Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{207555,
        author = {BIBISUGARA PATEL and TASKEEN A MANGOLI},
        title = {DEEPCROPNET: INTELLIGENT MULTI-CROP DISEASE DETECTION AND SEVERITY ANALYSIS USING TRANSFER LEARNING},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {3},
        pages = {1586-1598},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=207555},
        abstract = {Agriculture plays a vital role in global food production and economic development; crop diseases remain a major challenge, significantly reducing crop yield and quality. Early and accurate identification of plant diseases is essential for effective disease management and to prevent large-scale agricultural losses. Traditional disease detection methods rely mainly on manual observation by farmers and agricultural experts, are time-consuming, require specialised knowledge, and may lead to incorrect diagnoses. This research presents an Intelligent Multi-Crop Disease Detection and Severity Analysis System Using Transfer Learning that applies deep learning and computer vision techniques for automatic plant disease identification. The proposed system uses a MobileNetV2-based transfer learning model to classify diseases from leaf images of multiple crops, including tomato, potato, and pepper. The framework involves image pre-processing techniques such as resizing, normalisation, and augmentation to improve model performance and generalisation. The trained model extracts important visual features from leaf images and predicts disease categories with confidence scores. In addition to disease classification, the system performs severity analysis by estimating the percentage of infected leaf area and categorising disease severity levels as mild, moderate, or severe. Weather parameters such as humidity and rainfall are incorporated to analyse disease risk conditions and provide preventive recommendations. The proposed approach integrates disease detection, severity assessment, weather-based risk prediction, and farmer alert support into a single intelligent agricultural solution. Experimental evaluation demonstrates that transfer learning improves classification accuracy while reducing computational complexity compared with traditional approaches. The developed system provides a fast and user-friendly method for early crop disease diagnosis.},
        keywords = {Deep Learning, Transfer Learning, Crop Disease Classification, MobileNetV2, Plant Leaf Analysis, Smart Agriculture, Disease Severity Prediction},
        month = {August},
        }