Machine learning (ML) algorithms have shown potential in automatically detecting and measuring stomata. However, ML algorithms require substantial data to efficiently train and optimize models, but their potential is restricted by the limited availability and quality of stomatal images. To overcome this obstacle, we have compiled a collection of around 11,000 unique images of temperate broadleaf angiosperm tree leaf stomata from various projects conducted between 2015 and 2022. The dataset includes over 7,000 images of 17 commonly encountered hardwood species, such as oak, maple, ash, elm, and hickory, and over 3,000 images of 55 genotypes from seven Populus taxa. Inner_guard_cell_walls and whole_stomata (stomatal aperture and guard cells) were labeled and had a corresponding YOLO label file that can be converted into other annotation formats. With the use of our dataset, users can (1) employ state-of-the-art machine learning models to identify, count, and quantify leaf stomata; (2) explore the diverse range of stomatal characteristics across different types of hardwood trees; and (3) develop new indices for measuring stomata.

Automated guard cell detection and measurement are vital for understanding plant physiological performance and ecological functioning in global water and carbon cycles. Most current methods for measuring guard cells and stomata are laborious, time-consuming, prone to bias, and limited in scale. We developed StoManager1, a high-throughput tool utilizing geometrical, mathematical algorithms, and convolutional neural networks to automatically detect, count, and measure over 30 guard cell and stomatal metrics, including guard cell and stomatal area, length, width, stomatal aperture area/guard cell area, orientation, stomatal evenness, divergence, and aggregation index. Combined with leaf functional traits, some of these StoManager1-measured guard cell and stomatal metrics explained 90% and 82% of tree biomass and intrinsic water use efficiency (iWUE) variances in hardwoods, making them substantial factors in leaf physiology and tree growth. StoManager1 demonstrated exceptional precision and recall (mAP@0.5 over 0.96), effectively capturing diverse stomatal properties across over 100 species. StoManager1 facilitates the automation of measuring leaf stomatal and guard cells, enabling broader exploration of stomatal control in plant growth and adaptation to environmental stress and climate change. This has implications for global gross primary productivity (GPP) modeling and estimation, as integrating stomatal metrics can enhance predictions of plant growth and resource usage worldwide. Easily accessible open-source code and standalone Windows executable applications are available on a GitHub repository (https://github.com/JiaxinWang123/StoManager1) and Zenodo (https://doi.org/10.5281/zenodo.7686022).

StomaVision is an automated tool designed for high-throughput detection and measurement of stomatal traits, such as stomatal number, pore size, and closure rate. It provides insights into plant responses to environmental cues, streamlining the analysis of micrographs from field-grown plants across various species, including monocots and dicots.

The stomata on the leaf surface are mainly responsible for the material exchange between the internal and external environments of the plant, a large number of methods have been proposed to automatically measure the distribution position and number of stomatal, but few methods could achieve both stomatal count and open/closed-state judgment. Therefore, this study proposes an automatic detection method for leaf stomatal morphology analysis based on an attention mechanism and deep learning. In order to obtain more stomatal feature information and send it to the network for learning, the proposed method adds a coordinate attention (CA) mechanism to the YOLOV5 backbone part. At the same time, in order to avoid the overfitting of the model during the training process, the authors added the training trick of label smoothing. Finally, the detection ability of the proposed method for stomata is verified on the broad bean leaves stomata dataset. The experimental results show that our method achieves a detection accuracy of 0.934 and an mAP of 0.968. By comparing with other state-of-the-art algorithms, the detection capability of our method has been significantly improved. The generalization of the model is verified on the wheat leaf stomatal dataset. The experimental results show that our method can achieve a detection accuracy of 0.894 and an mAP of 0.907.

Main conclusion: This study developed the reliable Mask R-CNN model to detect stomata in Lonicera caerulea. The obtained data could be utilized for evaluating some characters such as stomatal number and aperture area. Abstract: The native distribution of haskap (Lonicera caerulea L.), a small-shrub species, extends through Northern Eurasia, Japan, and North America. Stomatal observation is important for plant research to evaluate the physiological status and to investigate the effect of ploidy levels on phenotypes. However, manual annotation of stomata using microscope software or ImageJ is time consuming. Therefore, an efficient method to phenotype stomata is needed. In this study, we used the Mask Regional Convolutional Neural Network (Mask R-CNN), a deep learning model, to analyze the stomata of haskap efficiently and accurately. We analyzed haskap plants (dwarf and giant phenotypes) with the same ploidy but different phenotypes, including leaf area, stomatal aperture area, stomatal density, and total number of stomata. The R-square value of the estimated stomatal aperture area was 0.92 and 0.93 for the dwarf and giant plants, respectively. The R-square value of the estimated stomatal number was 0.99 and 0.98 for the two phenotypes. The results showed that the measurements obtained using the models were as accurate as the manual measurements. Statistical analysis revealed that the stomatal density of the dwarf plants was higher than that of the giant plants, but the maximum stomatal aperture area, average stomatal aperture area, total number of stomata, and average leaf area were lower than those of the giant plants. A high-precision, rapid, and large-scale detection method was developed by training the Mask R-CNN model. This model can help save time and increase the volume of data.

Stomatal traits of leaves are critical for regulating the exchange of gases between plant tissues and the atmosphere, and thus play a crucial role in the physiological activities of plants. The hypothesis of this study is that distinct stomatal features among different species grown in diverse habitats can serve as a potential marker for species identification. Leaf samples were collected from the mangrove forests of Sundarbans and the freshwater swamp forests of Ratargul in Bangladesh. In total, we examined 11 species from eight different families. We used deep convolutional neural network (DCNN) to automatically identify tree species from microscopic stomatal imprints, as there is currently no established protocol for this task. For model training, 80% (866 images) of the data was used for training the models. Our study observed significant variations in stomatal attributes such as length, width, and density among different species, families, and habitats. These variations could help in accurate species identification by machine learning approaches used in the present study. An empirical comparison was conducted among EfficientNetV2, Xception, VGG16, VGG19, MobileNetV2, ResNet50V2, Resnet152, DenseNet201, and NasNetLarge. We propose a novel approach called the “Normalized Leverage Factor” that utilizes accuracy, precision, recall, and f1-score to select the optimal model. This approach eliminates the non-uniformity of the scores. Although MobileNetV2 achieved an accuracy of 99.06%, our findings indicate that EfficientNetV2 is the optimal model for species identification. This is due to its higher normalized leverage factor (1.92) compared to MobileNetV2 (1.88). The findings demonstrate that plants of diverse habitats show a unique footprint of stomata that offers an innovative method of species identification using DCNN. The study would help to develop a stomatal image-based user interface to identify species even without expert taxonomic knowledge and could be particularly useful in fields such as pharmacology, conservation biology, forestry, and environmental science.

The quantification of stomatal pore size has long been a fundamental approach to understand the physiological response of plants in the context of environmental adaptation. Automation of such methodologies not only alleviates human labor and bias but also realizes new experimental research methods through massive analysis. Here, we present an image analysis pipeline that automatically quantifies stomatal aperture of Arabidopsis thaliana leaves from bright-field microscopy images containing mesophyll tissue as noisy backgrounds. By combining a You Only Look Once X–based stomatal detection submodule and a U-Net-based pore segmentation submodule, we achieved a mean average precision with an intersection of union (IoU) threshold of 50% value of 0.875 (stomata detection performance) and an IoU of 0.745 (pore segmentation performance) against images of leaf discs taken with a bright-field microscope. Moreover, we designed a portable imaging device that allows easy acquisition of stomatal images from detached/undetached intact leaves on-site. We demonstrated that this device in combination with fine-tuned models of the pipeline we generated here provides robust measurements that can substitute for manual measurement of stomatal responses against pathogen inoculation. Utilization of our hardware and pipeline for automated stomatal aperture measurements is expected to accelerate research on stomatal biology of model dicots.

Background: Stomata are tiny pores on the leaf surface that are central to gas exchange. Stomatal number, size and aperture are key determinants of plant transpiration and photosynthesis, and variation in these traits can affect plant growth and productivity. Current methods to screen for stomatal phenotypes are tedious and not high throughput. This impedes research on stomatal biology and hinders efforts to develop resilient crops with optimised stomatal patterning. We have developed a rapid non-destructive method to phenotype stomatal traits in three crop species: wheat, rice and tomato. Results: The method consists of two steps. The first is the non-destructive capture of images of the leaf surface from plants in their growing environment using a handheld microscope; a process that only takes a few seconds compared to minutes for other methods. The second is to analyse stomatal features using a machine learning model that automatically detects, counts and measures stomatal number, size and aperture. The accuracy of the machine learning model in detecting stomata ranged from 88 to 99%, depending on the species, with a high correlation between measures of number, size and aperture using the machine learning models and by measuring them manually. The rapid method was applied to quickly identify contrasting stomatal phenotypes. Conclusions: We developed a method that combines rapid non-destructive imaging of leaf surfaces with automated image analysis. The method provides accurate data on stomatal features while significantly reducing time for data acquisition and analysis. It can be readily used to phenotype stomata in large populations in the field and in controlled environments.

Stomata act as a pathway for air and water vapor during respiration, transpiration and other gas metabolism, so the stomata phenotype is important for plant growth and development. Intelligent detection of high throughput stoma is a key issue. However, current existing methods usually suffer from detection error or cumbersome operations when facing densely and unevenly arranged stomata. The proposed RotatedStomataNet innovatively regards stomata detection as rotated object detection, enabling an end-to-end, real-time and intelligent phenotype analysis of stomata and apertures. The system is constructed based on the Arabidopsis and maize stomatal data sets acquired in a destructive way, and the maize stomatal data set acquired in a nondestructive way, enabling one-stop automatic collection of phenotypic such as the location, density, length and width of stomata and apertures without step-by-step operations. The accuracy of this system to acquire stomata and apertures has been well demonstrated in monocotyledon and dicotyledon, such as Arabidopsis, soybean, wheat, and maize. And the experimental results showed that the prediction results of the method are consistent with those of manual labeled. The test sets, system code, and its usage are also given (https://github.com/AITAhenu/RotatedStomataNet).

Stomata play an essential role in regulating water and carbon dioxide levels in plant leaves... (truncated for brevity)