<![CDATA[Efficiency in agricultural management remains a major challenge in supporting sustainable food security. One critical issue faced by farmers is the limited capability to monitor plant conditions in real-time and accurately determine the optimal timing for irrigation. This study aims to develop an intelligent system based on the Internet of Things (IoT) capable of monitoring and automatically irrigating plants with the support of the Naive Bayes classification algorithm. The system was built using the ESP32 microcontroller and a set of environmental sensors, including the DHT11 (temperature and humidity), soil moisture sensor (soil water content and pH), and LDR (light intensity). Data collected by the sensors are transmitted to a monitoring server and analyzed using the Naive Bayes model to classify whether the plants require irrigation. If the classification result indicates the need for irrigation, the system will automatically activate a water pump. The system was tested over a 48-hour period with data captured every five seconds. The experimental results demonstrate that the system operates stably and accurately, achieving an average classification accuracy of 92.5%. Furthermore, water usage was optimized by up to 35% compared to manual irrigation methods. This system has reached Technology Readiness Level (TRL) 6, indicating its feasibility for controlled field testing. The results of this research are expected to support the implementation of precision agriculture in Indonesia, particularly in data-driven water management.]]>
Copyrights © 2025
