As the world’s population grows and the demand for food rises, more attention has been paid to increase crop yields and enhance global food security. Modern remote sensing technologies enable us to capture spectral features (such as NDVI) of crop canopy, which are widely used to assess crop growth, health, and stress conditions. We noticed in the literature that crop NDVI shows short-term variation within a day. Therefore, in this study, we leveraged the Spidercam Field Phenotyping Facility at University of Nebraska-Lincoln to measure and quantify the diurnal variation of canopy NDVI for corn and soybean crops. The experiments and data collection were conducted in 2022 and 2023, with canopy reflectance measured by a spectrometer (400-1000 nm) at multiple days covering different growth stages. In each day, measurements were taken at multiple time points within a time window ±3 hours centered around solar noon. Our analysis showed a clear concave-shaped, diurnal trend in NDVI for both crops, with the lowest NDVI at solar noon. More analyses will be performed to quantify this diurnal pattern and dissect the sources of variation due to solar angle and change in canopy morphology. This research will further improve the accuracy and relevance of NDVI in plant phenotyping and many other scientific disciplines and applications.
Global warming poses a substantial threat to food security, necessitating the development of crops resilient to the adverse effects of stress including, drought, heat, and their combined impact. To understand maize responses to individual and combined stress conditions of drought and heat at early vegetative stages, we did a comprehensive evaluation of the phenotypic responses of 47 diverse maize inbred lines. The plants were stressed for 13 days beginning at 7 days after planting, with heat stress conditions of 38/28°C day/night cycles, and the drought condition was achieved by reducing the water pot volume from 88 to 40% over the course of the experiment. The Bellwether Phenotyping Facility, a high-throughput phenotyping platform, was used to capture daily RGB images of the plants throughout the experiment. We extracted morphological and color-related traits from the images, and particular interest was placed on traits that exhibited high broad-sense heritability throughout the experiment. This approach allowed for the collection of a robust dataset of phenotypic responses. Our results revealed distinct responses among the maize genotypes under different stress conditions, with the combined drought and heat treatment leading to the most severe impairments in plant height and leaf area. To gain further insights, we applied a time series analysis to the extracted traits and created groups with dynamically-similar response patterns. This research is foundational for understanding maize stress responses to heat and drought conditions and will inform future work towards identifying important genes and molecular mechanisms, particularly in the context of combined stressors.
Malting is the process of controlled germination of cereal grain that is steeped, germinated, and dry kilned to develop flavor compounds, fermentable sugars, the hydrolytic enzymes necessary for the brewing process. To meet the strict standards of the brewing industry, variation in the germination of barley grains need to be minimal but also maintain rapid germination and optimum levels of \(\alpha\) and \(\beta\) amylase. Preharvest sprouting poses a signinicant threat to barley cultivars prior to harvest, resulting in premature endosperm modification, reduced enzyme content, and poor malthouse pertormance. Pregerminated grain is ditticult to detect as there are often no signs of damage, and current methods such as the Hagberg falling/Stirring number, or pearling tests, each of which ultimately leads to the destruction of the seed. Here we used time-series hyperspectral imaging of barley seeds undergoing active and or pregerminated seed and used a deep neural network to predict stirring number and alpha amylase values, which are proxy measures for sprout damage. Prediction models were made for seven genotypes tested individually and with all genotypes combined. Stirring number assays ranged from 0 to 190 and our prediction models had mean average errors of 10.5 to 23.9 depending on the model. To increase the resolution and accuracy of the predictions we transitioned from using bulk conventional molecular assays to single seed assays and prediction models. These results demonstrate that hyperspectral imaging and machine learning models can be used to predict germinated grain in bulk and single seed assays.
Stomatal conductance (gs ) is a critical plant biophysical variable that reflects plant regulation of CO2 uptake and associated water loss, yet its direct measurement is often prohibitively time-consuming. Estimating the impacts of gs indirectly through leaf temperature (Tleaf ) is a common practice, but is complicated by confounding factors such as ambient conditions, measurement aggregation scale, sample size, and measurement time. Using Tleaf measurements to instead determine parameters of a model for gs that can remove these external factors can provide quasi-traits that are more reliable and heritable. Our objective was to develop an automated pipeline for gs model parameterization using thermal data, which could be applied within a 3D biophysical model to predict the impacts of trait variation on canopy-level processes related to water-use efficiency. Field experiments were conducted on common bean, cowpea, and sorghum crops, involving high-resolution thermal measurements obtained from a robotic sensing platform. Subsequently, a deep learning algorithm was trained using synthetic thermography data generated using Helios 3D model simulations encompassing canopy structure, ambient conditions, and Tleaf , enabling the prediction of long-wave radiation and incident shortwave radiation for each thermal image pixel. Following this, a leaf-surface energy budget analysis was applied to the collected field thermal data to predict gs parameters. Validation of these predictions was performed through comparisons with ground-truth leaf-level gas exchange data. This pipeline offers a promising pathway to predictive simulations of water status and transpiration-related traits, regardless of environmental variation, ultimately enhancing our understanding of plant responses to changing environmental conditions.
Cold tolerance is of paramount importance for the survival of winter wheat, as failure to withstand low winter temperatures necessitates costly replanting during the spring season. Initial observations indicate that higher cold tolerance is associated with increased winter dormancy, resulting in slower spring growth and potentially lower grain yields. Understanding how quickly the plants grow during this critical period can provide insights into their overall health and yield potential. This study investigates the interaction between cold tolerance, winter dormancy, rate of spring growth, and final grain yield to develop cultivars with high cold tolerance and early spring growth. The plant material consists of 480 diverse soft white winter wheat varieties collected from Pacific Northwest (PNW) breeding programs. The population was cultivated for three years (2016, 2017, and 2018) at two PNW locations (Pullman, WA and Pendelton, OR). RGB and NIR images were captured weekly to generate growth curves and calculate NDVI values for each genotype. Additional data on tiller count, heading date, plant height, grain volume weight, and grain yield were collected. Modeling NDVI regression curves enabled us to quantitatively define plant growth attributes including spring growth rate, time of peak greenness, dry-down rate, time of total dry-down, time from heading to total dry-down. These data, correlated with final grain yield, will enable a better understanding of winter wheat growth patterns. This information is crucial for breeding regionally specialized winter wheat varieties that can maximize spring growth and yield potential while minimizing the risk of cold damage.
The Embedded Automated Generator of Labeled Images (EAGL-I) system is a tool for generating labeled images, particularly for data-driven methods, such as deep learning models. The system has already generated hundreds of thousands of images of weeds and crops. We present modifications made to the original system that are based on the experiences gathered from generating such large-scale datasets. The improvements relate to lighting conditions, ease of use, refined image segmentation, and pathfinding for camera-movements. To address lighting conditions, we made three major changes to the hardware. First, the blue keying fabric was replaced by solid black panels, mitigating reflections and achieving reliable color accuracy; second, sunlight entering the room through a window is diffused and partially blocked by a screen, achieving consistent and uniform lighting of the imaging environment; third, dimmable LED lights are installed allowing us to image with lower ISO and to reduce noise in the resulting images. A YOLO machine learning model was trained to replace the previous methods of estimating bounding boxes around the plants. This new way of creating bounding boxes adapts to different plant architectures, such as grasses or different kind of dicots. Finally, we implemented a version of the A* pathfinding algorithm to define save zones through which the camera will not be moved. Overall, these modifications improved system performance and image quality significantly, while making EAGL-I easier to use. We have extended potential applications of EAGL-I, particularly for plant phenotyping research and in fine-tuning machine learning models for image analysis.
We present CherrySet, a comprehensive dataset comprising observations of three cherry trees throughout an entire vegetation period. This publication is part of the For5G: Digital Twin project, where we aim to develop an end-to-end pipeline for the creation of digital twins in horticulture, from data acquisition up to end-user applications. For this purpose, we have developed a methodology for precise scanning and capturing of high-resolution image data of trees using UAV technology. Now we are releasing the dataset and preliminary findings of the 2023 season to encourage fellow researchers to leverage the data for their own research and contribute to the scientific community.CherrySet encompasses a collection of 2D images covering three sweet cherry trees at 12 distinct time points, spanning from dormancy in March through blooming and growth until harvest in July 2023. In addition to the image data, CherrySet offers manually recorded ground truth information obtained from reference branches throughout the growing season, which includes comprehensive bud, blossoms and fruit counts during all vegetation phases, as well as the total number of cherries gathered at harvest. The combination of visual and ground truth trait data allows insights into intra-seasonal analysis of tree and fruit development, providing valuable data for conventional or AI based follow-up research.We are committed to refining our image acquisition pipeline and intend to provide corresponding data for these trees throughout the 2024 season. This expansion will open up opportunities for inter-seasonal research.
Photogrammetry is the science of obtaining a 3D scan of an object. Through this process, reliable information about the physical object's complex structure can be obtained, studied and analysed. A low-cost Structure from Motion (SfM) technique can be used to create 3D models using multiple 2D images from different viewpoints. A point cloud is a widely used 3D data form, which can be produced by depth sensors, such as LIDARs and RGB-D cameras. However, the cost of such scanners can be prohibitive, putting photogrammetry out of reach for many researchers and practitioners in the agriculture industry. We are developing a low-cost close-range photogrammetry rig that could be a beneficial tool for agronomists, plant scientists, and breeders. Our imaging system utilizes the Raspberry Pi to capture images with multiple cameras, and a commercial rotatory table to get images from different viewpoints. We discuss the development of extracting quantitative trait indices in wheat in order to automatically characterize planophile versus erectophile canopy architectures. Moving forward, we plan to use our photogrammetry rig for a variety of applications such as growth monitoring and extracting plant traits such as number of leaves, stem height, leaf length, leaf width, leaf area, and canopy volume. We also plan on developing bespoke, plug-and-play systems that are tailored to the specific needs of a researcher and can be operated with minimal expertise.
Plants store carbon as oil in their seeds, which is a resource that needs to be mobilized in order to germinate. Camelina sativa is a prospective biofuel crop which has the potential to be used as a cover crop in corn and soy growing regions. Camelina plants have been engineered to produce medium-chain fatty acids useful in the production of biofuels, lubricants, and other products. To test suitability of these modified Camelina lines for growth in cool climates such as those found in the midwestern US, we performed germination tests on seeds in growth chambers at temperatures similar to those encountered in early season in corn-growing regions (6°C, 15°C, and 22°C). Controls were the untransformed background Suneson genotype, as well as plants from the far northern and southern ranges of C. sativa. Germinating seedlings were imaged using Raspberry Pis, and analyzed with PlantCV for the number of plants and the cotyledon area. To determine effects of seed fatty acid content later in the growth cycle, seedlings were transplanted and grown at 22°C until seed set. These plants were imaged every 20 days to track height, width, area, and solidity using PlantCV to analyze the data.
Weed competition with crops is the number one cause of yield loss worldwide. Plant breeders combat this issue by breeding herbicide tolerant varieties. The Aggressor (Group1) and Beyond (Group 2) herbicides are commonly used to control weeds in the Pacific Northwest. Many weed species are developing tolerance to group 1 and 2 herbicides. Metribuzin is a group 5 herbicide that is labeled for use in wheat, but application results in severe plant injury. Release of winter wheat variety tolerant to Metribuzin would provide producers an alternate mode of action to control weeds. Historically breeders visually rate injury in breeding plots, these ratings can be variable and subject to individual bias. This study aims to improve the accuracy and efficiency of selecting herbicide tolerant lines in a breeding program by utilizing a drone mounted multispectral sensor. Multispectral data was collected on paired rows and advanced generation lines grown in yield trails. The vegetative indices calculated from the wavelengths measured by the multispectral sensor in this study include NDVI, NDRE, TCARI, NWI, and MTVI. Visual injury scores, plant height, and yield were also measured. Correlations between reflectance indices and yield were stronger than correlations between visual injury ratings and yield. There were also moderate to strong correlations observed between visual injury rating and vegetative indices as well as plant height difference and vegetative indices. The results of this study suggest that multispectral analysis on the plot level is an accurate indicator of herbicide injury in winter wheat.
Maximizing crop yield while conserving resources is a pressing challenge in modern agriculture. Maize (Zea mays L. ), a staple crop worldwide, relies heavily on photosynthesis, making radiation interception a pivotal factor in crop growth and yield. This study presents a novel approach to improve maize crop productivity by harnessing the principles of phyllotaxy and optimizing planting patterns to efficiently intercept solar radiation. Through the enhanced 3D maize model generation algorithm, the simulation incorporates critical factors such as curved surface leaf area, leaf arrangement, plant spacing, and solar angles, allowing us to quantify the radiation intercepted by the maize canopy. We investigate the most efficient phyllotaxy for individual plants and evaluate a range of planting patterns and their impact on radiation interception at various growth stages. Simulation results reveal that optimizing planting patterns based on phyllotactic principles can substantially enhance radiation capture compared to traditional planting methods. In conclusion, our research signifies a significant step towards harnessing the power of plant arrangement and optimizing planting strategies, including the use of an enhanced 3D maize model, to maximize radiation interception in maize crops. The optimal phyllotaxis and planting patterns establish a distinct phenological target for breeders. These findings hold promise for the development of more resilient and productive agricultural systems in an era of growing global food demand and resource constraints.
Breeding for improved, reliable cultivars despite growing environment irregularity can be challenging. Unmanned aircraft systems (UAS) are a popular high-throughput phenotyping technology that has been shown to help understand the mechanisms associated with crop productivity and create a potential for improved breeding strategy by providing unique insight into environmental response and cultivar productivity. Spectral reflectance indices (SRI), including both vegetation and water indices like NDVI, NDRE, and NWI were used to evaluate 11,593 Washington State University winter wheat breeding plots between 2019 and 2022. SRIs were then used with genomic data in univariate and multivariate gBLUP model predictions for grain yield. Prediction accuracy was evaluated on a leave-one-year-out validation strategy. Including SRI data as fixed effects in univariate genomic prediction models can improve prediction accuracy over the control but is unreliable across years. When used in multivariate models, SRIs improve prediction performance across years but minimally when considering the computationally more efficient base model. In univariate models, when test year NDVI data was used to calculate breeding values, prediction performance was at least 16% better than the control, ranging in prediction accuracy from 0.54 in 2019 to 0.93 in 2020. This study highlights the limitations of SRI and its use in genomic selection, especially when dealing with large breeding populations across environmental extremes. A significant application for the technology can be found in early season UAS data collection to aid accurate predictions in late season, a helpful tool in tight turnaround times commonly experienced in winter crop breeding programs.
Nitrogen is a crucial nutrient for soybean growth and production. Enhancing soybean crop yield is essential to address the growing challenge of ensuring food security. While nodulation and nitrogen fixation reduce the need for additional nitrogen, the presence of actively fixing nodules, distinguished by their pink or red color, ensures effective nitrogen fixation and yield improvement in soybeans. Changes in global climate led to shifts in soil characteristics that restrict root growth and create conditions resembling drought, diminishing the capacity of plant roots to absorb water and nutrients, consequently impacting overall plant growth as well as nodulation related traits. In this research, we’re examining nodulation related traits across 500 late maturing soybean accessions. We germinated seeds on germination paper and transferred them to blue blotting papers and captured root images after 21 days. Nodulation traits such as Nodules number and area will be evaluated using the Soybean Nodule Acquisition Pipeline (SNAP). Statistical assessments including population structure, kinship matrix, and principal component analysis will be measured using R. We’ll utilize both phenotypic data and SNPs from Illumina Infinium SoySNP50K iselect SNP Beadchip for Genome-wide Association Studies (GWAS) using the GAPIT package in R. This study aims to identify genetic regions linked to nodulation traits, potentially uncovering valuable QTLs or genes for enhancing nodulation related traits.
Climate change poses a significant threat to agricultural systems, with drought becoming increasingly prevalent in the Canadian prairies. This study addresses the urgent need to enhance crop resilience, focusing on Brassica carinata, a promising industrial feedstock crop used for the production of biofuels. Our research aims to comprehensively evaluate drought adaptive capacity in B. carinata through a combination of physiological and digital phenotyping methods. Under controlled conditions, we utilized a high-throughput phenotyping platform, the Plantarray system, to screen B. carinata germplasm. This system facilitated precise measurements of physiological traits, soil conditions, and atmospheric parameters, enabling the assessment of drought response. Concurrently, we conducted a field phenotyping experiment with 47 B. carinata Nested Association Mapping (NAM) founder lines and two B. napus checks, under irrigated and non-irrigated conditions. Aerial imagery obtained through Unmanned Aerial Vehicles (UAVs), complemented by phenological observations and manually recorded phenotypic data, was systematically gathered. Digital phenotypes extracted from aerial images are analyzed to identify a digital phenotype(s) for drought tolerance. Our study also explores the correlation between indoor physiological data and field performance of B. carinata lines, in an effort to identify parameters that can serve as reliable predictors of seed yield under drought stress. Overall, we believe this research provides valuable insights for enhancing crop resilience to drought.
Chenopodium quinoa is an important crop known for its salt tolerance. Salinity is an osmotic stress and ions accumulation in the root zone causes a reduction in soil water availability, affecting the uptake of essential nutrients, changing seed composition, and reducing biomass. Hence, the need for high-yield crops in poor soils. This research examines the effect of salt stress on quinoa photosynthetic efficiency and salt bladder development. Sensitive and tolerant quinoa lines were examined under salt stress conditions when a concentration of 155mM NaCl was applied. Soil conductivity was monitored for salt stress during the experiment. At approximately two months old, CropReporter images were taken and analyzed using PlantCV to estimate photosystem II efficiency, non-photochemical quenching (NPQ), chlorophyll content, and anthocyanin content. The analysis showed that the salt treatment did not negatively affect the plant photosynthetic efficiency (no changes in Fv/Fm, NPQ, Fq’/Fm’) but leaf area and chlorophyll content was statistically negatively affected by the treatment when comparing genotypes. Live tissue was also analyzed using reflection and fluorescence confocal microscopy, where epidermal salt bladders images were acquired, visualized and analyzed in 3-D and the salt tolerant line showed bigger bladder volumes compared with control conditions. A more high-throughput approach using PlantCV, an open-source image analysis software package targeted for plant phenotyping. This software helped count epidermal salt bladders using stereoscope images. A comprehensive understanding of the quinoa salt tolerant mechanisms by employing multidisciplinary approaches is necessary for their effective incorporation into salt-sensitive crops for better crop yields under stressful environments.
Plant phenology and phenotype prediction using remote sensing data is increasingly gaining attention in order to enhance agricultural productivity. This work aims to generate synthetic forestry images that satisfy a specific phenotypic attribute, viz. canopy greenness. We harness a Generative Adversarial Network (GAN) to generate biologically plausible and phenotypically stable forestry images conditioned on the greenness of vegetation over a specific region of interest (describing a particular vegetation type in a mixed forest). The training data is based on the automated digital camera imagery captured by the National Ecological Observatory Network (NEON) and processed by the PhenoCam Network. This method helps render the appearance of forest sites specific to a greenness value. Further, synthetic images are utilized to predict another phenotypic attribute, viz., redness of plants. The Structural SIMilarity (SSIM) index is used to assess the quality of the synthetic images and their greenness and redness indices are compared against that of the original images using Root Mean Squared Error (RMSE) to evaluate the accuracy and integrity. The generalizability and scalability of our proposed GAN model is determined by effectively transforming it to generate synthetic images for other forest sites and vegetation types. From a broader perspective, this technique could be used to visualize forestry based on different phenotypic attributes in the context of various environmental parameters. This work provides a useful step in leveraging generative AI principles from pattern recognition and computer vision for plant phenological research.
Plant breeding programs demand efficient and accurate methods for crop phenotyping, especially for economically important crops like soybeans. Traditional manual assessment methods are labor-intensive and prone to errors. The emerging field of phenomics leverages advanced technologies, including high-resolution satellite and drone imagery, to monitor crops in a time, cost and labor efficient way. Drones offer localized, high-resolution data but have limitations in coverage and operator skills. In contrast, high-resolution satellite imagery provides broad-scale views of the vegetation with increasing improvements in spatial and temporal resolution.Our study investigates the potential of high-resolution satellite imagery as an alternative to drone imagery for assessing soybean maturity and monitoring the crop condition in a small plot breeding program. We compare the efficiency of these two technologies and we explore the utilization of various vegetation indices (VIs) derived from satellite-based multispectral imaging sensors for maturity estimation, indirect assessment of essential plant traits and identification of the growing patterns of different maturity groups.Our findings reveal the promise of high-resolution satellite imagery as a valuable tool in soybean phenotyping, addressing the spatial scale challenges in breeding programs. With advances in spatial resolution, satellites can provide detailed insights into crop health, productivity, and resource management. This research contributes to the evolution of precision agriculture, offering a cost-effective and scalable solution for monitoring soybean maturity and enhancing crop adaptability and yield.
Metamorphic core complexes (MCC) provide a rare glimpse into thermomechanical processes in the lithosphere and play a substantial role in the evolution of the crust. The North American Cordillera contains a northwest trending line of MCCs, which have been extensively studied using bedrock thermochronology and modelling approaches to better understand extensional processes related to Cordilleran collapse. While these studies have proposed a wide variety of models to explain the timing and mechanism behind MCC formation, few have considered the syn-deformational basin record, which preserves a unique archive of sediment sources in adjacent MCC highlands. This study focuses on the Deer Lodge Valley, located in the hanging-wall of the Anaconda MCC. We utilize detrital zircon (U-Pb)-(U-Th)/He double dating in the context of stratigraphic and sedimentologic analyses, and HeFTy time-temperature modelling to reconstruct basin evolution. Stratigraphic analysis shows that the basin was dominated by deposition of coalescing alluvial fans, with sediment sourced directly from the footwall of the detachment fault. U-Pb maximum depositional ages indicate late Paleocene to early Eocene proximal basin sedimentation. (U-Th)/He analyses from U-Pb dated zircons range from 194-32 Ma; >70% of dates are Eocene. Preliminary HeFTy modelling shows a period of rapid cooling between 65-55 Ma, which is supported by short (<10 Myr) sediment lag times and inferred rapid exhumation in the MCC. Our findings support a link between MCC exhumation and basin formation. They further depict a potentially earlier period of MCC exhumation than previous work has proposed, indicating an earlier onset of extension in western Montana.