Estimating of Water Distribution Uniformity in Sprinkler Irrigation Using Data Mining techniques

Considering that water shortage is the major dilemma for Sustainable agriculture development and water potential of the country is no longer able to adequately meet the growing needs of water demand especially in agricultural section, it's essential to optimize water consumption.Uniformity of sprinkler irrigation is an important technical parameter for designing sprinkler irrigation systems. Due to high diversity of sprinklers used in sprinkler irrigation, it's necessary to improve irrigation system performance with simple changes such as changes in system operating pressures, riser head, setting sprinkler spacing on laterals and the distance between laterals. In this research, CU quantities of two types of sprinkler (AQ-20 and KA-6) were measured in slow wind velocity (0-2 m/s) , at Hashemabad cotton research station of Gorgan city under 4 different operating pressures (2, 2.5, 3 and 3.5 at), 16 distances of sprinklers (including 9×18, 12×18, 15×18, 18×18, 9×15, 12×15, 15×15, 18×15, 9×12, 12×2, 15×12, 18×12, 9×9, 9×12, 9×15 and 9×18) , 4 riser heads (60, 90, 120 and 150 cm) and 3 arrangements of sprinklers (square, rectangular and triangular). Decision tree model M5 was used to estimate uniformity of each sprinkler and the results were compared with K - nearest neighbor method. By statistical comparison of results, root mean squared error (RMSE) for AQ-20 sprinkler in M5 and K-NN methods were obtained as 0.0681 and 0.052 and for KA-6 sprinkler as 0.086 and 0.0716, respectively. The results indicate the high accuracy of both methods for modeling, since M5 is capable of estimating explicit equations for estimating CU; it incorporates more practical features.