Ai-Powered Crop Yield and Health Monitoring System

Monitoring plant health is essential to sustainable agriculture since it allows for prompt action to increase crop yield and reduce losses. This research uses cutting-edge ML & DL approaches to identify, categorise, and forecast plant health in an AI-driven manner. Crop yield prediction, crop health identification/classification, and crop health prediction are the three interconnected modules that make up the framework. To precisely detect and categorise plant health issues, a logistic regression classifier is used in conjunction with a pretrained ResNet-50 model for feature extraction. To guarantee dependability in a variety of settings, the system is trained on a carefully selected dataset using strong preprocessing and data augmentation techniques. Evaluation criteria that show how well the model identifies plant health states. Furthermore, visualisation techniques like feature map analysis offer interpretability into the model's decision-making process. The initiative promotes precision agriculture and sustainable farming methods by providing a scalable solution for real-time plant health monitoring. In the future, the system will be expanded to include a wider range of crops and weather circumstances, and models for edge deployment will be improved.