Developing Pedotransfer Functions for Estimating some Soil Properties using Artificial Neural Network and Multivariate Regression Approaches

Study of soil properties like field capacity (F.C.) and permanent wilting point (P.W.P.) plays important roles instudy of soil moisture retention curve. Although these parameters can be measured directly, their measurement isdifficult and expensive. Pedotransfer functions (PTFs) provide an alternative by estimating soil parameters from morereadily available soil data. In this investigation, 70 soil samples were collected from different horizons of 15 soilprofiles located in the Ziaran region, Qazvin province, Iran. The data set was divided into two subsets for calibration(80%) and testing (20%) of the models and their normality were tested by Kolmogorov-Smirnov method. Bothmultivariate regression and artificial neural network (ANN) techniques were employed to develop the appropriate PTFsfor predicting soil parameters using easily measurable characteristics of clay, silt, O.C, S.P, B.D and CaCO3. Theperformance of the multivariate regression and ANN models was evaluated using an independent test data set. In orderto evaluate the models, root mean square error (RMSE) and R2 were used. The comparison of RMSE for two mentionedmodels showed that the ANN model gives better estimates of F.C and P.W.P than the multivariate regression model.The value of RMSE and R2 derived by ANN model for F.C and P.W.P were (2.35, 0.77) and (2.83, 0.72), respectively.The corresponding values for multivariate regression model were (4.46, 0.68) and (5.21, 0.64), respectively. Resultsshowed that ANN with five neurons in hidden layer had better performance in predicting soil properties thanmultivariate regression.