The growing world population increases demand for agricultural production, which is becoming even more challenging as climate change increases global temperatures and causes more extreme weather events. Using high-throughput phenotyping, this study examines the phenotypic variation of 149 accessions of Brachypodium distachyon under drought, heat, and the combination of both stresses. Heat alone causes the largest amounts of tissue damage and the combination of heat and drought causes the largest decrease in plant biomass compared to other treatments, however, we identified heat alone as being the most detrimental stress condition. Notably, we identified Bd21-0, the reference line for B. distachyon, as not having robust growth under stress conditions, especially in the heat-drought combined treatment. We found climate of origin (climate data from the accessions' collection locations) to be significantly associated with height and percent of plant tissue damage under the conditions assessed, indicating a relationship between climate of origin and B. distachyon phenotype under drought and heat stresses. Additionally, genome wide association mapping found a number of genetic loci associated with changes in plant height, biomass, and the amount of damaged tissue under stress. Significant SNPs were closely located to genes known to be involved in plant responses to abiotic stresses. The anticipated increase in drought and heat stress as a result of climate change and the distinct impact of stresses in combination, as demonstrated in this study, underscores the importance of phenotyping plants under multiple stresses that frequently converge.
High-oil tobacco varieties have been recently engineered to produce increased leaf oil content for future food and fuel needs. An engineered variety of Nicotiana tabacum produces ~30 percent of leaf dry weight in lipids in the form of triacylglycerol (TAG), a significant increase relative to the less than 1 percent storage oil normally found in wild-type leaves. This high-oil tobacco also accumulates oil bodies in stomatal guard cells. In order to understand the impact of oil on guard cell shape, aperture, and dynamics, we have co-opted computer vision tools in PlantCV to create an accurate, flexible, and high-throughput method for microscopy image analysis of stomata. To this end, leaf impressions are made with silicone putty; clear nail polish peels of the putty impressions are imaged using light microscopy. Binary thresholding followed by point-and-click regions of interest and morphology calculations provide stomatal counts, aperture, and other shape characteristics. Applying this method to high-oil tobacco demonstrated reduced stomatal aperture but the same number of stomata per unit leaf area, providing a mechanistic explanation of high-oil tobacco responses to high temperature and water deficit stresses.
3D scans of real world objects are often represented by point clouds, creating XYZ-coordinates of individual scan points. However, unlike point clouds that are generated from CAD data, points generated from a real world scene lack information about their local context, making segmentation of the structural information contained in the data difficult. Using neural networks (e.g. PointNet) has shown promising results. However, this approach is not well suited for scans of large areas of similar objects, like e.g. a wheat field, because of limitations of the input vector size of the neural network. In addition, point clouds are often unordered, further complicating processing. Since point clouds of biological objects often contain recurring features, we propose to subdivide the point cloud into locally neighboring subsets with a fixed number of points. The collection of subsets can then be used to train neural networks. This approach preserves the original resolution of the point cloud while offering simple data augmentation concepts like creating a number of different subset collections from the same ground truth. There are several advantages to this approach, like significantly simplifying the training phase, because a single, large annotated scan can be sufficient for training, utilizing the similarity of the instances of a plant in the field.
Malting is the controlled germination of a cereal grain. In barley, malted grains provide the fermentable sugars necessary for brewing and distilling processes. Harvested barley must adhere to strict industry quality standards to be considered for malting including robust hydrolytic enzyme content, low protein content and high rates of germination. Failure to meet quality metrics results in significant loss of market value and presents a risk to growers considering malting barley. Modern cultivars of malting barley are susceptible to preharvest sprout (PHS), or germination of the seed prior to harvest, resulting in premature endosperm modification, reduced enzyme content and poor malthouse germination. Seeds with PHS damage fail quality assessments and are sold for feed at reduced prices. Most presprouted grain shows no visual signs of damage and accepted methods to assess PHS damage including Hagberg falling number and stirring number (Rapid Visco Analyzer), which are costly and destructive to the seed. To address this need, we applied time-series hyperspectral imaging of barley seeds with varying levels of PHS damage and used a deep neural network to predict stirring number and alpha amylase values, which are indicators of sprouting. Prediction models were generated for each of the seven genotypes tested individually and also for all genotypes when combined. Our prediction models had mean average errors from 10.5 to 23.9 and root mean square errors from 19.0 to 35.1 demonstrating the applicability of hyperspectral imaging as a high-throughput, nondestructive method for predicting levels PHS damage in malting barley.
Tillers are shoots that arise from the base of a plant. When plants tiller, they place more carbon resources into vegetative growth as opposed to their grains. Understanding the environmental and genetic factors behind tillering is hampered by lack of high-throughput phenotyping for determining plant tiller count and angle. Currently, plant tiller counts are determined through manual inspection, which is laborious and low-throughput. In this study, we introduce a PlantCV (https://plantcv.danforthcenter.org/)-based algorithm for detecting tillers. This method uses OpenCV's line detection algorithm to detect lines that correspond to the tillers of the plant. From this, tiller count and angle of growth can be inferred. We use this method on Sorghum bicolor accessions from the TERRA-REF project that were grown for two weeks, cut back, and then allowed to regrow for two weeks. Of 200 randomly chosen images, this algorithm was able to accurately count within 1 tiller of the true number of tillers for 165 images. Furthermore, we find that these Sorghum bicolor accessions appear to place less resources into their tillers in the regrowth phase.
Temporal analysis reveals diverse root system architecture and development differences among pennycress accessions to nitrate nutrition (Thlaspi arvense L.) Roots have a central role in plant resource capture and are the interface between the plant and the soil affecting multiple ecosystem processes. Field pennycress (Thlaspi arvense L.) is a diploid annual cover crop species that has potential utility for reducing soil erosion and nutrient losses; and has rich oil seeds amenable as a biofuel (30-35% oil) or high-protein animal feed. The objective of this research was to (1) precisely characterise root system architecture and development, (2) understand adaptive responses of pennycress roots to nitrate nutrition, (3) and determine genotypic variance available in root development and nitrate plasticity. Using a root imaging and analysis pipeline 4D pennycress root system architecture was characterised under four nitrate regimes (from zero to 5 mM nitrate concentration) across four time points (days 5, 9, 13 and 17 after sowing). Significant nitrate condition response and genotype interaction was identified for many root traits with a greater impact on lateral root traits. In trace nitrate conditions a greater lateral root count, length, interbranch density, and a steeper lateral root angle was observed compared to high nitrate conditions. Genotype by nitrate condition interaction were observed for root width, width depth ratio, mean lateral root length, and lateral root density. These results illustrate root trait variance available in pennycress accessions and useful targets for breeding of improved nitrate responsive cover crops for greater productivity, resilience, and ecosystem service.
High throughput phenotyping and quantitative genetics have enabled researchers to identify genetic regions, or markers, associated with changes in phenotype. However, going from GWAS markers to candidate genes is still challenging. When selecting candidate genes for ionomic GWAS markers, we curated a collection of well-known ionomic genes (KIG) experimentally shown to alter plant elemental uptake and their orthologs in 10 crop species: 2066 genes total. Yet when compared to ionomic GWAS markers, over 90% of significant markers were not linked to a KIG - indicating the list is incomplete and many causal genes are unknown. Continuing to use only functional annotations as candidate selection criteria will keep efforts biased toward well-known genes and hinder the characterization of unknown genes. We propose an unbiased computational approach that compares analogous GWAS markers from multiple species and searches for conserved genes linked to trait markers. Like the KIG list, we expect many of these unknown candidate genes to have orthologs in other species. By leveraging the evolutionary relationship of these conserved genes, rather than prior knowledge and gene annotations, this method: 1) finds more candidate genes than we expect from random chance, 2) selects and prioritizes candidates in poorly annotated species, and 3) includes unknown genes in the results. With this approach, we now have an unbiased list of gene candidates across 19 ionomic traits in model species and crop species to verify in future experiments.
Barley is the most produced crop in Ireland; it is essential as a fodder crop and a key ingredient for the malting industry, contributing to Irish national identity. In Ireland, climate change is bringing more extreme rain; leading to an increase in flooding and waterlogging events. Barley is particularly sensitive to waterlogging urging the need to harness genetic diversity and breed barley with increased waterlogging tolerance to maintain current agricultural production. One of the limiting factors in breeding is the drawbacks of traditional phenotyping. This project relies on modern high-throughput phenotyping, which allow non-destructive, continuous and quantitative data collection. Using imaging sensors in controlled conditions, we phenotyped a collection of barley accessions under controlled and waterlogged conditions using RGB, fluorescent and hyperspectral cameras (VNIR and SWIR). We used the core European Barley Heritage collection (ExHIBiT); made up of 230 diverse 2-row spring barley accessions. This collection was assembled, genotyped, agronomically characterized and its application for association mapping has been established by our team. We observed that 14 days of waterlogging lead to a significant reduction in pixel count (Project Shoot Area) and Quantum yield, showing a large impact on several hyperspectral indices. We also observed that 7 days of recovery after stress are fundamental for differentiate stress resilience. Work is ongoing to optimize hyperspectral image analysis, and establish parameters to distinguish plant performance, enabling to discriminate between resilient and sensitive accessions. These data will be used for association mapping to identify genetic regions contributing to waterlogging tolerance in spring barley.
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.
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.
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.