Design of Basin Irrigation System using Multilayer Perceptron and Radial Basic Function Methods

The common use of an artificial neural network model has been in water resources management and planning. length, width, discharge a basin were measured this study utilizing field data from 160 Dashti Hawler existing projects. Multilayer Perceptron (MLP) Radial Basic Function (RBF) networks employed the irrigation assessment. Input factors included soil type, conveyance system effectiveness, root zone depth. 130 projects used for calibration, while remaining 30 validation. When developing system, models’ aforementioned indicators’ performance was evaluated using coefficient determination (R2), mean absolute error (MAE), relative (RE), Nash Sutcliff efficiency (NSE). For basin's discharge, (R2) values MLP determined to be 0.97, 0.96, respectively, whereas corresponding RBF 0.88, 0.89, 0.89. Compared model, (MAE) 8.99, 8.52, 42.58, respectively. However, (NSE) models mentioned above 0.95, 0.94, as well 0.65, 0.66, 0.66 basin’s it comes building basin, is more precise than depending on Finally, ANN approach uses additional design options quickly examine which computationally efficient.