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.

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.

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.

Fusarium head blight (FHB) is an economically important disease in wheat which can cause yield losses >50%. Breeding for host resistance is the most effective control method, however time, labor, and human subjectivity limit phenotyping efforts. A novel, high-throughput phenotyping rover was used to collect in-field RGB images of inoculated wheat spikes at multiple time points in 2021 and 2022. A deep neural network pipeline was developed to classify wheat spikes, segment healthy and diseased tissue, and quantify FHB severity as the region of intersection between spike and disease masks. To validate the pipeline, model inferences on a plot and spike scale were compared to five raters who performed disease scoring in the field and on images. The precision and throughput of the phenotyping rover and FHB quantification pipeline exceeded conventional rating methods. The plot aggregate disease scores based on pipeline outputs correlated strongly with plot-level disease scores by raters in the field and imagery. When comparing disease annotations on spike images, pipeline to human disease correlations were equivalent to correlations between raters, however location tended to influence disease assessment. The pipeline has strong generalizability and performed well on images taken across environments, with different camera orientations, and throughout disease progression. These results demonstrate a breakthrough in FHB phenotyping and facilitate precise and efficient disease quantification on spikes and plot aggregates across time and imaging conditions that are unachievable using conventional methods.

PlantCV is an open-source open-development image analysis software package for plant phenotyping written in Python that has been actively developed since 2014. A new version of PlantCV was recently released. Major goals of the version 4 release were to 1) simplify the process of developing workflows by reducing the amount of coding needed; 2) broadening the set of supported data types; and 3) introducing interactive annotation tools that can be used directly in PlantCV workflow notebooks. Here we highlight the use of point annotations that can be used to quickly collect sets of points for parameterization of functions such as regions of interest or the identification of landmark points. Another application of point annotations this for image annotation, which is a major bottleneck in plant phenomics. For example, we have used point annotations to analyze microscopy images aimed at measurement of quinoa salt bladders, the number and size of stomata, and scoring of pollen germination. These tasks have traditionally been low throughput and have required manual scoring, but our point annotation tools can be used along with traditional segmentation methods to semi-automatically detect and annotate images. The PlantCV point annotation tools also allow users to correct semi-automated detection results before classification (e.g., germinated vs non-germinated pollen) and extraction of size & color traits per object. Once images are annotated, results can be analyzed directly or potentially can be used as labeled data in supervised learning methods.

In precision agriculture and plant biology, monitoring nutrient stress in crops is of paramount importance for ensuring optimal yield and resource utilization. However, nutrient stress phenotypes can be nuanced, subtle, and display in a variety of ways. We propose using Neural Radiance Fields (NeRFs) for the organized reconstruction of plant structures to observe the changes of plant structure and color under nutrient stress.Neural Radiance Fields, a cutting-edge technique in computer vision, leverage neural networks to model complex high-frequency geometry directly from 2D images, offering high-fidelity reconstructions. This methodology holds immense potential for plant imaging, as it allows for the creation of detailed and organized 3D models that can capture subtle alterations in plant morphology associated with nutrient stress responses.The proposed methodology involves the acquisition of high-resolution images of plants under different nutrient conditions. These images are inputted to the NeRFStudio Nerfacto implementation, a NeRF model that is a aggregation of many different existing models. A 3D reconstruction of the scene is outputted from the model and can be further reduced to a point cloud containing point locations, colors, and normals. Phenotypic traits are then calculated from the point clouds. The reconstructed plant models enable the quantitative analysis of morphological changes associated with nutrient stress. This includes alterations in leaf size, branching patterns, and overall plant geometry. The utilization of NeRFs allows for non-destructive monitoring, offering a significant advantage over traditional methods that may be labor-intensive or invasive.This research not only contributes to the field of precision agriculture but also presents a powerful tool for plant biologists to deepen their understanding of how nutrient stress impacts plant architecture. The insights gained from this approach have the potential to inform precision nutrient management strategies, leading to more sustainable and efficient agricultural practices.

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.

Snap beans and kidney beans are poor nitrogen fixers and need nitrogen (N) fertilizer. However, excessive application of N leads to groundwater contamination. The traditional way of measuring crop nitrogen status is destructive and time-consuming. The objective of this study was to develop a tool that accurately predict the real-time crop nitrogen status and the end-of season yield for optimizing fertilizer management.The field trial was conducted in 2022 and 2023. Eight nitrogen treatments were applied at 22 kg ha-1, 56 kg ha-1, 84 kg ha-1, 112 kg ha-1, 140 kg ha-1, 168 kg ha-1, 196 kg ha-1, 224 kg ha-1 to three kidney beans cultivars. Six nitrogen treatments were applied at 22 kg ha-1, 56 kg ha-1, 84 kg ha-1, 112 kg ha-1, 140 kg ha-1, 168 kg ha-1 to two snap beans cultivars. Hyperspectral images (400 nm to 2500 nm) were collected on a weekly basis. Top twenty bands along with genotype (cultivars), environmental factors (temperature, precipitation, growing Degree Days), management factors (nitrogen rate, days after planting, irrigation) were used to train different machine learning algorithms including linear regression, random forest, XG Boost, support vector machine and k-nearest neighbors for predicting the nitrogen status and the final yield.Our results indicated that top twenty bands along with GEM performed the best for predicting final yield (R2 as high as 0.82 and RMSE as low as 1.6). Our study demonstrated the potential capacity of hyperspectral imaging and machine learning models to estimate crop yield and nitrogen status.

PlantCV is a Python-based image analysis tool that lowers the barrier to entry for complex image analysis workflows in plant phenotyping. To provide support for subsequent analysis steps of measured trait data we have developed pcvr, an R package to assist in common plant phenotyping analyses. The goal of pcvr is to make common statistical analyses both easier and more consistent and to lower the barrier to entry for useful Bayesian methods. Here we demonstrate three pieces of a possible analysis covering single value trait analysis, longitudinal modeling, and multi-value trait analysis.

The maize root system architecture (RSA) influences the absorption of water and nutrients and plays an important role in determining grain yield. Selecting root traits could be an important consideration to improve maize productivity. Traditional approaches in root measurements are destructive, time-consuming and labor-intensive. Nowadays, the X-ray Computed Tomography (CT) technology has been widely applied for non-destructive root trait quantification of maize plants. The root-based imaging technique can be integrated with visible-near-infrared (VNIR) and short-wavelength-infrared (SWIR) cameras to monitor the root and shoot development in the cycle of maize growth. To evaluate the impact of X-ray radiation on maize development, twenty-eight (28) plants were grown in the Ag Alumni Seed Plant Phenotyping Facility (AAPF) at Purdue University and exposed to three different X-ray doses during the growth. The plant root CT and shoot hyperspectral images were collected several times from planting to harvesting. The dry weight/biomass was measured for each plant immediately after harvesting. The results showed that the plants under the three X-ray doses did not exhibit significant differences in root and shoot development. Since the plants were under different water treatments, the water impact on the maize RSA configuration was also studied.

Current phenotyping technologies, whether based on cameras, LIDAR or hyperspectral imaging, are capturing mainly 3D surfaces and are limited, to penetrate into growth media and internal tissue and structures. 3D X-ray computed tomography (CT) alleviates many of these shortfalls by enabling a non-destructiv visualization of optically inaccessible plant structures, allowing for the 3D reconstruction and measurement of objects at high resolution and high throughput. We will present a range of fully automated, industrially validated 3D X-ray CT based technologies, that enable to visually and quantitively follow up in 4D the entire plant development cycle from flowers/ears to seeds to germinating seedling in filter paper to plants and root structures in soil. We will emphasize the non-destructive fully-automated 3D phenotyping of seeds and the resulting germinating seedlings including their internal organs in filter paper across time, i.e. in 4D, at a current throughput of 200 seeds/min and 25 seedlings/min, respectively.The presented technologies, being universally applicable across plant and crop species, allow for the quantitative, objective and reproducible assessment of morphological seed and seedling traits in 4D. They provide powerful tools to investigate any influence, whether genetic, environmental or treatment-related on seed quality and the germination capacity, vigor and 3D phenotype of the resulting seedling over large samples as big data. We will present the technologies and data on traits such as seed quality, seedling development, degree of abnormalities, germination capacity and vigor across different crop types.

Northern corn leaf blight (NCLB), caused by the fungus Setosphaeira turcica, is one of the most devastating corn diseases in the U.S. and has reduced Indiana yields for the last decade. NCLB can cause significant yield loss if conditions are favorable for early disease onset near tassel/silk (VT/R1) growth stages. Therefore, early detection and timely disease management are essential to mitigate yield loss and optimize fungicide applications. Remote sensing technologies have broad applications in plant phenotyping areas, but they present specific challenges in the early detection of diseases, particularly for diseases where lesions first appear in the lower crop canopy. While laboratories can provide more accurate results than remote sensing, their throughput is limited. To achieve higher throughput and more precise measurements for improved early disease detection, a portable digital microscope prototype has been developed. Distinct from other portable microscopes, this device can detect pathogens and directly monitor their growth on live plant tissue due to its 1 nm spatial resolution. Moreover, it is built with a confocal configuration to capture high-resolution reflective images, thereby outperforming traditional microscopes in throughput. This feature also permits repetitive non-destructible measurements on a single leaf and accommodates leaves of varying thicknesses. By analyzing time-series images of infected leaves, this portable digital microscope has proven its ability to detect spores and germ tubes of the pathogen before symptoms are visibly apparent. It has the potential to effectively bridge the gap between precision and throughput, providing critical insights into disease management.

Early detection of plant stress is important, particularly in the face of unpredictable climates. Conventional methods of phenotyping, while useful, lack the ability to provide non-destructive early plant stress detection, a capability provided by remote sensing technologies. The aim of this study was to determine the effect of planting date on various commercial maize hybrid growth and development, focusing on changes in spectral reflectance and vegetation indices related to plant health. An experimental study was set up in Pretoria, South Africa, encompassed planting dates spanning from November 2022 (Early) over December 2022 (Optimum) and January 2023 (Late) to February (Very late). Weekly UAV (unmanned aerial vehicle) flights starting four weeks after planting were conducted with the DJI M210 carrying the Micasense Altum multispectral sensor. Preliminary findings identified a higher spectral reflectance of maize, in the visual, red-edge, and near-infrared bands at optimum planting date as compared to the earlier and later planting. These shifts in spectral reflectance were also reflected in increased values of the Simple Ratio Index (SI), Green Ratio Vegetation Index (GRVI), and Normalized Pigment Chlorophyll Index (NPCI) in the earlier planting dates, when contrasted with the later planting dates. The findings confirm that planting date impacts maize health, and that this can be detected through remote sensing methods. This research demonstrates that UAV technology is a feasible alternative to fixed plant phenotyping platforms, especially in the African context where infrastructure stability remains a major challenge.

UAS-based image analytics has been deployed to expedite the plant phenotyping and replace laborious manual notetaking but is limited for global validation in all field conditions. Plot-level metrics is essential for plant phenotyping on many plots and extracted by defining a region of interest (ROI) of the field boundary and processing sub-ROIs aligned with rows and columns of the total number of plots, called gridding. Gridding is offered by commercial software but is limited to upright rectangular fields. When UAS tile images are stitched, an orthomosaic image is georeferenced to make the image top to north, whereas the field orientation is often off the north. Due to the misaligned orientation, the gridding process requires a preprocess of image rotation to align the grid onto the field boundary, which creates resampling errors and takes laborious multiple adjustments to precisely align sub-ROIs with plots across the field. To address this issue, an open-source software was developed to generalize the gridding method and provide a quick extraction of plot-level metrics without the image rotation. Adaptive gridding algorithm is to rotate the grid by applying geometry of a rectangle in a circle that keeps right angles. Metrics of the rotated ROI is calculated by geofencing pixels in the ROI for segmentation, filtering, masking, and clustering. The open-source software with adaptive gridding allows the end-users to process their UAS images for high throughput phenotyping in an effective manner without understanding details of image processing.

Tar spot disease in maize is the result of a fungal pathogen, Phyllachora maydis, and reduces yield up to 40 percent depending on severity of infection. Traditional disease monitoring techniques often suffer from limited coverage and time inefficiency. This study explores the application of drone-based imagery for phenomic prediction models in maize tar spot onset and severity detection. Using unoccupied aerial vehicles (UAVs) equipped with high-resolution cameras, multi-spectral and high-resolution images are captured of maize fields prior to disease onset and throughout the season. UAV images are processed and analyzed to extract essential phenotypic features related to plant health, including color, texture, size, and shape characteristics. The resulting data are integrated into machine learning algorithms to develop predictive models for disease detection and quantification. Tar spot detection and monitoring techniques would help with field management, minimizing overall yield loss caused by infection. The utilization of drone-based imagery for maize tar spot detection represents a significant advancement in precision agriculture, with the potential to revolutionize the way we monitor and manage crop health.

South Africa is dependent on dryland farming, causing crops to be sown only once the rainy season begins. With climate change altering weather patterns, unpredictable rainy seasons may lead to cash crops such as maize and soybean being planted later, which makes them susceptible to extreme temperatures and drought. Farmers often switch to planting sunflower (Helianthus anuus L.) under these conditions because of its shorter rotation time and hardier nature. For this reason, sunflower tends to be planted outside of its optimal planting window. To understand the effects of different planting dates on sunflower growth and development, a planting date trial was established in Potchefstroom under the Phenospex FieldScan system. Low-and high-density monthly plantings were sown from October to March and scanned three times a day (RGB, NIR, Laser). Values are extracted to calculate plant growth and health indices over the season for each planting date. The aim of this project is to develop a Shiny application that can analyse the Phenospex data outside of the platform. Phenospex software is expensive and impractical to use in the South African context with unstable infrastructure because it requires the sever to be on in one location for analysis in a different location. The Shiny app will allow Phenospex data to be analysed offline, offering more flexibility in an African setting.

This work presents a methodology for creating digital twins of root system architecture (RSA) that can be used for studying the phenotypic variation in RSA. Growing populations demand increased global food production. To sustainably support this increase, crops must be developed to flourish in nutrient-depleted soils. Since the effectiveness of nutrient uptake is determined by plant rooting system dynamics, much focus has been placed on studying RSA across species and varieties. A particularly effective tool for studying RSA in 3D has been X-ray computer tomography (CT). However, this technology is cost prohibitive and cannot model field-grown samples. A far more cost-effective technology is close-range photogrammetric scanning, which uses multiple 2D images to reconstruct 3D point clouds of RSA. This project develops a point cloud processing pipeline that takes high-density point clouds of soybean rooting structures and generates 3D RSA models. These digital twins are then used as the basis for analyzing the phenotypic variation of the geometric and biometric features of the RSA. We believe this digital twin construction and analysis pipeline will increase the impact of RSA research in support of sustainable food production in nutrient-depleted areas of the world.