ارزيابي روش شبكههاي عصبي مصنوعي براي شبيهسازي پيشروي جبهه رطوبتي خاكهاي لومي از يك منبع نقطهاي

Evaluation of artificial neural networks approach for simulation of advanced wetting front of loam soils from a point source

Shape (diameter and depth of wetted soil) and trend of advanced wetting front under a trickle is a function of soil properties, discharge and duration of applied water. With respect to numerous effective factors on shape and trend of advanced wetting front under drip irrigation, and capability of artificial neural networks, it seems that with collection of information for a relative extensive range of effective parameters, shape and trend of advanced wetting front in soil could be predicted. In this study conducted in 1383, cropping soil of Zayanderood River banks of Isfahan was used through combining various variables (such as loam textured soil with discharge applications of 2, 4, 8 and 12 lit/hr with 48 lit of irrigation water). Shape and trend of advanced wetting front was measured with a physical model and then, using Matlab ver 7 software (an artificial neural network named ANN-L) was designed to predict shape and trend of advanced wetting front under the trickle irrigation method.The results of this study showed that for this loam soil and each of the four applied discharges, the ANN-L had the ability to predict the trend of wetting front. In the designed network, RMSE was estimated to be 0.2878 and the coefficient of determination was R2=0.995. Small RMSE and large R2 values of network indicated proper match between trends of observed and predicted wetting fronts. The sensitivity analysis on parameters entered in ANN-L showed that with omission of the amount and time of irrigation, the performance of this neural network was weakened. The omission of physical properties of soil had lesser effect on neural networkʹs performance (p<0.05). The error of ANN-L network was equal to 1% which is not significant in applied cases. Thus, using ANN-L is recommended in predicting the trend of advanced wetting front under trickle irrigation under similar conditions.