Prediction of Water Distribution Uniformity of Sprinkler Irrigation System Based on Machine Learning Algorithms

Abstract

Abstract The coefficients of uniformity (Christiansen's uniformity coefficient CU and distribution uniformity DU), an important parameter for designing irrigation systems, and is an accurate measure for water lose. That research include, three sprinklers were used to measure the CU and DU results based on operating pressure, heights of sprinkler, discharge, nozzle diameter, wind speed, humidity, highest temperature and lowest temperature to determine the best parameters for good irrigation design and also to select the best scenario effects on CU and DU values for square and triangular system based on four scenarios were applied to predict the DU based on machine learning algorithms. The main findings are 1) the highest CU was 86.7% in the square system of 2520 sprinkler under 200 kPa, height of 0.5m and the discharge was 0.855 m3/h (Nozzle 2.5mm). Furthermore, it was 87.3% in the triangled system under the same pressure and discharge however on the 1m height. 2) In CU, the highest of R2 is 0.796, 0.825 and 0.929 in RF, XGB and XGB-RF respectively in the first scenario. 3) On contrast, for the DU, the highest value of R2 is 0.7014, 0.4791 and 0.8275 in RF, XGB and XGB-RF respectively in the first scenario.