Autonomous quadcopter-based intelligent irrigation system for enhancing crop care

Abstract

Efficient crop care and high productivity are paramount to meeting global food demands amid a growing population. Leveraging advanced technologies, including precise irrigation systems conserve vital resources such as water, minimize waste, and foster sustainability. Consequently, the study presented focused on developing an intelligent irrigation system with the facility of real-time environmental monitoring to optimize water usage and increase efficiency through precise, data-driven irrigation practices. The methodology involves an autonomous quadcopter (DJI Tello) hovering over a selected land area and a weather station on the ground. The weather station was created using an ESP32 microprocessor equipped with several sensors; a DHT11 sensor, Infrared counting sensor module, Capacitive soil moisture sensor (MD0247), water level sensor (MD0207), and LDR sensor (MD0222) to monitor temperature, humidity, rainfall, wind speed, solar intensity, and soil moisture. Furthermore, a computer vision model was developed using YOLOV8 to identify the selected three crops: Arachis hypogaea, Capsicum annuum, and Antherella Sessilis. The developed irrigation system demonstrated outstanding water delivery performance by effectively reducing wastage of water by 20% and enhancing crop growth rates by 10%. This enhancement is ascribed to real-time environmental monitoring and continuous analysis of data from the sensors of the weather station. Moreover, the acquired data is stored in a database and displayed through a user-friendly web application where the data is precisely analyzed and displayed as a dashboard. Web application is aimed at user convenience providing users with location-based weather forecasts, sensor outputs and user tips while predicting the amount of water needed to be delivered in upcoming months. The findings in the presenting work highlighted significant improvements in both irrigation efficiency and crop yield. This demonstrates its potential to be applied in agriculture more extensively by adapting to different environmental conditions and crop needs. Furthermore, the developed web application integrates real-time monitoring and computer vision, providing actionable insights that democratize agricultural knowledge and improve agricultural outcomes. In conclusion, the findings signify a significant leap forward in agricultural technology, addressing inherent challenges of traditional farming with sustainable solutions. This initiative not only aims to enhance agricultural productivity but also aligns with broader goals of promoting sustainable and environmentally friendly farming practices.