Crop Disease Prediction Using Deep Learning Algorithm

Plant diseases pose a significant threat to global agricultural productivity, particularly affecting key crops like tomato and potato. Traditional disease detection methods are often slow, subjective, and labour-intensive, leading to delayed responses and increased crop losses. This study proposes a hybrid machine learning framework that integrates ResNet9 for classification and U-Net for segmentation to detect and localize leaf diseases in tomato and potato plants. A comprehensive dataset of over 22,500 images spanning 13 classes, including healthy and diseased samples, was compiled from multiple sources and preprocessed using image normalization, histogram equalization, and data augmentation techniques. The model was trained using a 70:20:10 data split and optimized through early stopping and cyclic learning rates. Evaluation metrics including accuracy, precision, recall, F1-score, and ROC-AUC were used to assess performance, with the proposed model achieving a remarkable accuracy of 96.3%, F1-score of 95.2%, and ROC-AUC of 97.1%. The use of U-Net enabled accurate segmentation of infected regions, improving model interpretability and trustworthiness. Confusion matrix analysis revealed minimal misclassifications, and visual tools such as saliency maps confirmed the model’s attention to disease-prone areas. Real-world testing demonstrated the system’s robustness across different environments and lighting conditions. Comparative results showed superior performance of the hybrid model over VGG16, EfficientNet-B0, and baseline CNNs in both accuracy and inference speed. This approach offers a scalable, real-time solution for automated plant disease detection and diagnosis, particularly suited for use in resource-constrained agricultural settings. The hybrid model not only supports early intervention and precision agriculture practices but also bridges the gap between advanced machine learning and practical farming needs.