Automated phenotyping of soybean stomatal responses to water deficit using YOLOv8

Artificial intelligence applied to plant phenotyping is crucial for consistent results, as stomata classification under stress impacts physiology, water use efficiency, and productivity. Manual analysis is laborious and error-prone, limiting the efficiency and accuracy of evaluations. In this context, this study developed a soybean-specific dataset from water deficit (WD) and well-watered (WW) plants, training YOLOv8 model for automated detection and classification of open vs. closed stomata. Soybean plants were grown under water deficit and well-watered conditions, generating significant variations in stomatal structural opening and associated gas exchange traits. To capture stomata variations, epidermal printing techniques were employed, with images obtained by microscopy. The dataset was labeled using the intelligent polygon tool of the Roboflow application, with 269 images of the adaxial and abaxial surfaces of leaves annotated in two categories: open and closed stomata. The images underwent geometric transformations to facilitate model training. The results demonstrated that the YOLOV8 neural network achieved precision recall and mAP greater than 90%, highlighting its effectiveness in detecting and classifying stomata. By integrating automated classification of aperture states (open and closed) with a defined physiological stress context in soybean, this work establishes a dataset specifically designed for functional analysis. This approach extends the applicability of deep learning toward stress-oriented plant physiology studies, offering a robust tool for evaluating crop adaptation under climate change scenarios.