Plant diseases continue to pose significant challenges to global agriculture, impacting crop yields and food security. This study presents a comprehensive system that leverages deep learning and artificial intelligence to detect plant diseases and provide tailored treatment recommendations. The core of the system is the InceptionV3 convolutional neural network, trained on a diverse dataset of plant leaf images to accurately classify various diseases. The model training was conducted using GPU-enabled environments to ensure efficiency and accuracy. The system architecture integrates a React-based frontend and a Node.js backend, facilitating seamless user interaction and data flow. A Flask microservice is employed to handle image processing and disease prediction tasks. Upon disease identification, the system generates a dynamic prompt incorporating the disease name and environmental context, which is then sent to OpenAI's language model. The AI model responds with a structured JSON containing personalized treatment protocols, preventive measures, and maintenance strategies. Extensive testing of the system demonstrated a disease classification accuracy of 91%. The integration of AI-driven treatment recommendations offers a significant advancement in precision agriculture, enabling farmers to make informed decisions and implement effective disease management strategies. This approach not only enhances crop health and yield but also contributes to sustainable farming practices by reducing reliance on broad-spectrum pesticides.

Keywords: Deep Learning, InceptionV3, Plant Disease Detection, Precision Agriculture, AI Treatment Protocols, Farm Management