This research aims to estimate a plant’s water stress using advanced deep-learning techniques and stomata micrographs. Over 100 microscopic im ages of Oryza sativa (rice) were captured and annotated with open and closed stomata as part of the dataset. The images were captured under an optical lens with 40x zoom. Standard preprocessing steps such as image resizing and gray scaling were performed to enhance model performance and reduce complexity. The YOLOv8 model was then trained over 600 epochs resulting in an accuracy of 92% in stomata detection and classification. The study can facilitate the currently manual and time-consuming process of stomata annotation. Further research is necessary to generalize the model for different stomata shapes. Integrat ing this technology into IoT networks can help reduce inefficiencies in water management in agriculture.