Ahmed I. Al-Amoud

Artificial neural networks for estimating the hydraulic performance of labyrinth-channel emitters

The emitter flow variation (qvar) and manufacturers coefficient of variation (CV) were modeling.Artificial neural network (ANN) was developed for estimating of the emitter hydraulic performance.Statistical criteria indicated that the ANN model was better than multiple linear regression model.Using the ANN model provides qvar and CV values with high accuracy. In this paper, we examine the discharge of labyrinth-channel emitters under different operating pressures (P) and water temperatures (T). An artificial neural network (ANN) and multiple linear regression (MLR) model are developed for the emitter flow variation (qvar) and the manufacturers coefficient of variation (CV). As well as P and T, the structural parameters of the labyrinth emitter are considered as independent variables. The ANN results demonstrate that a feed-forward back-propagation network with five input neurons and 14 neurons in the hidden layer successfully model qvar and CV. The trapezoidal unit spacing and path length of the labyrinth emitter are found to be insignificant. In our ANN model, we use a hyperbolic tangent as the activation function in the hidden layer and the output layer. Statistical criteria indicate that the ANN is better at predicting the hydraulic performance of the labyrinth emitters than MLR. The root mean square errors for qvar and CV are 1.0497 and 0.0044, respectively, for the ANN model, and 2.0703 and 0.0107, respectively, for the MLR model using a test dataset. The relatively low errors obtained by the ANN approach lead to high model predictability and are feasible for modeling the hydraulic performance of labyrinth emitters.

Water conservation through irrigation scheduling under arid climatic conditions

Abstract A field experiment was carried out on wheat crop at the project sites of Hail Development Company (HADCO), about 500 km north-west of Riyadh, Kingdom of Saudi Arabia. Four centre pivot circles (each 54 ha in area) were used in the study. A model based on the Modified Penman Method (FAO version) was developed and used for irrigation scheduling. The required micro-climatic parameters were continuously monitored by an automatic weather station installed at the site and transmitted to a computer for processing and analyses. The results of the experiment indicated that an appreciable amount of water (25%) was saved as compared to the irrigation practice adopted by HADCO, and the yield is increased significantly by using this technique of scheduling. In addition, the conservation of water results in reducing the working hours of the equipment and labour.

Infrared telemetry for data acquisition and telecontrol in automatic irrigation scheduling

Abstract An infrared telemetry and telecontrol system was employed in a project of automatic irrigation scheduling based on soil moisture sensing. It was used to transmit continuous soil moisture potential from a remote field planted with wheat to a base station for analysis. In the base station, where a microcomputer was housed, the field information was processed through water management software developed for this purpose to decide when to start or stop irrigation based on a predetermined threshold for soil water potential. When start or stop irrigation was decided by the computer, a telecontrol signal was sent through the infrared system to the pumping station to deliver water or to stop it.

Gene expression programming approach for modeling the hydraulic performance of labyrinth-channel emitters

GEP was developed to predict of the emitter hydraulic performance qvar and CVm.The GEPwithout L model was better than GEPwithout S model for qvar.The GEPwithout S model was better than GEPwithout L model for CVm.The predicted non-pressure-compensating emitters qvar and CVm were more accurate.The GEP approach leads to high model predictability. The different hydraulic measures of emitter flow variation (qvar) and manufacturers coefficient of variation (CVm) at different operating pressure (P) and water temperature (T) were determined by measuring the discharge of different labyrinth-channel emitters. Gene expression programming (GEP) was used to model and predict qvar and CVm of the labyrinth emitters. The structural parameters of each labyrinth emitter [namely, trapezoidal unit number (N), height (H), and spacing (S), and path width (W) and length (L)] as well asP and T were considered as independent variables. The accuracy of GEP models was evaluated by their coefficient of determination (R2), root-mean-square error (RMSE), overall index of model performance (OI), and mean absolute error (MAE). Results of GEP applications established that L and S were the least important variables affecting qvar and CVm, respectively, while N and H were the most important variables. For qvar, the GEPwithout L model gave higher R2 and OI and lower RMSE and MAE than those of the GEPwithout S model. Conversely, for CVm, R2 and OI of the GEPwithout L model were lower and its RMSE and MAE were higher than the corresponding parameters of the GEPwithout S model. Overall, our results indicated that the performance of the developed GEP models were better at predicting qvar and CVm for non-pressure-compensating emitters than pressure-compensating ones. The GEP approach can be a good tool to predict the hydraulic performance of labyrinth emitters.