Rice Leaf Disease Detection System with IOT-Based Environmental Monitoring

Rice cultivation is vital to global food security, yet farmers face significant challenges from leaf diseases and pest infestations, These problems can have a major impact on both the quantity and quality of crops. Conventional approaches to detecting diseases and pests, such as manual inspections, are labor-intensive, error-prone, and can lead to delayed interventions. To address these limitations, this system leverages deep learning and IoT technologies. To develop an automated system capable of real-time detection of diseases and pests in rice crops. The system utilizes the Inception V3 convolutional neural network, recognized for its superior accuracy and computational efficiency, to classify rice leaf images into categories such as healthy, diseased, or pest- damaged. A comprehensive dataset, enriched with data augmentation techniques, is used to train the model, enhancing its robustness in various environmental conditions. The system integrates an Arduino microcontroller, DHT11 sensor for environmental temperature monitoring, an LCD for real-time feedback, and a NodeMCU for IoT connectivity. Farmers can capture leaf images using mobile devices, which are analyzed by the model to detect diseases or pests. Upon detection, the system provides immediate feedback, suggests targeted pesticide recommendations, and tracks the progression of issues over time. The IoT integration allows remote monitoring and data storage, offering valuable insights for long-term crop management. This cost-effective and scalable solution empowers farmers with advanced diagnostic tools, reducing chemical overuse, minimizing crop losses, and promoting sustainable,Agricultural methods. By leveraging artificial intelligence and IoT, this system aims to revolutionize rice cultivation, making precision agriculture accessible to farmers worldwide.