Abstract
A new approach based on Artificial Neural Networks (ANNs) is presented to simulate the effects of wind on the distribution pattern of a single sprinkler under a center pivot or block irrigation system. Field experiments were performed under various wind conditions (speed and direction). An experimental data from different distribution patterns using a Nelson R3000 Rotator® sprinkler have been split into three and used for model training, validation and testing. Parameters affecting the distribution pattern were defined. To find an optimal structure, various networks with different architectures have been trained using an Early Stopping method. The selected structure produced R2= 0.929 and RMSE = 6.69 mL for the test subset, consisting of a Multi-Layer Perceptron (MLP) neural network with a backpropagation training algorithm; two hidden layers (twenty neurons in the first hidden layer and six neurons in the second hidden layer) and a tangent-sigmoid transfer function. This optimal network was implemented in MATLAB® to develop a model termed ISSP (Intelligent Simulator of Sprinkler Pattern). ISSP uses wind speed and direction as input variables and is able to simulate the distorted distribution pattern from a R3000 Rotator® sprinkler with reasonable accuracy (R2> 0.935). Results of model evaluation confirm the accuracy and robustness of ANNs for simulation of a single sprinkler distribution pattern under real field conditions.
Highlights
The water distribution pattern and spacing of sprinklers are two important factors that can affect the application uniformity of sprinkler irrigation systems
The aim of this paper is to develop and evaluate a new approach based on Multi-Layer Perceptron (MLP) neural networks to simulate the wind distorted water distribution patterns under field conditions
A multi-layer perceptron with backpropagation training algorithm was used for simulation of single sprinkler distribution pattern
Summary
The water distribution pattern and spacing of sprinklers are two important factors that can affect the application uniformity of sprinkler irrigation systems. To avoid laborious field tests and to improve the design of irrigation systems, several studies have been conducted over the last 30 years to develop irrigation simulation models which can be used for the estimation of water distribution patterns of irrigation systems under real or controlled conditions. These models have been categorized to ballistic, semi-empirical and statistical (Granier et al, 2003). For a given sprinkler configuration in a no-wind condition, droplet diameter is a major factor that affects the travel distances of droplets (i.e. the horizontal distance between droplet landing point and the sprinkler nozzle). The major advance of ballistic models has occurred in the last few decades and several irrigation simulation models have been developed (Fukui et al, 1980; Vories et al, 1987; Seginer et al, 1991a; Carrion et al, 2001; Montero et al, 2001; Dechmi et al, 2004; Lorenzini, 2004; De Wrachien & Lorenzini, 2006; Playan et al, 2006; Yan et al, 2010)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
