Machine learning (ML) and Internet of Things (IoT) are bolting down the agriculture in the area of plant disease management, especially. Then, this paper presents an innovative framework that utilizes ML and IoT technologies to improve the crop health and yield. IoT devices such as sensors and drones are used in the system at all times to monitor environmental conditions and plant health indicators including temperature, humidity, soil moisture, etc. This data is collected and transmitted to a central node for analysis by these sensors. ML algorithms at the advanced level such as convolutional neural networks (CNNs) and decision trees are used to find patterns in the data which signal the presence of possible diseases in the plant. Alerts are sent to the farmers real time when a disease is detected so that intervention is done early to reduce the spread of disease and save on crop loss. Large datasets are handled and powerful computations are made with cloud computing and there are scalable data processing and storage solutions provided. Using the proposed system, it was demonstrated that predictions of diseases like powdery mildew and blight are improved compared to traditional methods both in terms of accuracy as well as in the speed of response. Further, the framework is structured for privacy of data and security using strong encryption and secure access protocols. Using an integration between ML and IoT, agriculture is transformed to smart and better crop management, reducing the losses and encouraging sustainable farming. This helps in establishing that there is still room for disruption in smart agriculture technologies, and that the future holds promise in enabling more breakthroughs related to this area.
Bhoi et al. (Fri,) studied this question.