Effective field capacity prediction model for management of UAV spraying

Abstract

The use of pesticides in agriculture is critical to maintaining the quality of agricultural production. Farmers are required to finish their spraying with high efficiency due to constraints in cost and time. Nevertheless, farmers need more knowledge and information required for managing Unmanned Aerial vehicles (UAV) spraying and providing the conditions of their fields because both data (management and field conditions) affect capacity. The field capacitance model was generated from UAV spraying (Tiger Drone) on a sugarcane field. Consequently, this research intended to discover the prediction model for effective field capacity for UAV spraying (Tiger Drone) in the sugarcane field. The procedure began by collecting the data of nine UAVs spraying in the sugarcane fields, for example, field, crop, UAV condition, and working times, to develop the prediction model for the UAV spraying in the sugarcane field. The prediction model was then validated using nine sugarcane fields collected correspondingly to the model’s output. The conclusion presented was that the model’s root mean square error (RMSE) was 0.14 m²/s. Farmers and providers can apply a predictive model to manage the spraying process and provide their field conditions.