Plant phenotyping plays a crucial part in the development of new crop genotypes. In this study, the applicability of relatively simple commercially available digital phenotyping devices was tested and improved in the context of wheat variety testing. Aerial thermography is used to evaluate the performance of genotypes by measuring canopy temperature (CT). Because lightweight thermal cameras for drones are prone to significant thermal drift effects due to a lack of a signal stabilizing cooling, we propose a new approach to analyze drone based thermal images. Through the inclusion of covariates such as trigger timing and the position of the drone relative to measured plots, temporal trends and viewing-geometry related effects could be mitigated, which improved the CT measurements. Correlations between measurements on 270 experimental wheat plots taken within 20 min were very strong (R = 0.99) and highly genotype specific with generalized heritabilities > 0.95 in many cases. In a second experiment, autonomous PhenoCams mounted on poles 12 m above the field were evaluated for their suitability to track main phenological stages and senescence as a replacement for time consuming manual field scorings. Senescence and maturity of wheat could be tracked reliably in the field for three subsequent seasons with strong correlations between field-scorings and image-based estimates (R > 0.8). For emergence and heading, achieved correlations were poor. Both experiments demonstrated how image-based phenotyping with a comparably simple setup can be used to derive high quality data relevant in the evaluation of the performance of wheat genotypes in the field.
This paper presents an inventive and precise methodology for measuring tree diameters at specific heights, leveraging iPhones equipped with light detection and ranging (LiDAR) and red, green, and blue (RGB) sensors. Initially, a single snapshot of the tree is captured, incorporating depth and RGB images. Sparse LiDAR data is processed to generate a dense 3D point cloud for each RGB pixel, allowing accurate estimation of the tree trunk’s orientation. This raw 3D point cloud is then standardized, ensuring consistency irrespective of the capture angle. A specific band of transformed 3D points around the target height is selected to estimate the initial diameter and the average distance from the tree to the smartphone camera. To enhance accuracy, a precomputed lookup table is utilized. Experimental results showcase the method’s efficacy, achieving a measurement accuracy of approximately 1.12 cm in mean absolute error and 0.77 cm in root mean square error for 218 trees within a depth range of 0.2 m to 5 m, using an iPhone 13 Pro. This proposed diameter estimation technique proves invaluable for practical forest inventory applications, given its unmatched reliability and precision. Forestry experts and researchers can significantly benefit from this approach, revolutionizing the way tree measurements are conducted in the field. The integration of smartphone technology with advanced sensors marks a pivotal advancement in the realm of forest assessment, paving the way for more accurate and efficient ecological studies and resource management initiatives.
Tree trunk diameter measurement, particularly Diameter at Breast Height (DBH) is a critical task for foresters, indispensable for both the health assessment and market valuation of trees. Traditionally, this measurement has been performed using diameter tapes, a method which is both labor-intensive and time-consuming. In extreme cases where trees are inaccessible, obtaining accurate diameter data becomes particularly challenging. While mobile technology offers a convenient avenue for data collection, most existing algorithms for diameter calculation are not optimized for mobile applications. Wang, et al. has developed a method for diameter calculation utilizing 3D data and tree trunk mask, but it requires clean segmentation of the tree trunk for precise measurement. Advanced AI solutions like SAM exist, but their adaptation for mobile platforms is not yet feasible. In this study, we introduce an efficient method for tree trunk segmentation using 3D Lidar data captured via iPhone devices. Crucially, our approach mitigates issues arising from tilted camera angles and maintains stability in complex background environments. Moreover, we have released an iOS application to facilitate field-testing of this innovative approach. Our method not only simplifies the process but also significantly enhances the accuracy and accessibility of diameter measurements, bridging the gap between advanced algorithms and real-world mobile applications.
Nanoplastic (NP) is an organic contaminant that is widespread in soil, water, and food. However, the effects of NP are not well understood, especially in the context of the rhizosphere-roots-microbiome interface and how they can impact both plants and the soil microbiome. Our hypothesis is that the presence of NP in the soil will lead to distinct changes in the root microbiome and result in a unique phenotype in the plant. To investigate this, we conducted an experiment in which two crops, tomato (Solanum lycopersicum cv. Micro-tom) and lettuce (Lactuca sativa L. cv Canasta), were planted in three different soil conditions: a control group with no NP (zero-NP) and two experimental groups with NP concentrations of 25 and 250 mg.kg-1. The experiment took place over a 41-day period at Purdue’s Ag Alumni Seed Phenotyping Facility. During this time, manual plant measurements and red-green-blue (RGB) and hyperspectral imaging were performed on 17 different dates. After the 41-day growth period, the plants were harvested and weighed, soil from pots and subject to various enzymatic assays to quantifying difference in elemental cycling potential, and DNA was extracted from both the bulk soil and the rhizosphere+roots. The 16S and ITS rRNA genes were then amplified and sequenced using the MiSeq Illumina technology and subject to various bioinformatic programs to quantify differences in composition and functional potential. This study aims to provide insights into how NP affects the rhizosphere, plants, and the associated microbiome, and the results may shed light on the environmental implications of NP contamination.
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.
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.
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.
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.
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.
Plant functional traits capture essential morphological, physiological, or phenological characteristics of plants that influence growth, resource allocation, and survival. These traits can be used to identify plant adaptations to changes in the environment. Functional traits that are indicators of water status in plants can be used to identify adaptative mechanisms to overcome drought. Measuring functional traits using standard approaches is costly, time consuming, and destructive. Vegetation spectroscopy has been shown to estimate a wide variety of plant functional traits, but still can involve extensive field work. Using proximal spectral measurements as a training input for unpiloted aerial vehicle (UAV) collections can potentially bridge spatial gaps between point-based reference and proximal measurements and whole-field UAV measurements. This research proposes a non-destructive approach to transition from proximal spectroscopy to high resolution UAV imagery to predict photosynthetic and water relation traits in maize hybrids grown in two different environments under varying levels of water availability. Both proximal and UAV collected spectral measurements covered the visible, near infrared, and shortwave infrared regions. Partial least squares regression (PLSR) models were developed for both proximal spectra, using reference measurements, and UAV spectra, using proximal predictions as response variable. Many UAV-based PLSR models, including chlorophyll concentration, CO2 assimilation, osmotic potential, and succulence, performed well with goodness of fit statistics over 0.60. These preliminary results highlight the opportunity to advance the capabilities of UAV-based hyperspectral imaging to rapidly and non-destructively predict leaf-level functional traits related to drought, improving breeding approaches and genotype selection.
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.
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.
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.