An Integrated IoT-Based System for Automated Plant Disease Detection and Management

These days, a plant health examination is essential for guaranteeing food security and sustainable farming practices. This study introduces a novel integrated system that automates the detection and management of plant diseases by utilizing computer vision, machine learning, and Internet of Things (IoT) technology. The ESP32 microcontroller, at the heart of the system, manages the gathering of data from a camera module and several environmental sensors. Together, these elements are able to take readings and pictures of the crop environment in real time. The photos are processed by a Convolutional Neural Network (CNN) that has been trained to recognize the visual signs of common plant diseases. The system provides disease-specific insights and recommended mitigation measures to farmers immediately upon detection through a Telegram bot and a dedicated web dashboard. Although the prior works have shown the ability of CNNs for classification of plant disease and environmental monitoring via IoT network, many of the works lacked real-time communication ability or possessed complex configurations. The proposed solution corrects these limitations through the offer of a compact, low-cost, and scalable design, implementable in rural areas. Through the facilitation of the early detection of disease, the minimization of labor, and the support of environmentally responsible farming, the system attempts to empower the farmer with real-time, data-based decisions. The integration of AI-based analysis and smart communication tools makes the work herein a step further in the development of precision agriculture, particularly among resource- constrained groups of farmers.