A new suggestion for an irrigation schedule with an artificial neural network

This study used artificial neural networks (ANNs) to propose a new system of irrigation ratios and time intervals. Data on soil moisture, soil type, product type and time interval were used as input parameters for the ANN and the network was trained through the Levenberg-Marquardt learning algorithm. The outputs of the model determined the water requirement of the plant and the irrigation time intervals. The aim of this study is to perform irrigation at night, to reduce water losses from evaporation and thereby promote water conservation. In addition, the study aimed to save on energy, as less irrigation would be provided compared to daytime irrigation. The system was tested in a strawberry orchard of 1000 m2 in the Serik district of Antalya, Turkey. The trial achieved a 20.46% water saving and 23.9% energy saving. © 2013 Copyright Taylor and Francis Group, LLC.