Plant phenotyping using images from unoccupied aerial systems (UAS) is typically limited to trait acquisition at the plot level, generally accompanied by the manual delineation of plot boundaries. However, phenotyping of natural populations, mutant populations, and segregating germplasm are difficult or impossible without plant level phenotypes. Plant level boundary delineation is complicated by many factors and manual delineation is impossible in even relatively small field experiments. We present a method for using object detection models on raw UAS images followed by the "projection" of the resulting bounding boxes onto the orthophoto for geolocation. The method is able to detect individual maize plants in UAS images, create accurate bounding boxes around these plants on the orthophoto via differential orthorectification, and extract individual plant heights from the Digital Surface Model (DSM) as well as spectral indices like Normalized Difference Vegetation Index (NDVI) values from orthophotos. For verification, we compared the heights obtained from this method to the heights obtained by manually drawing the bounding box for each plant and calculated the precision. The method performs with accuracies as high as 0.9 depending on the growth stage and other factors. We expect this accuracy can be increased with larger training sets and further methods development.

Gray mold, caused by the fungus Botrytis cinerea, is a major pre-and post-harvest disease that affects all aboveground parts of tomato and many other economically important crops. The main control strategy to manage gray mold is through the use of synthetic fungicides. However, B. cinerea has a high ability to develop resistance to fungicides, and fungicides pose environmental hazards and health risks to off-target organisms. The use of nanoemulsions encapsulating hydrophobic plant essential oils to improve water dispersibility is a promising strategy to ameliorate gray mold without the application of harmful fungicides. This study evaluates the potential of cinnamon essential oil nanoemulsion (EONE) to suppress gray mold in hydroponically-grown tomatoes. The root system of four-week-old tomatoes were dosed with different concentrations of EONE before the leaves were inoculated with B. cinerea. The effect of EONE on the plant's photosynthetic capacity and ability to suppress necrotic lesion development were measured using Plant Explorer Pro+ and LeafSpec imagers. Multispectral data showed significant differences in Fv/Fm, chlorophyll content, and NDVI values between inoculated and uninoculated leaves. In addition, EONE-treated plants showed up to 45% reduction in gray mold lesions compared to the non-treated control. Future experiments will evaluate the efficacy of foliar-application of EONEs to suppress tomato root diseases, and investigate potential mechanisms using RNA-seq and microbiome analyses. Results of the study could be useful in further development of EONEs as an effective management tool against different diseases and could be adapted to evaluate other nanocarrier formulations for disease control.

Soil Organic Carbon (SOC) fluctuations in agricultural fields play a critical role in determining soil fertility and carbon sequestration. Efficient, non-destructive monitoring of SOC is essential. This study utilized Unmanned Aerial Vehicles (UAVs) and four Machine Learning (ML) algorithms-Multiple Linear Regression (MLR), Partial Least Squares Regression (PLSR), Random Forest (RF), and Xtreme Gradient Boosting (XGB)-to predict SOC levels.Our research, set at the Danforth Center Field Research Site (FRS), comprised 35 sorghum genotypes in a complete block design. Using a GeoProbe drilling machine, we collected soil cores for compositional analysis through the Haney test. Concurrently, drone-captured multispectral images were processed to create orthomosaic maps and extract features. The ML algorithms effectively predicted SOC levels, with MLR models showing the highest accuracy (RMSE = 7.12 ppm; R = 0.74). We observed variation in SOC among genotypes, suggesting that genotype-specific traits could influence SOC estimation accuracy. Field plots planted with genotypes like SC1345, BTx623, and SAP-133 showed strong predictability with errors below 5%. In contrast, SC283 and SAP-154 had prediction errors exceeding 30%.UAV-based remote sensing offers promising avenues for soil health assessment, contributing to precision agriculture and sustainable land management. Future studies could benefit from integrating hyperspectral sensors to fully harness this technology's potential.

Modern agriculture increasingly relies on non-invasive techniques for plant health monitoring. Touch-based proximal hyperspectral imaging (HSI), where sensors directly clamp onto leaves, offers intricate plant details but faces distinct challenges. Current methods lack real-time awareness of the pressure and alignment between the sensor and the leaf surface. This blind interaction could lead to potential damage to the leaf or even affect internal cellular structures, which could alter the hyperspectral readings. In this research, we introduce the integration of a tactile sensor with a robotic system specialized for touch-based proximal HSI of corn. This fusion of HSI with the GelSight sensor provides high-resolution tactile feedback, crucial for gentle plant navigation and precise positioning. This tactile guidance ensures the robotic system applies consistent and safe pressure on the corn, reducing the risk of unintended damage and improving the consistency in hyperspectral data. Experiments showcased the efficacy of this integration. Results highlighted a significant improvement in imaging data quality, scanning success rate, and consistency, with the tactile sensor reducing inadvertent plant disturbances compared to non-tactile methods. In conclusion, the seamless merger of HSI with tactile feedback represents a significant advancement in precision agriculture. This integrated approach promises enhanced plant health monitoring, fostering sustainable farming and increased yield potential.

Modern maize hybrids prolong the period that they photosynthesize and accumulate Nitrogen (N) out of the soil which has helped them produce more yield per unit of N fertilizer. However, the increase in post flowering activity is inversely correlated with N remobilization from the leaves. Further gains in N response could be achieved by breaking this association, but doing so requires an in-depth understanding of the temporal dynamics of maize canopy traits and plant N mobilization. Leaf nutrient samples were collected at five time points and remote sensing phenotypes were extracted from Unoccupied Aerial System (UAS) imagery (orthomosiacs and point clouds). Spectral indices and point-cloud based metrics were used to investigate the relationship between changes in N storage dynamics and yield among hybrids grown in low and high N treatments. From these combined phenotypes, it is possible to dissect how rate of growth and canopy health help to describe hybrid response N and also provide clues for how to break the negative relationship between yield and N remobilization.

In the Chicago region, common buckthorn and bush honeysuckle stand out as dominant invasive species, accounting for over 40% of the regional forest coverage. Their proliferation leads to the formation of dense thickets that hinder sunlight penetration, resulting in diminished native plant diversity in the understory. Accurate detection of these species across this region is essential for the effective management of these invasives. Airborne LiDAR datasets show strong potential in detecting the distinctive structural patterns created by these thickets. Previous studies have utilized multi-temporal spectral imagery to track the phenological shifts of invasive species. However, in the Chicago region, it is difficult to employ multi-temporal spectral imagery due to substantial cloud cover during early spring and late autumn. Consequently, our research adopted the use of dense airborne LiDAR datasets specific to the Chicago area. Preliminary results indicate that invaded plots manifest less complex vertical structure, higher vegetation area index in the subcanopy, and lower NDVI values compared to their non-invaded plots. Notably, LiDAR-derived metrics surpass NDVI-based ones in estimation. Using binomial logistic regression (with an AUC of 0.97), we assessed the presence and absence of these invasive species across Chicago's forests, achieving an accuracy rate of 0.92. Alarmingly, our findings suggest that these invasive species have affected over 75% of the forest patches in Chicago. In summary, our research highlights the important role of LiDAR datasets in regional-scale invasive species detection.

This study explores cross-species variations in structural metrics derived from individual tree lidar scans and analyzes the structural characteristics of trees at both the individual and plot levels. Understanding the species composition of forests is vital for assessing ecosystem health and biodiversity. For this reason, much research has been dedicated to distinguishing between species through remotely sensed datasets; however, the goal of remote species identification remains unrealized. Progress has been hindered by two key challenges: 1) the lack of precisely georeferenced ground validation data, and 2) insufficient consideration of 3D environmental factors such as terrain, understory layers, and the structural entanglement of natural forests. In this study, we address these challenges by compiling a ground validation dataset comprised of precisely high-density laser scans at 60 forest inventory plot locations. Within this dataset, each of the 1200 trees is segmented and paired with a manually verified species label. Using this comprehensive dataset, we first isolate individual trees and investigate cross-species variations in lidar feature metrics. Subsequently, we examine how these structural features vary within the context of the micro-environment of their respective plots. Our analysis also explores how factors such as terrain and neighboring species impact structural feature variance. Our findings suggest that detectable structural features hold significant potential in accurately assessing biodiversity and determining the species composition within forests.

Thermal remote sensing has been introduced as a robust technology for monitoring water status in plants, in a real-time and non-destructive approach, under a variety of environments. Canopy temperature is a key indicator of water stress and is extensively used for the determination of the water status in crops. A previous planting date study conducted in South Africa revealed a large decline in yields between December and January regardless of cultivar or location. This study aims to monitor crop water status and plant health across the four monthly planting dates and four weekly planting dates between December and January. The trial was designed as a split plot with three replicates arranged in complete randomized blocks in Pretoria, South Africa. A Thermal sensor fixed to a UAV is used to monitor water status of maize across planting dates and will be correlated with ground truth data. Aerial and ground truth data were taken from week four to physiological maturity at a weekly interval. Analysis of variance was used to determine the influence of late planting on maize physiological traits. Preliminary results revealed that planting date affected stomata conductance (sg ), photosynthesis (A ) and transpiration (Tr ). At the third weekly planting (WPD3), plants were exposed to water stress, which led to a decrease in photosynthesis, stomatal conductance and transpiration. These preliminary findings will be correlated with thermal data and crop water stress index calculated to understand changes in water status across planting dates.

Autonomous robot platforms are increasingly being explored as a solution to critical problems in agriculture and in particular high-throughput field-phenotyping for crop-improvement. However, deploying autonomous vehicles in agricultural settings requires developing a complicated technology stack, including a robust hardware platform, reliable autonomy, multi-sensor recording, advanced analytics algorithms, and a data visualization and management pipeline. Without a robust platform in place, agricultural researchers and companies often have no choice but to develop their own robot from scratch. To address this problem EarthSense has developed the TerraSentia platform, capable of end-to-end autonomous data collection and high-precision high-throughput phenotyping in multiple crops. Our TerraSentia platform is capable of autonomous navigation using a planar LiDAR (sweeping horizontally), cameras, GPS, and IMU. It is equipped with four high-definition RGB cameras and a second planar LiDAR (sweeping vertically) for measuring phenotypes. A second UGV model, the TerraSentia+, supports more powerful drivetrain, on-board compute systems, and the ability to modularly configure the sensor stack. Furthermore, EarthSense has developed algorithms for estimating multiple key phenotypes with state-of-the-art precision, including corn plant height, corn ear height, corn stem width, corn nitrogen deficiency, Leaf Area Index (LAI), and soybean pod count. These algorithms are available to users out-of-the-box. Our system has provided estimates for many of these traits on thousands of experimental units over the last 2 years, with a steadily-improving rate of 2700 meters between interventions.

Cotton fibers in the Gossipyum genus are the foundation of a multi-billion-dollar textile industry. Fiber development begins as unicellular trichoblasts emerge from the seed coat epidermis. This hemispherical trichoblast subsequently tapers and executes a complex cell elongation program. The trichoblast transitions to a cellulose-generating machine as it puts down layers of secondary cell wall before cell death and desiccation. Elucidating the multi-scale interactions and feedback controls among cytoskeletal systems, cell wall properties, and changing cell geometries will provide an abundance of opportunities to engineer more favorable traits during fiber development. To meet this long-term goal, we are conducting a "multi-omic" systems level analysis to better understand the fiber elongation process from 5 to 24 days post anthesis. An evolutionarily conserved microtubule-cellulose synthase control module is central to the processes of fiber tapering and anisotropic cell elongation. As such, molecular signatures of transcripts and proteins using quantitative proteomics were profiled and integrated across fiber development. Concurrently, a multi-scale image analysis pipeline was developed. Whole organs and fiber growth was measured under a stereomicroscope, fiber geometry and cellulose microfibril anatomy was characterized with confocal microscopy, and wall thickness was measured via TEM. Changes in the microfibril system are being analyzed in the context of the microtubule-CESA-module of gene expression dynamics. Though correlation of the phenotypic and molecular data is ongoing, these analyses are generating models to predict mechanisms of cellular pathway integration and phenotypic control. Finally, the structural information provides a robust dataset to refine finite element models of fiber growth.

Above-ground biomass (AGB) is one of the key features of understanding forests. Thanks to lidar’s ability to observe the structural characteristics of forests, much research has successfully estimated AGB over diverse forests using airborne lidar (light detection and ranging) data. However, a limited number of studies have focused on the AGB of hardwood forests, which include more complex structural characteristics and require higher-quality lidar data. In this study, we explore the structural information derived from UAS (unoccupied aerial system) lidar data with high point density and estimate the AGB of a hardwood forest, the Martell Forest, Indiana, USA. Particularly, a deep learning-based approach by subplots is proposed in this paper to utilize high-dimensional information of UAS lidar data, considering conventional methods by plots showed the inability to fully exploit the potential of UAS lidar. The experimental results in this paper demonstrate that the UAS lidar data can be alternatively used to investigate hardwood forests in the northern USA.

Feeding the world’s population of 9 billion by 2040 is one of the major challenges of the agriculture sector. Wheat (Triticum aestivum L.) is the second most important staple crop, with a global production of 773 million tonnes per year, but the expected yields need to increase by 60% to ensure future food security. Achieving this requires the development of new cultivars with heightened expression of yield-associated traits, such as radiation use efficiency (RUE), which is fundamental to enhancing plant performance and yield. Recently, plant architectural phenotypes involving leaf inclination angle have shown promising traits in improving RUE at the canopy level. Specifically, the erectophile leaf arrangement exhibits a higher yield potential, receiving more even light distribution than the planophile arrangement, which is susceptible to light saturation on the top layer. This study used a mobile robotic phenotyping system with 3D-multispectral laser scanners and hyperspectral cameras. In 2022 and 2023, data were collected from 100 spring wheat canopies at the heading/anthesis and booting/anthesis stages, respectively. Using 3D data, we estimated canopy tangency angles, identified two architectural phenotypes, and incorporated them into one-dimensional (1D) convolutional neural networks (CNN) to predict canopy-based RUE. Canopy architectural phenotypes in CNN models improved the prediction accuracy of RUE. These findings underscore the potential of canopy architectural traits derived from 3D images as a critical parameter for enhancing RUE predictions in wheat canopies. It could potentially be used in other cereal crops.

Given the changing environmental conditions, understanding internal mechanisms of crops and their interaction with the environment in abiotic stress conditions is very important. To estimate the yield of e.g. wheat, spike and grain traits are used for the selection of resilient genotypes for further breeding programs. Typically, the extraction of these traits is laborious and destructive. With automated X-ray technology a non-destructive screening of spikes can be conducted faster and more accurate. Furthermore, the technology allows extracting additional traits such as center of mass and aspect ratio of each grain, together with the position of the grain within the spike.We present the analysis of 203 wheat accessions carried out using a portable computed-tomography system (CT). The wheat plants were exposed to either drought or combined drought and heat stress. With the EarS algorithm, spike traits were analyzed with an accuracy of 95-99%. The system scanned 4 spikes simultaneously, which resulted in a scanning-time of 7 minutes per spike. To enable a high-throughput acquisition and comparison of wheat traits, we present the required steps for automation. Thus, together with PhenoKey, we developed an automated CT-system with integrated conveyor belt for The Plant Accelerator®, University of Adelaide. This system examines spikes and grains with high throughput. The system has space for 35 spike holders, each of which can carry 30 spikes. This allows a scanning time of 13 seconds per spike. Combined with an automatic data post processing each grain can be identified and linked to the corresponding genotype.

Understanding and enhancing plant resilience traits in maize is critical for ensuring consistent yields in the face of challenging conditions such as drought, disease, and insect pressure. The adoption of drought-resistant and insect-resistant maize varieties has already proven highly beneficial to growers, sparking further interest in uncovering the precise genetic and phenomic factors associated with increased resilience. This study utilized genetic, phenomic, and environmental data collected by Genomes to Fields teams across diverse regions of the United States. These regions exhibited a wide range of climatic conditions, from optimal to stressful, including drought and heat challenges. Leveraging advanced Machine Learning techniques, the study aimed to predict the impact of drought and heat stress on the anthesis-silking interval, a crucial trait influencing yield, and to identify the most effective combination of phenotypes for enhancing drought resilience in maize.

Corn is a cornerstone of the global food supply, but its vulnerability to unpredictable weather patterns, exacerbated by climate change, poses significant challenges to its consistent production. This study aims to enhance maize breeding efforts by identifying genetic markers associated with plant resilience, including the factors of growth rates, stress resistance, disease resistance, overall productivity, and variation in weather. Leveraging previous years of genetic, phenotypic, and drone imagery data from the maize Genomes to Fields project, we conducted a genetic analysis utilizing location-year datasets with varying disease presence, environmental stressors, and weather conditions. The focus was primarily on the anthesis-silking interval (ASI), an essential metric in drought resistance. Machine learning techniques were employed for efficient large-scale data analysis, hypothesis testing, and result interpretation. The outcomes of this research hold immense value for farmers grappling with seasonal droughts and extreme heat. Cultivating crops with a history of weather resilience can serve as a predictive tool, mitigating supply chain disruptions and food shortages, ultimately stabilizing food prices.

Maximizing crop yield is a central goal in agriculture and plant breeding. Several phenotypic traits, including leaf chlorophyll content and canopy greenness, can help predict yield across different varieties. In this study, we aimed to quantify the relationship between leaf chlorophyll concentration, canopy greenness, and crop yield within the Genomes to Fields trials. Our goal was to assess the correlation and enhance predictive modeling between these factors, evaluating the effectiveness of canopy cover and spectral reflectance in predicting yield. We accomplished this by collecting chlorophyll data from multiple leaves within each field plot and utilizing imagery captured by unoccupied aerial systems. This image data provided RGB and multispectral reflectance information on a per-plot basis throughout the growing season, allowing us to model patterns linking chlorophyll concentration and yield for each plot. We integrated data from these two methods with genotypic data from the same maize varieties to explore the fundamental relationships between chlorophyll levels, canopy greenness, and crop yield.

Plant phenotyping technologies have been developing rapidly over the last 2 decades. Plant sensors are becoming more accurate, faster, and easier to use. However, there are still bottleneck issues in plant sensing, including the changing environmental conditions, the plant’s diurnal activities, and the complicated Genotype-by-Treatment-by-Environment interactions. These issues keep plant phenotyping difficult and limit further application of the sensor technologies in precision agriculture. The Purdue Ag Engineers have been working innovatively to develop the next generation sensor technologies to address these issues. In this presentation, Dr. Jin will firstly introduce the four automatic high-throughput phenotyping facilities recently developed at Purdue and explain why they were built and how they’ve been successfully used in detecting diseases, nutrients deficiencies, and chemical damages. He will then introduce ABE’s most recent plant sensor technologies, including the 2021 Davidson Prize winner, LeafSpec, and the new drone and ground-based robots for automatic field phenotyping in different scenarios. Dr. Jin will also briefly share some discovery stories in plant phenotyping, such as how the crop images diurnal variances, and how to leverage the advantages of remote sensing and proximal sensing. 

Carrot (Daucus carota L.) can take up high concentrations of toxic heavy metals like cadmium (Cd) and store them in their edible taproots, leading to food safety risks.  Cd poisoning in humans is strongly linked to damage to the liver, lungs, and bones, as well as prostate, kidney, pancreatic, and testicular cancer.  Cd may also be detrimental to carrot plant growth and nutrient content. A potential way to address this challenge is to select for carrot varieties with lower uptake, however, this is difficult because plants generally exhibit few visible signs of Cd stress. The goal of this study was to determine if hyperspectral imaging can be used as a tool to screen for carrot breeding lines that can withstand Cd stress and restrict uptake, thereby accelerating breeding efforts. To accomplish this goal, we grew 6 carrot breeding lines previously shown to differ in their tendency to accumulate toxic heavy metals like Cd at Purdue’s Ag Alumni Phenotyping Facility (AAPF).  Carrots were either treated or not with cadmium chloride (CdCl2), and imaged with red-green-blue (RGB) and hyperspectral cameras throughout their growth. After 2 months, plants were destructively harvested and Cd and other elements were quantified using ICP.Results of this study verified differences in the uptake of Cd and other elements between the carrot lines, and several reflectance values and vegetative indices have potential to detect Cd stress in carrot plants.