Object detection algorithms have heavily relied on deep learning techniques to estimate the count of grapes as the resulting quality of grapes is directly correlated to its yield. With temporal analytics, early actions and logistical organizing can be performed to maintain the quality of grapes. However, the issue with using these object detection algorithms is that they are limited to counting only the visible grapes, thus omitting hidden grapes, and in turn affecting the true estimate of grape yield. Many grapes are occluded because of either the compactness of the bunch cluster, or due to canopy interference. Therefore, models need to be able to estimate the unseen berries in order to give a near true yield estimate. An end-to-end framework is proposed in which the grape clusters are first segmented using a deep learning model, after which the extracted candidate regions of grape clusters are fed to a CNN regression model that can estimate the count of berries by incorporating a correction factor. A new dataset is also proposed which consists imagery of grape clusters, along with their ground truth values of grape count and weight. The proposed framework will also be tested using three open-source datasets and will encourage future research in determining which features of grapes can be leveraged to correct grape counting algorithms and produce higher accurate results.

A document by Mao Li. Click on the document to view its contents.

Smart glasses are a rapidly emerging mobile data platform, which can be operated in a hands-free manner through voice commands, a heads-up display and a range of sensors and other digital features. As such, smart glasses enable crop scientists, horticulturalists and agronomists to capture, send and receive digital information, while leaving their hands free to carry out accompanying hands-on tasks or plant manipulations. Phenotypic data increasingly drives agricultural and horticultural development and breeding pipeline discovery. Real-world use cases from innovative agriculture and horticulture technology companies, such as Bayer Crop Science, demonstrate how smart glasses are: 1. serving as a digital phenotyping platform that complements established phenotyping platforms; 2. significantly increases efficiency in phenotypic data collection; 3. facilitate remote collaborations on experiments and other agronomic activities. Smart glass technology integrates easily into existing apps extending capabilities and workflows.

A document by Jose C. Tovar. Click on the document to view its contents.

Texas A&M University recently completed a set of Automated Precision Phenotyping (APP) Greenhouses that incorporate robotic systems for automated collection of advanced sensor-based plant phenotypes. Transiting the length of a greenhouse is a gantry beam, on which a rolling truck provides a second axis of motion along the gantry. Attached to the truck is a 3.0-m long robotic arm that is controlled to position a sensor head at virtually any position relative to any plant in a greenhouse. The robotic arm can be programmed to operate quickly and safely in complicated scanning patterns to enable data collection on all plants in the greenhouse within a time window of a few hours, ensuring consistent conditions during data collection. The sensor head includes a high-speed multispectral camera and eventually a Raman spectrometer. Relative to phenotyping greenhouses at other institutions, the APP Greenhouses have the advantage of maximum flexibility in configuration of plants in the greenhouses, in positioning of sensors relative to the plants, and in the types of sensors used, making research capabilities in the APP Greenhouses truly unique. Preliminary data have been collected on sorghum and maize plants. Four-band multispectral images have been collected daily, scanning the side of each plant from top to bottom. Preliminary software development is directed at automated image stitching to create a full side-view image of each plant, from which consistent metrics can be automatically calculated, such as plant height, stalk diameter, leaf angle, etc.

Mung bean (Vigna radiata (L.) Wilczek) is an important crop providing protein, fiber, carbohydrates, and minerals in Southeast Asia and Africa. Trifoliate leaves in mung beans are central to several plant processes like photosynthesis, light interception, early disease & pest warning signals, and overall canopy architecture. We sampled more than 5000 leaf images of the Iowa Mung bean diversity panel (IMDP) during the 2020 and 2021 growing seasons in a Randomized Complete Block Design. We recorded the phenotypic diversity, developed a regression model for the oval leaflet type, and conducted GWAS for the image extracted traits. The diversity in the morphology included leaflet type (oval or lobed), leaflet size (small, medium, large), lobed angle (shallow, deep), and vein coloration (green, purple). A universal regression model LA = b0 + b1L + b2W + b3L*W was the best at predicting the area of each ovate leaflet with an adjusted R2 of 0.97. The candidate genes Vradi01g07560, Vradi05g01240, Vradi02g05730, and Vradi03g00440 are associated with multiple traits (length, width, perimeter, and area) across the leaflets (left, terminal, and right) and would be suitable candidates for further investigation in their role in leaf development, growth, and function. Future studies will be needed to correlate the observed traits discussed here with yield or important agronomic traits for use as phenotypic or genotypic markers in marker-aided selection methods for mung bean crop improvement.

Plant height is a critical indicator for monitoring plant growth status and productivity estimation. Accurate measurement of plant height through a high-throughput manner is crucial for precision agriculture and field-based plant phenotyping. Manually measuring plant height is time-consuming and labor-intensive, and it only provides the height information at each sampling point but cannot tell the detailed within-field spatial variations. LiDAR and digital imagery-based photogrammetry have been increasingly used in plant phenotyping in recent years thanks to the developments in Unmanned Aerial Vehicle (UAV) and sensor technology. LiDAR point clouds can be directly used for plant height extraction, digital imagery-based photogrammetric point clouds can also be used for derivation plant height. The goal of this study is to investigate the potential of UAV LiDAR and digital photogrammetry in measuring plant height of different crops at multiple growth stages. To this end, a high resolution 32 channel LiDAR and digital cameras mounted on DJI Matrice 600 Pro UAV were employed to collect data from agricultural fields in Missouri, USA. Canopy Surface Models (CSM) and Digital Terrian Models (DTM) are generated from LiDAR and digital Photogrammetry point clouds, respectively, then plant height is derived by subtracting DTM from CSM, the UAV-based plant height is compared against manually measured height to evaluate the accuracy and performance of LiDAR and digital photogrammetry technologies. This study proved that UAV-based LiDAR and digital photogrammetry are important tools in sustainable field management and high-throughput phenotyping.

Volume is an important phenotype and quality attribute of sweetpotato storage roots. Conventionally the volume of most agricultural products is measured by water displacement. This method, which requires submerging the products in a container of water and measuring the displacement of water in the container, is time-consuming and tedious. It would be beneficial for sweetpotato breeding programs and quality inspection if a rapid method is developed for measuring the volume of sweetpotatoes. This study is therefore to evaluate the feasibility of LiDAR (light detection and ranging) technology as a novel high-throughput approach to phenotyping and measurement of the volume of sweetpotatoes. LiDAR data will be acquired from sweetpotato storage roots using a consumer-grade sensor, Intel® RealSense™ L515, which is an RGB-D (red-green-blue-depth) camera. Ground-truth volume values will be obtained using the reference water displacement method. RGB images will be used to segment sweetpotatoes from background, and extract meaningful features (e.g., the major axis length and the center of mass), complement the point cloud data from depth images for volume estimation. The shape of the sweetpotatoes will be constructed by a series of three-dimensional coordinate points, the alpha shape method is to be used to envelop the boundary points of sweetpotatoes to obtain a non-convex body, and thereby the volume of the sweet potato will be calculated. The efficacy of the proposed method will be evaluated in terms of volume estimation accuracy.

Reliable and accurate method to phenotype disease incidence and severity is essential to unravel the complex genetic architecture of disease resistance in plants, and to develop disease resistant varieties. Genome-wide association studies (GWAS) involve phenotyping large numbers of accessions phenotyped across multiple environments and replications, which takes a significant amount of labor and resources. Machine learning (ML) methods are becoming more routine for phenotyping traits to save time and effort. This research aims to conduct GWAS on sudden death syndrome (SDS) of soybean [Glycine max L. (Merr.)]. This study uses disease severity from both visual field ratings and ML-based (using images) severity ratings collected from 473 accessions. Images were processed through an ML framework that identified soybean leaflets with SDS symptoms, and then disease severity was quantified on those leaflets into few classes. Both visual field ratings and image-based ratings identified significant single nucleotide polymorphism (SNP) markers associated with disease resistance. These significant SNP markers are either in the proximity of previously reported candidate genes for SDS, such as ss715584164 and ss715610404, or near the potentially novel candidate genes, such as ss715583703 and ss715615734. Within previously reported SDS quantitative trait loci there were significant SNPs from both visual rating and image-based ratings. The results of this study provide an exciting avenue for using ML to capture complex phenotypic traits from images to get comparable or more insightful results compared to subjective visual field stress phenotyping.

Pores in the leaf epidermis called stomata allow plants to take up carbon dioxide for photosynthesis, but are also pathways for water vapor loss. New image acquisition and analysis methods are allowing high-throughput phenotyping of stomatal patterning, which can be applied to better understand the genetic basis of variation in certain species. However, it takes considerable data and effort to train the models and their ability to accurately detect epidermal structures is constrained by the training data. This issue of context dependency, the inability to perform effectively in novel contexts, is the main hurdle preventing widespread adoption of machine learning in high-throughput phenotyping of intraspecific, interspecific, and environmental variation. Here we show the limited ability of a Mask-RCNN tool trained and successfully applied to Zea mays, to analyze images from a closely related grass called Setaria viridis. We then demonstrate successful retraining of the tool to cope with the novel amounts of diversity presented by this new species. The stomatal complexes in optical tomography images of mature Setaria leaves were accurately identified by comparison to expert raters (R 2 = 0.84). This study highlights the challenge of context dependency for widespread application of machine learning tools for phenotyping plant traits, even in closely related species. At the same time, it also provides a new tool that can be applied to leverage Setaria as a model C4 species, and a roadmap for the translation of a machine learning tool to analyze stomatal patterning in diverse datasets of new plant species.

ORCiD: [https://orcid.org/0000-0003-0655-2343] Increasing weather variability is affecting the overall productivity of agriculture. In this scenario, current crop improvement science is essential to improve productivity while retaining the quality of plant products. There has long been an interest in using process-based modeling to examine the interaction between environment and genotype. The methodological challenges to better predict how various environmental conditions may impact novel genotypes and it has been a fundamental barrier to model parameterization. Thus, a phenotypic campaign was conducted to collect a comprehensive physiological dataset from a panel of 25 genotypes (including both breeder panel and diversity panel) in the summer of 2022. Additionally, an unmanned aerial vehicle (UAV) was used to gather remote sensing data. The red-green-blue (RGB) 3D point cloud, NDVI (Normalize difference vegetation Indices), and LIDAR (Light detection and ranging) were also used to identify the trait variations among the genotypes. The data is being analyzed to explain the physiological and phenotypic trait differences. The outcome of this project would help to develop a genetically informed, realistic soybean model. Finally, it will help breeders and growers in locating high-yielding cultivars for the appropriate geographical areas.

Measurement of key crop physiological traits using high resolution aerial imagery with unmanned aerial systems (UASs) holds enormous potential to increase consistency and accuracy of data collected for field evaluations. Here, we demonstrate temporal corn response to fertility treatments using repeated measurements followed by an area-under-the-curve progression analysis. Radiometrically calibrated multispectral datasets were used to calculate standard vegetative indices as well as to leverage models that approximate leaf area, nitrogen content, chlorophyll content, and canopy uniformity. In addition, digital elevation models can be employed to measure relative canopy heights and spatial variability in the field. Taken together, these digital assessments allow for a researcher to have significant insight into experiment outcomes during the growing season, including the identification of relative yield potential. This approach automates and standardizes the acquisition of key phenotypes that can be used to more efficiently evaluate field trials across multi-location programs.

In recent decades, the field of phenomics has lagged behind the advances in genomics, which have become increasingly high-throughput and low-cost. In comparison, manually collected phenotypes are often time-consuming, labor intensive, and more costly to obtain. The development of high-throughput phenotyping platforms (HTPP) are bridging these gaps and enabling improved spatial and temporal resolution for researchers. We used imagery from unoccupied aerial vehicles (UAV) flown over multiple site years in Saskatchewan and Italy to gather data for crop height, area and volume in a lentil diversity panel. We found high correlations for our UAV-derived traits (height & volume) with our manually collected phenotypes (height & biomass). In addition, the high-throughput nature of the UAV allowed for the collection of time-series data which enabled the modelling of growth curves for volume, height and area, which would be impractical under traditional phenotyping procedures given the large population grown in multiple environments. Principal component analysis and hierarchical clustering revealed differential growth strategies amongst our diverse lentil population across contrasting environments. Our study demonstrates the potential for HTPP to obtain data that traditionally require destructive sampling, e.g., volume as a proxy for vegetative biomass, and improve the temporal quality of phenotype data enabling researchers to take their analysis beyond single time points, e.g., model growth curves. In addition, performing our analysis on data from contrasting environments, i.e., Saskatchewan and Italy, has helped elucidate optimal adaptation with regard to growth strategies in lentils.

Dani C. Gafford1, Jaime Barros1

Root studies in controlled environments are typically conducted either in rhizotrons, pots, or small scale mesocosm systems, like PVC tubes or root boxes. These systems have two limitations for translating results to crop roots grown in fields. First, the size and shape of containers change the root phenotype when plants are in the mature stage. Second, often only one plant is planted per container without interaction among neighboring plants. Therefore, the root architecture observed in these isolated environments has low predictability for the root architecture in a community setting in fields. To better translate the root traits observed in a controlled environment to field observations, we developed a macro-mesocosm system (5.5 m (W) x 6.7 m (L) x 0.7 m (H)) to mimic the real field soil conditions in a greenhouse. We also installed 64 capacitance soil moisture sensors to monitor the whole macro-mesocosm system at 15.24 cm and 38.10 cm soil depths in real-time. We evaluated the phenotypic spectrum in one common bean (Phaseolus vulgaris. L) genotype, SEQ7, in a time series experiment. We grew SEQ7 for two, six, nine, and twelve weeks under sensor-controlled water-stressed and well-watered irrigation regimes. SEQ7 showed four different root architecture types across developmental stages. These four root architecture types are consistent with previous field observation. This novel macro-mesocosm system will be a great setup to study the field dynamics of the root phenotypic spectrum in a controlled environment.

Stomata are the microscopic pores on plant leaves that open or close to regulate the flux of water from leaves. Guard cells of stomata are known to react to environmental conditions such as light and CO2 in order to optimize CO2 uptake and water loss. Stomatal anatomy (aperture, length, width, etc.) influences leaf-level physiology traits including conductance to water. Stomatal anatomy can be visualized in situ by microscopy, but the difficulty of regulating the atmospheric environment of a microscope stage means that the conditions under which imaging is done are rarely physiologically relevant. Alternatively, portable photosynthesis measuring instruments offer a non-destructive estimate of leaf gas exchange, including stomatal conductance, while the leaf experiences tightly controlled steady-state or dynamic environmental conditions. However, these measurements reflect stomatal characteristics in aggregate on a leaf area basis, which are heavily influenced by the mesophyll as well as epidermal structure and function. Observing the behavior of stomata by microscopy simultaneous to controlling the leaf environment and measuring gas exchange fluxes would allow advances in the understanding of leaf structure-function relationships. To reconcile the microscopic stomatal characteristics with leaf-level gas exchange we have combined laser scanning confocal microscopy and gas exchange instruments to simultaneously observe stomatal characteristics (e.g. stomatal aperture, pore depth, closing speed) and leaf-level traits like photosynthesis, transpiration, and stomatal conductance. Results are presented for the use of this approach on diverse plant species.

Globally, water supply is the major limiting factor for crop productivity. Water use efficiency (WUE) is defined as the ratio of photosynthetic carbon gain relative to water vapor loss from the leaf through the stomata to the atmosphere. Improving WUE would slow crop water use and delay the onset of drought stress when water supply does not meet crop demand. Stomatal density is an important factor that influences plant gas exchange efficiency. We have proof-of-concept that reducing stomatal density in sorghum by ubiquitously expressing a synthetic EPF2core gene can increase WUE without any decrease in photosynthetic carbon gain. However, ubiquitous expression of the synthetic EPF gene has unwanted pleiotropic effects on stem development and seed set. In this study, we test whether tissue-specific promoters can be used to isolate the desired leaf phenotypes without causing unwanted side effects. This provides an important step towards engineering stomatal density to improving WUE and protecting C4 crop yields from drought-induced losses today and in a future, warmer climate.

The maize disease lesion mimic mutants spontaneously form lesions on leaf blades and sheaths that strongly resemble the plant's responses to pathogen infection. Variations in lesion morphology, spatiotemporal distribution, and sensitivity to genetic background and weather make them ideal candidates to develop high throughput and high resolution phenotyping methods for individual plants and their organs in unstructured fields. We present three approaches to imaging lesions at different phenotyping scales and image resolution. Each strategy has distinct advantages and poses unique collection and computational challenges. The first is imaging individual leaves ex situ before sexual maturity using reflected light. The challenge is to identify leaves while the lesions are sufficiently separated for easier segmentation, yet numerous enough for good sample size and mature enough to display the range of lesion developmental stages. This is a moderate throughput, moderate resolution strategy. The second is to image plants using UAVs in situ. The challenges are to fly low enough for good lesion resolution while minimizing extraneous movement and to register individual plants and their leaves during the growing season. This is a high throughput, lower to moderate resolution strategy. The third is to image lesions using after-market lenses on cell phones in situ. The challenges are to capture the same region of the leaves over time without interfering with lesion formation and to mosaic the imagery of highly repetitive surface features into a summary view for registration. This is a low throughput, high resolution strategy.