This study employed artificial neural network method for predicting the sprayer drift under different conditions\nusing image processing technique. A wind tunnel was used for providing air flow in different velocities. Water Sensitive\nPaper (WSP) was used to absorb spray droplets and an automatic algorithm processed the images of WSPs for measuring\ndroplet properties including volume median diameter (Dv0.5) and Surface Coverage Percent (SCP). Four\nLevenberg-Marqurdt models were developed to correlate the sprayer drift (output parameter) to the input parameters (height,\npressure, wind velocity and Dv0.5). The ANN models were capable of predicting the output variables in different conditions\nof spraying with a high performance. Both models predicted the output variables with R2 values higher than 0.96 indicating\nthe accuracy of the selected networks. Therefore, the developed predictor models can be used in precision agriculture for\ndecreasing spray costs and losses and also environmental contamination.
Loading....