Davatgar, N., Sepaskhah, A., Neyshabouri, M., Neyshabouri, M., Bayat, H., Narimanzadeh, N. (2015). Evaluation of Group Method of Data Handling (GMDH) Algorithm Efficiency for Predicting Water Retention Indices in Paddy Soils. , 29(2), 175-188. doi: 10.22092/ijsr.2015.102211
N. Davatgar; A. R. Sepaskhah; M. R. Neyshabouri; M. R. Neyshabouri; H. Bayat; N. Narimanzadeh. "Evaluation of Group Method of Data Handling (GMDH) Algorithm Efficiency for Predicting Water Retention Indices in Paddy Soils". , 29, 2, 2015, 175-188. doi: 10.22092/ijsr.2015.102211
Davatgar, N., Sepaskhah, A., Neyshabouri, M., Neyshabouri, M., Bayat, H., Narimanzadeh, N. (2015). 'Evaluation of Group Method of Data Handling (GMDH) Algorithm Efficiency for Predicting Water Retention Indices in Paddy Soils', , 29(2), pp. 175-188. doi: 10.22092/ijsr.2015.102211
Davatgar, N., Sepaskhah, A., Neyshabouri, M., Neyshabouri, M., Bayat, H., Narimanzadeh, N. Evaluation of Group Method of Data Handling (GMDH) Algorithm Efficiency for Predicting Water Retention Indices in Paddy Soils. , 2015; 29(2): 175-188. doi: 10.22092/ijsr.2015.102211

Evaluation of Group Method of Data Handling (GMDH) Algorithm Efficiency for Predicting Water Retention Indices in Paddy Soils

پژوهش های خاک
Article 5, Volume 29, Issue 2, September 2015, Pages 175-188    PDF (363.57 K)
Document Type: Research Paper
DOI: 10.22092/ijsr.2015.102211
Authors
N. Davatgar* 1; A. R. Sepaskhah2; M. R. Neyshabouri3; M. R. Neyshabouri4; H. Bayat5; N. Narimanzadeh6
1Assistant Professor, Rice Research Institute of Iran
2Professor, Shiraz university
3Professor, Tabriz University
4MSc, Rice Research Institute of Iran
5Assistant Professor, Hamedan University
6Professor, Guilan University
Abstract
Accuracy of the pedo-transfer functions can be improved using more flexible equations. The objective of this study was to compare pedo-transfer functions with different flexibility [e.g. multiple linear regression (MLR), the physic-empirical model of Arya and Paris (AP), artificial neural network (ANN), and group method of data handling (GMDH)] for predicting soil water contents at field capacity and permanent wilting point. Pedo-transfer functions were developed from data of particle size distribution, organic carbon, bulk density, and water contents at 0,.33 and 1500 kPa. The accuracy and reliability of the GMDH algorithm was superior to the other pedo-transfer functions for predicting the soil volumetric water contents at field capacity and permanent wilting point, because of fewer lower roots mean squared error (RMSE) and AIC criteria and more larger agreement index (D-index). It seems that the GMDH preference superiority is due to its higher GMDH capability to determine nonlinear and complex relationships between soil factors affecting factors the soil water contents at field capacity and permanent wilting points.
Keywords
Field capacity; Multiple Linear Regression; Neural network; Pedo-transfer function; Permanent wilting point
Statistics
Article View: 2,268
PDF Download: 1,455


counter
Journal management system. designed by sinaweb