Deep Transfer Learning with MobileNetV2 for Automated Classification of Healthy and Diseased Rice Plant Leaves

India is one of the leading productions of Paddy. Compared to previous year Gross Domestic Product (GDP) Export rate of Paddy in the year 2021 has increased to around 33%. Paddy is the Major food production crop in India. Every crop is prone to many diseases throughout their lifespan. The disease can affect the crop at any stage of their growing phase. Early detection of disease is the only solution to reduce the damage. Early detection of plant diseases is vital for sustainable agriculture. In this study, we propose a deep learning–based approach for classifying healthy and diseased rice leaves using MobileNetV2 with transfer learning. A dataset of 2,314 rice leaf images (2,126 for training, 188 for testing) was used. Data augmentation and class weighting techniques were applied to address dataset imbalance. The proposed model achieved 96% accuracy, 0.96 F1-score, and a ROC AUC of 0.996 on the test set, demonstrating strong generalization ability. These results suggest that lightweight transfer learning models such as MobileNetV2 can provide scalable and accurate disease diagnosis solutions for precision agriculture.