IOT-driven precision agriculture: A comprehensive review of machine learning techniques for rice plant disease diagnosis and nutrient deficiency detection using IOT sensor data

In many nations, rice is the primary agricultural product. On the other hand, illnesses on rice plants may cause the crop to produce less rice overall and of lower quality. Consequently, early identification of plant diseases will aid in shielding rice from serious infection and minimizing crop loss. The recent utilization of GPS and a camera in agricultural monitoring is a substitute tool for gathering data in large area fast and independently. This review describes existing systems based on Internet of Things (IoT) which uses real-time information, including acquisition utilizing image processing techniques to perform rice disease diagnosis and classification in order to improve rice yield. The IoT sensors employed in such systems continuously monitor crucial environmental parameters, including soil moisture, temperature, and nutrient levels, providing real-time data for analysis. The system can map the location of diseased rice plants on rice fields and present the analytical technique by using a sensor to detect the position in real-time. The aims of these systems are to function as a prototype for an early and real-time disease detection system based on the Internet of Things.