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

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.