Proactive Soybean Disease Detection through YOLO Leaf Extraction and ResNet-50 Classification to Reduce Crop Loss and Boost Productivity

Abstract

Agriculture contributes 18% to India's GDP, with soybean production at 14 million metric tons annually, making it a major crop for farmers, though the sector's share is decreasing. Bacterial, fungal, and viral diseases, along with nematode infestations, can affect soybeans throughout the growing season. Accurate disease identification and appropriate treatment improve soybean production by stopping the spread of infections, reducing crop loss, enhancing plant health, boosting yields, and providing better economic benefits for farmers. The fifty different soybean farms in Maharashtra were surveyed to construct a dataset on the major diseases affecting the soybean crop. The collected images are preprocessed through resizing for uniformity, data augmentation for diversity, and normalization to scale pixel values, facilitating efficient training. The collected dataset is used to train several deep learning algorithms, such as AlexNet, VGG-16, Inception-v3, EfficientNetV2B0, and ResNet-50, to predict diseases. To evaluate the model's effectiveness, the study analyzed the training and validation loss and accuracy. The real-time soybean plant images were utilized, and YOLO was employed for leaf extraction, generating test images that were then fed into the trained models. The outcomes show that ResNet-50 predicts soybean conditions from the captured pictures from the soybean farm more effectively than cutting-edge methods. Performance metrics for classification were calculated for each model, with ResNet-50 yielding the most accurate predictions across all metrics. A confusion matrix was also generated to assess the model's classification accuracy, further confirming ResNet-50’s robustness. These results suggest that deep learning models, especially ResNet-50, can serve as effective tools for early and accurate detection of soybean diseases, offering valuable support for precision agriculture.

Plant phenotyping relevance

大豆葉画像から病害状態を抽出・分類するYOLOおよび深層学習ワークフローが研究の中心であり、植物病害表現型の画像ベース推定を評価している。

Code and data availability

The supplied blocks describe a self-collected soybean disease image dataset (5,600 images from Maharashtra farms) and model training, but contain no public deposit, availability statement, or URL for the dataset, images, code, or trained models. No paper-specific public asset is actionable.

No evidence-backed public reproduction asset is currently recorded.