Prediction of soil electrical conductivity using artificial neural network under deficit irrigation and salinity condition

Due to the limited water resources in agriculture, using to any ways to save water and also increase the acreage is very important. The objectives of this study were to predict the soil moisture content and soil electrical conductivity using artificial neural network model and to identify the most important independent properties affecting the soil moisture content and soil electrical conductivity under deficit irrigation and irrigation water salinity. Prediction of the artificial neural network models resulted R2=0.82-0.86 and root mean square error of 0.71-1.5 for soil moisture content and R2=0.78-0.85 and root mean square error of 0.08-0.38 for soil electrical conductivity, respectively. Our results indicated that the artificial neural network models could explain 0.78-0.86 % of the total variability in soil moisture content and soil electrical conductivity.