A robust AI-driven system has been developed for the early detection and prediction of fungal diseases in various plants, addressing a key challenge in precision agriculture. High-resolution leaf images are analyzed using Convolutional Neural Networks (CNNs) to identify disease symptoms with high accuracy. Two leading CNN architectures, ResNet and AlexNet, were tested on a diverse dataset covering multiple climates and disease types, with AlexNet achieving a 94.72% accuracy. The results highlight the system's potential to provide farmers with timely insights, enabling rapid intervention to minimize crop losses. By facilitating proactive disease detection, this tool contributes to sustainable agriculture and a more resilient food supply chain

Artificial Intelligence, Plant Disease Detection, Deep Learning, Convolutional Neural Networks, Agricultural Innovation

This study introduced a Plant Disease Prediction System using Convolutional Neural Networks (CNNs) to detect plant leaf diseases with high accuracy. Through a comparative analysis of ResNet and AlexNet architectures, the system achieved 94.72% accuracy with AlexNet, demonstrating its effectiveness in disease identification. The proposed approach empowers farmers with early disease detection, enabling timely interventions to minimize crop losses and promote sustainable agricultural practices. This new approach will focus on Fine-tuning model parameters and using data Augmentation to address existing challenges. The Review highlights that current algorithm often Slow accuracy, emphasizing the importance of continuous improvement. By solving these Issues, a new CNN model could greatly enhance the early detection of apple leaf diseases and Assist farmers in managing their crops more Effectively. This gap in research motivates us to Create a deep learning model for detecting apple Leaf diseases. For future improvements, we aim to: Develop a treatment recommendation system to provide tailored advice on fertilizers and disease control measures. Expand the model’s scope to cover a broader range of plant diseases beyond cultivation. Enhance real-time monitoring by integrating IoT-based sensors for continuous disease tracking. Optimize model efficiency for deployment in resource-constrained agricultural environments

-