Evaluation of Artificial Neural Network (ANN), Adative Neuro-Fuzzy Inference System (ANFIS) and Regression Models in Prediction of Particulate Organic Matter-Carbon (POM-C) in the Rangelands Kharabe Sanji of Urmia

Soil organic carbon has favorable effects on the chemical, physical and thermal properties of the soil as well as on the biological activities in the soil. Particulate organic matter-carbon (POM-C) is one of the important unstable elements in the soil organic matter has a considerable role in soil quality and rangeland management. In this research, in order to exact estimate of POM-C using ANN, ANFIS, Regression models were developed. Towards this attempt, 60 soil samples were taken from the depth of 0-30 cm of the soil within 60 quadrates of 1m2 of located along 6 transects of 100m in the rangelands Kharabeh Sangi of Urmia. Soil properties (Nitrogen, clay, silt, organic carbon, pH, EC, apparent specific weight of soil) were measured. Statistic indicators RMSE, CE were used for performance evaluation of the models. The results showed RMSE and CE were calculated 0.16 and 0.41(in Regression Model), 0.11 and 0.65(in Artificial Neural Network Model), 0.06 and 0.79 (in Adative Neuro-Fuzzy Inference System Model), respectively. Also Adative Neuro-Fuzzy Inference System Model is considered as a strong tool in prediction of POM-C compared with Multivariate Linear Regression and Artificial Neural Network Models in the rangelands Kharabeh Sanji of Urmia.