Advanced Deep Learning Approaches: Utilizing VGG16, VGG19, and ResNet Architectures for Enhanced Grapevine Disease Detection
Bibliographic record
Abstract
This study aims to give an overall comparison among three of the most powerful convolutional neural network (CNN) architectures-VGG16, VGG19, and ResNet for the classification of leaf diseases, particularly targeting leaf blight, ESCA, black rot, and healthy leaves. With the consequent economic effects of these diseases on viticulture, it is essential to create precise, productive, and scalable diagnostic tools for the pursuit of sustainable agricultural practices. Using a very large dataset of grapevine leaf images acquired from different localities, this study investigates the ability of the models to correctly assign the diseases to the visual symptoms. The models were assessed through a rigorous evaluation process including data preprocessing, augmentation, and stratified k-fold cross-validation approach to determine the overall accuracy, precision, recall, and F1 score. The study results reflect no doubt that the ResNet model surpasses its rivals with an outstanding accuracy of 95% which is followed by VGG19 with 93.5% and VGG16 with 92%. These observations emphasize the power of deep residual learning and the importance of architecture depth in ensuring the accuracy of CNNs in the field of plant disease classification tasks. In addition, the study underlines the need for having holistic and varied datasets that train models to generalize across different environments and disease presentations. The current research adds to the growing knowledge base on the use of deep learning (DL) in agriculture, thus providing insight into the most efficient CNN networks that can be used for grapevine disease recognition. This work contributes to the integration of AI-based diagnostic tools in precision agriculture; this will eventually help improve the current disease management practices and foster sustainable crop production systems.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".