In this study, a lightweight Convolutional Neural Network (CNN) model called MobileNet is used to provide an effective method for plant disease identification. Traditional approaches sometimes have trouble with complicated visual backdrops and heavy processing demands, which restricts real-time deployment on mobile devices. MobileNet overcomes these obstacles by maximizing model complexity and surpassing traditional techniques to achieve an astounding 99.28% accuracy on public datasets. Even with datasets that are not balanced, the model's use of deep transfer learning allows for reliable categorization. In-depth methods for data preparation and augmentation further improve the model's resilience. As a web application, MobileNet offers easily accessible, real-time disease detection, assisting farmers with crop management and prompt response. The sustainability and productivity of agriculture are enhanced by this effective model.