www.ccsenet.org/mas Modern Applied Science Vol. 4, No. 10; October 2010 ISSN 1913-1844 E-ISSN 1913-1852 76 Using of Artificial Neural Networks for Evaluation Soil Water Content with Time Domain Reflectometry Davood Namdar-Khojasteh (Corresponding author) Graduate student, Department of Soil Science Faculty of Agricultural Engineering and Technology University of Tehran, Karaj, Iran Tel: 98-913-958-2264 E-mail: davoodnamdar@gmail.com Mahdi Shorafa Associate professor, Faculty of Agricultural Engineering and Technology University of Tehran, Karaj, Iran Tel: 98-912-263-0992 E-mail: m_shorafa@yahoo.co.uk Mahmoud Omid Associate professor, Faculty of Agricultural Engineering and Technology University of Tehran, Karaj, Iran Tel: 98-912-361-1832 E-mail: omid@ut.ac.ir Abstract Time Domain Reflectometry (TDR) has become an established method for soil volumetric water content (  ) measurement. TDR exploits the difference in dielectric constant values between the solid phase, air phase and liquid phase. In this paper, we study and evaluate the ability of empirical models to fit TDR calibration data for the soils of different textures, and adopt artificial neural network (ANN) to predict the K a –  relationship using soil physical parameters for ten different heavy texture soil types. The explanatory parameters that gave the most significant reduction in the root mean square error (RMSE) were dielectric constant, bulk density, clay content, silt content, sand content and organic matter content. The K a –  relationship for each soil type was predicted using the other nine soils for calibration purposes. To find the optimum model, various multilayer perceptron (MLP) topologies, having one hidden layer of neurons were investigated. In this analysis, K a , bulk density and clay content were selected as input to ANN. The (3-10-1)-MLP, namely a network having 10 neurons in its hidden layer resulted in the best-suited model estimating the soil water content of the heavy texture soils at all soil types. For this topology, R 2 and RMSE values were 0.998 and 0.00433, respectively. A comparative study among ANN models and various empirical models was also carried out. ANN models with RMSE and R 2 of 0.0043-0.0134 (m 3 m -3 ) and 0.923-0.998, respectively, gave better predictions than empirical models. The ANN model performed superior than both empirical and physical models. Since (3-10-1)-MLP outperformed regression models and it uses only one set of weights and biases for all soil types, it should be preferred over empirical and physical models. Keywords: Soil, Volumetric water content, Dielectric constant, TDR, Artificial neural network 1. Introduction Time Domain Reflectometry (TDR) has become an established method for soil volumetric water content (SWC) measurement. TDR exploits the difference in dielectric constant values between the solid phase, air phase and liquid phase. At the TDR frequencies, pure liquid water has a dielectric constant of about 80 (depending on temperature and electrolyte solution), air has a dielectric constant of about 1, and the solid phase of about 4 to 16 (Wraith and Or, 1999). A dielectric model is typically used to translate measured dielectric properties (usually the relative constant, ε ௥ ) to SWC (ș) of the composite material. Dielectric mixing models aim to quantify the influence of a range of physical properties on ε ௥ of a material, and the model may take the form of ߠሺε ௥ ሻ or vice versa. Thus, in studies where high accuracy is needed, a soil-specific calibration is normally required. This is, however, often an elaborate procedure, even if in some of the recent studies researchers have provided more efficient calibration methods. To avoid such an elaborate, time-consuming procedure, the soil physical