Deep learning-based quantification of tall fescue abundance in pastures

Accurate and rapid measurement of tall fescue abundance is essential for efficient forage management and mitigating livestock exposure to potential endophyte-related toxicity. Traditional visual estimation methods are labor-intensive and are subject to change depending on the observer doing the calculations, which limits their scalability and consistency. This study explores the application of deep learning techniques to automate and improve the classification of tall fescue abundance across pasture systems in Kentucky. Ground-truth abundance classes were evaluated using one of the traditional methods with occupancy grid and compared against estimates derived from red-green-blue images. Two convolutional neural network architectures, YouOnlyLookOnce (YOLO) and ResNet were employed for image-based classification. Among the models tested, YOLOv8x achieved a classification accuracy of 96% across three abundance classes, effectively distinguishing tall fescue from other vegetation and bare soil. Results demonstrated the potential of artificial intelligence in detecting spatial distribution of tall fescue, thereby supporting risk assessment of toxicity. Compared to the traditional methods, the deep learning approach improves efficiency and reduces manual labor efforts while maintaining highly accurate prediction performance for continuous monitoring applications.