In our iGEM project, we developed a robust AI-based system to detect red rot disease in sugarcane using a combination of advanced deep learning and machine learning models. The primary goal was to create a scalable solution that could be deployed in agricultural environments to help farmers identify red rot disease at an early stage, enabling timely intervention to reduce crop losses. This project highlights how cutting-edge AI techniques can transform agricultural practices, particularly in disease detection and crop management

We collected a dataset of approximately 800-1000 images of sugarcane plants, encompassing both healthy and red rot-infected plants. The images were sourced from multiple agricultural databases and field surveys, covering a variety of environmental conditions and geographic regions. Expert agricultural professionals labeled each image to ensure that disease identification was precise, providing accurate annotations of red rot disease at different stages.

To improve the generalization of our models and compensate for the relatively small dataset, we applied extensive data augmentation. This increased the dataset size to over 8000 images and added variation to the training data, making the models more robust. Augmentation techniques included: Rotation: Random rotations between -40 and +40 degrees to simulate various orientations of plants in the field. Flipping: Horizontal and vertical flips to mimic different plant orientations. Brightness and Contrast Adjustments: Adjusting brightness levels within ±20% to simulate various lighting conditions during data collection. Zoom and Cropping: Introducing random zooms and cropping to simulate differing distances between the camera and plants. Random Noise Injection: Adding small levels of Gaussian noise to simulate real world image imperfections.

Contribution:
Our pipeline involved training several deep learning models, including EfficientNet, ResNet-152, VGG16, and Vision Transformers, as well as a Hybrid CNN + Random Forest model. The pipeline was designed to compare the performance of these architectures on the red rot detection task and identify the most efficient and accurate models for real-world deployment.

1.Hybrid CNN + Random Forest Model • Why Chosen: The hybrid model combined the feature extraction capabilities of Convolutional Neural Networks (CNNs) with the robust classification of Random Forests, aiming to leverage the strengths of both deep learning and traditional machine learning. Results: Test Accuracy: 96.15%, F1 Score: 96.11%. 2.EfficientNet Model • Why Chosen: EfficientNet was selected for its ability to scale network depth, width, and resolution efficiently, providing a good balance between model complexity and computational resources. • Results: Best Validation Accuracy: 99.88%, Test Accuracy: 99.88%, Precision: 100.00%, Recall: 99.76%, F1 Score: 99.88%. 3.ResNet-152 Model • Why Chosen: ResNet-152 was chosen for its depth and use of residual connections, which help mitigate the vanishing gradient problem in deep neural networks, allowing the model to learn more intricate features. • Results: Best Validation Accuracy: 100.00%, Test Accuracy: 99.64%, Precision: 99.53%, Recall: 99.77%, F1 Score: 99.65%. 4.VGG16 Model • Why Chosen: VGG16 was included for comparative analysis due to its historical significance in image recognition tasks. • Results: Best Validation Accuracy: 99.16%, Test Accuracy: 99.16%, Precision: 99.76%, Recall: 98.59%, F1 Score: 99.18%. 5.Vision Transformers Model • Why Chosen: Vision Transformers (ViT) were explored to leverage self-attention mechanisms, potentially capturing global image features more effectively than CNNs. • Results: Best Validation Accuracy: 97.71%, Test Accuracy: 96.51%, Precision: 96.73%, Recall: 96.01%, F1 Score: 96.37%

To assess the performance of the models, we used the following metrics: Accuracy: The percentage of correctly classified images. Precision: The ratio of true positive predictions to the total number of positive predictions. Recall (True Positive Rate): The percentage of actual positive cases (diseased plants) correctly identified by the model. F1 Score: The harmonic mean of precision and recall, balancing these two metrics. ROC Curve & AUC: The ROC curve evaluated the trade-offs between the true positive rate and false positive rate. Confusion Matrix: A confusion matrix provided detailed insights into model misclassifications.

These protocols provide a comprehensive approach to building an AI-based system for red rot disease detection in sugarcane. By following these steps, we were able to develop models that generalize well across different environmental conditions and disease stages. Our protocols ensure that this system can be replicated and scaled for use in other agricultural settings.

Model	Test Accuracy	Precision	Recall	F1 Score
EfficientNet	99.64%	99.53%	99.77%	99.65%
ResNet-152	99.88%	100.00%	99.76%	99.88%
Hybrid CNN + RF	96.15%	N/A	N/A	96.11%
VGG16	99.16%	99.76%	98.59%	99.18%
Vision Transformers	96.51%	96.73%	96.01%	96.37%

1. The ResNet-152 model Results: - Best Validation Accuracy: 99.88% - Test Accuracy: 99.88% - Precision: 100.00% - Recall: 99.76% - F1 Score: 99.88% .It delivered the best overall performance, achieving a perfect validation accuracy and near-perfect test accuracy. Its depth and use of residual connections allowed it to capture complex features, making it highly effective at distinguishing between healthy and diseased sugarcane plants.

2. EfficientNet Model Analysis: EfficientNet proved to be a highly accurate model, excelling in both precision and F1 score. Its ability to scale network depth, width, and resolution efficiently contributed to its high performance.

3. Hybrid CNN + Random Forest Model Results: - Test Accuracy: 96.15% - F1 Score: 96.11%

4. VGG16 Model Results: - Best Validation Accuracy: 99.16% - Test Accuracy: 99.16% - Precision: 99.76% - Recall: 98.59% - F1 Score: 99.18%

5. Vision Transformers Model Results: - Best Validation Accuracy: 97.71% - Test Accuracy: 96.51% - Precision: 96.73% - Recall: 96.01% - F1 Score: 96.37%

Based on the performance metrics and analysis, ResNet-152 and EfficientNet emerged as the most suitable models for deployment in real-world agricultural settings. These models demonstrated exceptional accuracy and precision, making them highly reliable for detecting red rot disease in sugarcane. The ResNet-152 model is recommended for deployment due to its ability to generalize well across varying disease stages, while EfficientNet offers an efficient alternative for scenarios where computational resources are limited