Sprayer System on Autonomous Farming Drone Based on Decision Tree

Agriculture in Indonesia faces various challenges, including inequality of productivity in various regions. One of the proposed solutions is the utilization of drones to increase the efficiency of the agricultural watering process. Machine learning technology is also used in classifying drone sprayers. This study used the decision tree method to classify the strength of watering with an accuracy rate of 98.9%. The classification analysis is based on measurements of the drone's altitude, wind speed and speed sensors. The results of this study contribute to improving precision control on agricultural watering using drones, opening up opportunities for significant productivity improvement in Indonesia's agricultural sector.