Published Paper Details:

This research addresses the challenge of leaf diseases in plants, which significantly affect global agriculture by reducing crop yield, quality, and food security. The study introduces an innovative method that integrates Convolutional Neural Networks (CNNs) for predicting leaf diseases with recommendations for preventative practices and fertilizer application. A diverse dataset of images, featuring both healthy and diseased leaves, is collected and processed for analysis using a custom-designed CNN model. This model is trained to accurately identify and predict leaf diseases. Additionally, the study offers recommendations for disease prevention, including cultural practices, biological controls, and chemical treatments, tailored to specific diseases and environmental conditions. The research also provides customized fertilizer strategies aimed at enhancing plant immunity and resilience against diseases. Experimental results show the CNN model's effectiveness in disease prediction, while the combined approach of preventative measures and tailored fertilizer use is intended to lower the incidence and severity of diseases. This comprehensive approach supports sustainable agriculture by providing farmers with tools for proactive disease management and promoting resilient crop production systems.