genuchten, M. Th. (1998). Neural network analysis for hierachical prediction of soil water retention saturated hydraulic conductivity. Soil Science Society of American Journal. Vol, 62. pp: 847-855.

    Schulze, R. (2000). Transcending scales of space and time in impact studies of climate and climate change on agro-hydrological responses. Agric.  Ecosyst. Environ. Vol, 82. pp: 185–212.

    Shirani, H. and Rafienejad, N. (2012). Prediction of Some Difficult-to-measure Soil Characteristics Using Regression Pedotransfer Functions and Artificial Neural Network in Kerman Province. Iranian Journal of Soil Research (Soil and Water Science). Vol. 25, No. 4.

    Torabi Farsani, N., and Ghahramani, B. (2007). Comparing some conventional transfer functions for estimating soil water retention curve in some soil in Iran. Irrigation and Drainage of Iran. Vol, 1. pp: 45- 55.

    Wosten, J. H. M., Pachepsky, Y. A., and Rawls, W. J. (2001). Pedotransfer functions bridging the gap between available basic soil data and missing soil hydraulic characteristics. Hydrology. Vol, 251. pp: 123-150.

    Zhang, S., Grip, H., and Lovdahl, L. (2006). Effect of soil compaction on hydraulic properties of two loess soils in China. Soil and Tillage Research. Vol, 90. pp: 117-125.

    1. Zhu, A. X., and Julian, J. (2011). Unsaturated Hydraulic Properties of Anisotropic Soils. State Water Resources Research Institute Program.

Files

History

  • Receive Date: 03 February 2018
  • Accept Date: 03 February 2018

Share

How to cite

Statistics