Crop Disease Prediction Using AI

This paper presents an AI solution that utilizes Convolutional Neural Networks CNNs to detect diseases in crops and flowers with the goal of improving precision and effectiveness in managing agricultural diseases. The system introduces features that fill existing gaps in disease detection. It expands its capabilities to include flowers often overlooked by systems thereby benefiting both the crop and flower farming sectors. Moreover it provides organic treatment suggestions for detected diseases promoting sustainable farming practices. A noteworthy component of the system is a web platform tailored, for farmers that streamlines access to disease predictions and organic treatments. This user friendly platform includes educational video tutorials to assist farmers in navigating its functions. User security is upheld through the implementation of JSON Web Tokens JWT ensuring access for each individual user. Additionally the incorporation of a weather API enhances the models performance by factoring in real time weather conditions to improve disease prediction accuracy. The findings from the experiments underscore how well the CNN model performs showing accuracy in predicting diseases in crops and flowers. Moreover real world examples illustrate the advantages of offering organic remedies suited to various ailments. With a user friendly and secure platform for accessing these technologies this system assists farmers in effectively handling crop and flower diseases fostering sustainable agriculture practices and playing a role in shaping AI advancements, in the farming sector.