Context and motivation: Design Thinking techniques have been widely used in the elicitation of software requirements, since such methods obtain satisfying results when applied to understand the necessities of both stakeholders and end-users. However, there is a lack of evidence on their effectiveness when applied to populations considered vulnerable. Question/problem: What are the implications of using Design Thinking techniques to elicit requirements in a community of former inmates - and what would be the benefits of and challenges in this deployment? Principal ideas/results: In this paper, we report our experience on using Design Thinking for Requirements Elicitation of a mobile application, customized for a vulnerable population: the former inmates of the Brazilian Prison System and their families. Research approach and methodology: We utilized the d.school Design Thinking method during our research. Techniques such as Brainstorming, Stakeholder Mapping, Personas Creation, Rapid Ethnography, and Interviews were used to obtain relevant data. Furthermore, during the development process, several prototypes were created. Contribution: The use of these techniques generated important contributions for the development of an uncommon application that aims to help the reintegration process of former inmates into society. The results obtained validate the initial hypothesis that such techniques, even when applied to a sensitive context such as this one, assist in the development of a product that meets the needs of the end-users by creating a higher quality product. Limitations of results: The main limitation of the research was the lack of access to low literacy end-users and/or former inmates without previous experience using mobile devices.

Methemoglobinemia is a rare but fatal disorder of the oxygen-carrying capacity of hemoglobin. Here is a case representing high-dose Sulfamethoxazole/ Trimethoprim ( SMX/TMP ) induced Methemoglobinemia in a boy treated for Ventilator-associated pneumonia (VAP), which was resolved successfully after administration of methylene blue and discontinuation of SMX/TMP

Under the “KISA2-Tai (KANSAI Intensive Area Care Unit for SARS-Cov-2) Osaka” system, which involves a team of several medical institutions, medical care can be provided for COVID-19 patients at home at a level close to that of in-hospital care.

Objectives: The aim of this study was to investigate whether the inhalation of CM-chitosan alleviates tracheal fibrosis in a rabbit. Methods: We designed a method of cauterizing rabbit tracheal stenosis with a spherical electrode electrocoagulation. Twenty New Zealand white rabbits were randomly divided into two groups of ten subjects each: the experimental group using CM-chitosan and the control group．All the subjects were successfully established tracheal damage model using electrocoagulation. On top of this, the experimental group was given 28-days long inhalation of CM-chitosan and the control group was inhaled saline．The effect of the inhalation of CM-chitosan were measured in tracheal fibrosis. Results: Laryngoscopy revealed that the tracheal cross-sectional area of rabbits in the drug group was smaller than that in the saline group. In the drug group, no abnormality was found in Heart, liver, spleen, lung and kidney tissues in HE stain and in non-surgical trachea under scanning electron microscope. Conclusion: These findings demonstrated that the inhalation of CM-chitosan mitigated post-traumatic tracheal fibrosis in a rabbit model，which provided a new way for further treatment study of tracheal stenosis. Key Words: Tracheal fibrosis, tracheal stenosis, CM-chitosan, inhalation, rabbits.

The application of herbicides in agriculture has significantly increased in recent decades. While many herbicides improve the efficiency and efficacy of weed control, their excessive use at the wrong growth stage can cause crop foliar damage, higher input cost and negative environmental footprints. There are limited techniques to accurately monitor herbicide effects. Visual ratings are highly subjective and require extensive training or experience. High-throughput digital imaging is a promising tool to measure plant herbicide interaction in field crops. In this study, proximal and aerial based advanced sensors have been utilized to evaluate different herbicide modes-of-action in two model species, tame oat [Avena sativa; model for wild oat (Avena fatua)] and oriental mustard [Brassica juncea; model for wild mustard (Sinapis arvensis)]. The experimental trials were performed at three agro-climatic locations in Canada (Lethbridge (AB), Saskatoon (SK), and Lacombe (AB)). The proximal and UAV multispectral imagery data were collected for baseline (before treatment) and 1, 3, 7, 10, 14 and 21 days after treatments (DAT), alongside visual ratings. The Normalized Difference Vegetation Index (NDVI), Photochemical Reflectance Index, Chlorophyll Vegetation Index, and Optimized Soil Adjusted Vegetation Index were used to assess variation of different DAT pigment content (photosynthetic rate) and chlorosis (damage %) in plot vegetation. The variation in obtained temporal indices (NDVI) suggest that the developed technology has potential to replace visual ratings (R2 ≈0.65-0.94) and can be used as a rapid screening tool for herbicide activity. Therefore, remote sensing tools could improve the precision and consistency of future herbicide assessments.

The automatic, and accurate plant phenotyping plays important role to improve the crop yield through enabling efficient plant analysis and plant breeding studies. The 3d deep learning has allows automatic segmentation of plant parts from point cloud data. However, the network architecture is designed manually and performance is limited to prior experience. The aim of this study is to search for optimal 3d deep networks to perform the plant part segmentation. We perform the 3d neural architecture search by training a super network composed of candidate networks. Using the trained super network, the evolutionary searching is used to search for top performing architecture. The results demonstrate the searched architecture outperforms manually designed architectures by attaining mean IoU and accuracy of more than 90% and 96%, respectively. The searched architecture achieves more than 83% class-wise IoU for all main stem, branches, and boll class. These plant part segmentation method shows promising results and holds potential to be utilized by plant breeders for enhancing the production quality.

Crop improvement over the last few decades, especially after the Green Revolution, is partially driven by the intensive application of less expensive inorganic nitrogen (N) fertilizer. However, the unsustainable use of inorganic N fertilizer in crop production decreases farming profitability and creates a series of ecological burdens. One of the long-standing goals of crop breeding is to increase crops' nitrogen use efficiency (NUE). Studies have shown a number of phenotypic variations of sorghums grown in different N conditions, including root architecture, leaf parameters, growth parameters, yield, and biochemistry traits. Additionally, previous studies showed that the demand for N varies during the sorghum developmental stages, indicating a dynamic genetic control. In our study, taking advantage of the CRISPR-based gene editing and UNL's automatic high throughput phenotyping platform, we generated five edited sorghum lines under TX430 background and phenotyped them in two N conditions from 30 days after planting to full maturity. We extracted time-series plant growth traits from these edited lines as well as the wild type (i.e., TX430), such as plant height, plant width, and pixel counts, along with vegetation indices. Statistical analyses suggested the distinct N responses between some of the edited lines and the wild type. These N-responsive edited lines will be tested in replicated field trials and potentially be incorporated into the breeding protocol for N-resilient sorghum development.

Maize (Zea mays ssp. Mays) is one of the most essential cereal crops in the world. As climate changes, breeding for high nitrogen-use efficiency maize genetic materials without sacrificing the yield becomes more urgent than anytime before. Image-based high-throughput phenotyping, functioning as a key element in plant breeding efforts, is critically important and has the potential to relieve difficulties in phenotypic scoring on breeding pipelines. Numberless studies using RGB images related to biomass and agronomically important traits have mostly focused on above-ground traits. The belowground root-related traits, however, have not been intensively studied. The objective of this study is to investigate the root architecture and phenotypic properties (number of aerial roots, stem diameter, internode length, and fresh root weight) of roots of the hybrid and inbred maize lines grown under low and high nitrogen conditions. In this study, a collection of BGEM lines (n = 304 inbred and n = 197 hybrids) were planted on the field in low and high nitrogen conditions. The root samples of n = 2,100 plants were collected, and the soil around the roots was washed out for automated image-based phenotyping. The roots were imaged with the completely automated conveyor belt LemnaTec system. A high variation in root structure, stem diameter, number of aerial roots, and internode length was observed among the genotypes. Our root phenotyping pipeline and traits extracted from these images will enhance root biology and facilitate breeding for below-ground root traits.

Advances in phenotyping tools, genomic methodologies, and analytics strategies provide new tools to assess germplasm merit; however, more work is needed to integrate these systems into modern plant breeding approaches. The objective of this work is to integrate genomics and phenomics for yield prediction in maize. A panel of 830 temperate and tropical inbred lines were evaluated for their testcross performance in 2018, and a subset of 400 testcross hybrids were evaluated in 2021 and 2022. These experiments were performed in West Lafayette, IN in a randomized complete block design with two replications. Remote sensing data was collected on a near weekly basis throughout each growing season for RGB (red-green-blue), LiDAR (light detection and ranging), and VNIR (visible near infrared) hyperspectral data and grain yield was harvested with a plot combine. Remote sensing traits extracted include canopy cover, plot volume, plant height, and NDVI. A GBLUP genomic prediction model was used to estimate yield performance in 2018 using data collected in 2021 and 2022. Remote sensing traits were estimated at regular intervals throughout each growing season using random regression modelling. Grain yield was estimated using the genomic estimated yield and the remote sensing traits in a machine learning model. Preliminary results indicate remote sensing can improve prediction accuracy of grain yield compared to genomic prediction alone even with data only collected before flowering. Improved prediction accuracy could benefit hybrid selection, increase genetic gain, and reduce cost in a breeding program.

Hyperspectral imaging is a promising method to predict traits in a high-throughput manner with the potential to unlock quantitative genetic studies. Researchers have successfully modeled physiological traits such as vegetative Nitrogen content, but scope of methodology and lack of truly novel testing data hinder large scale trust in the process. Here, I explore the ability to model leaf Nitrogen content from hyperspectral reflectance data collected with a LeafSpec imaging device on 22 maize hybrids. Three broad strategies based on different input feature sets are undertaken. Strategy one mines data for the most informative hyperspectral channels and then constructs a normalized index similar to NDVI as input features. Strategy two considers all 364 channels of hyperspectral data and makes predictions using various machine learning techniques; partial least squares regression(PLSR), random forest regression, and a feed-forward neural net regression. Strategy three aims to take advantage of the spatial distribution of hyperspectral data on the leaf surface by training a convolutional neural net(CNN). A normalized visual index constructed from bands most correlated with nutrient content out-performed established NDVI. PLSR was the most accurate algorithm, followed by feed-forward neural net and then CNN, based on coefficient of determination score. PLSR is well established as a robust method for hyperspectral prediction which is further evidenced by this study. This is one of the first applications of CNN for hyperspectral data. Despite not being the most accurate algorithm there remains room for hyper-parameter optimization.

Critical factors that determine crop yields are located underground, making them difficult to analyze. Traditionally, these factors have been measured by growing plants in clear media and measuring traits with visible imaging. Modern phenomics technologies use one or several imaging modalities to capture traits that reflect plant physiology or performance. Analytical techniques for plant phenomics are a crucial part of approaches to achieving desirable agronomic and biological traits. Advances in sensor technologies have paved the way for faster and more efficient plant phenotyping, with methods adapted from disciplines like high-resolution 3D X-Ray computed tomography (CT). A crucial step in their analysis is segmentation-the identification and classification of the scan's voxels as "root" or "non-root". Unlike roots in transparent mediums, roots in non-transparent mediums are difficult to segment from their surrounding materials as root and non-root voxels have overlapping CT values. The challenge we address is the development of neural-driven approaches for volumetric semantic segmentation of plant roots in 3D CT scans, and discuss subsequent trait extraction methods that enable the quantification of root systems and their traits in several agriculturally

An organism's phenome results from expression of its genome (nature) under certain environment and management effects (nurture) and interactions between these factors, as well as measurement error. For over 30 years, DNA sequencing and genomics tools advanced to where it's now feasible to saturate genomes of segregating individuals, such that polymorphisms at nearly any position can be determined from other known positions. This is due to structure, linkage disequilibrium (LD), or linkage and is a powerful tool for genomic prediction and investigating biological phenomena. In contrast, most phenomics to date focuses on automating previously known "traits" as measurable and interpretable phenotypes; akin to focusing on measuring a single DNA marker rather than measuring an entire saturated genome. Viewing phenomics as a platform for discovery, similar to genomics, opens new methods for capturing phenomena in nature and nurture. Saturating a phenome would mean that an individual's fitness, performance, responses to environment and/or specific phenotypes could be accurately predicted in untested environments. To date, our experience with phenomic prediction for cumulative, complex phenotypes such as grain yield suggests it's possible to predict organismal performance in untested environments, possibly better than genomic methods despite less advanced tools and data. Factors limiting to saturating a phenome are evaluating enough individuals and environments, but more importantly, tools and methods to extract or "sequence" more phenomic features. Successfully saturating phenomes will impact every aspect of science and society, in biological disciplines from germplasm curators, physiologists to breeders, to education, the courtroom and policy.

Vegetative indices (VIs) collected from an unoccupied aerial vehicle (UAV) equipped with a multi-spectral camera can be used to study growth and development of alfalfa throughout each growth cycle. Random regression models are well suited to fit longitudinal phenotypes such as VIs collected over time to estimate growth curves using covariance functions. Using these functions genetic variation in growth through time can be estimated and the relationships between VIs and end-use traits, like forage yield and quality, can be assessed. The main objectives of this project are (1) to incorporate aerial high-throughput phenotyping to predict performance and genetic merit of the breeding materials, (2) to fit longitudinal random regression models to estimate genotype-specific growth curves and estimate the heritability of key growth parameters. Univariate and multivariate models were used to estimate heritability of image features for alfalfa trial of Helfer, 2020 and 2021. The heritability of different image features in alfalfa ranged from 0-0.78. The preliminary results showed the strongest correlation for Green NDVI and biomass yield (0.4053, 0.7875, and 0.6779), followed by Red edge NDVI and biomass yield (0.417, 0.7898, and 0.6417) for the first, second and third cuttings respectively of the experimental trial located at Helfer, Ithaca for 2020, while the genetic correlations for 2021 were strongest for Red edge NDVI and biomass yield (0.76, 0.74, and 0.66) followed by Green NDVI and biomass yield (0.75, 0.76 and 0.60) for the first, second and third cuttings. The potential of random regression models was investigated using Legendre polynomial functions. Random regression model converged for most of the time points and showed potential for modeling genetic parameters associated with growth and development.

Plant reproduction is sensitive to heat stress. Pollen tube growth can be accelerated or arrested by high temperatures, leading to unstable tubes, failed sperm cell delivery, and ultimately crop yield loss. Pollen growth dynamics have historically been observed on the scale of individual pollen grains, but there are only a few studies surveying pollen populations across genotypes and environmental conditions. Here we describe a phenotyping system that quantifies tomato pollen characteristics on a large scale and under varied heat stress conditions. In this system, we combined high-throughput bright-field microscopy with automated object detection and tracking to investigate the lives of growing pollen tubes. We used this method to survey pollen from a diverse panel of 220 tomato and close wild relative accessions under different temperatures. This method can be readily adapted to pollen from difference species, providing a rapid way to characterize heat stress responses and molecular functions in flowering plants.

This study evaluates a hyperspectral imaging (HSI) technique to identify herbicide-resistant kochia (Bassia scoparia) biotypes to support weed management in cropping systems. The experiment was conducted under controlled-environment where glyphosate was applied to six different kochia populations. For each population (72 cell tray of plants), half of the plants were sprayed with Glyphosate 900 g ae ha-1 , while the other half remained an untreated control. Hyperspectral images were acquired over five time points spanning from glyphosate treatment to 15 days after treatment (DAT) using a proximal HSI system (Specim-IQ) with 204 spectral bands from 397nm to 1003nm. The average reflectances were extracted from plants that were characterized as glyphosate-resistant or-susceptible. We first analyzed the temporal variations of the spectra with and without the application of herbicide. The spectral profile exploits the advantages of temporal features in biotype discrimination. Random forest algorithms were used to classify the glyphosate-resistant and-susceptible populations, by using reflectance at optimal wavelengths (near-infrared) and various vegetation indices with high correlations with visual ratings. Based on the classification accuracy, the most important wavebands and vegetation indices were determined to classify the weed biotypes. Preliminary results show that:  1) For the untreated plants, the reflectance at red-edge to near-infrared reached the highest level on 8 DAT, revealing the highest chlorophyll content in the leaves. Then, the reflectance declined until 15 DAT.  2) In contrast, strong effects of glyphosate were captured on 8 DAT for the three herbicide-susceptible populations. For the three glyphosate-resistant populations, reflectance at red-edge to near-infrared did not increase from 1 to 8 DAT, which was opposite of the controlled plants.

Irrigation of crops accounts for a significant portion of fresh water consumption. In order to utilize this resource more efficiently, it is necessary to engineer crops that can more efficiently use water. Water use efficiency, defined as the ratio of plant growth to water used, is a complex property of plants affected by many different factors. Despite this complexity, genetic variability has been able to be identified in a number of different crops. The C4 model species Setaria viridis remains under-studied in this regard and consequently we sought to identify promising genetic loci contributing to variation in water use efficiency. In order to accomplish this goal we leveraged the high-throughput phenotyping platform at the Donald Danforth Plant Science center to grow S. viridis in well-watered and water-limited conditions. This automated system enables strict control of watering regimes as well as measures of plant traits extracted from photographs using computer vision. Combining these two sets of data allows for direct measurement of whole-plant water-use efficiency on a daily basis which was used as a response variable in a genome wide association study. Significant associations were found for water-use efficiency and related traits. These loci were then prioritized further by pooling information across each day of an experiment and across multiple experiments to zero in on the most likely locations of genes responsible for driving water-use efficiency in S. viridis.

ORCiD: [ORCiD of presenting author] Jaebum Park [0000-0001-6459-909X] AND/OR Max Feldman [0000-0002-5415-4326]Tuber size and shape, colorimetric characteristics of tuber skin and flesh, and tuber defect susceptibility are all factors that influence the adoption of potato cultivars. Despite the importance of these characteristics, our understanding of their inheritance is limited by our inability to precisely measure these features on the scale needed to evaluate breeding populations. To alleviate this bottleneck, we have developed a low-cost, semi-automated workflow to capture data and quantify each of these characteristics using machine vision. This workflow was applied to assess the phenotypic variation present within 189 F1 progeny of the A08241 breeding population and map the genetic basis of tuber characteristics. Several medium-to-large effect, quantitative trait loci (QTL) were found to be associated with different measurements of tuber shape. These results indicate that quantitative measurements acquired using machine vision methods are reliable, heritable, and can be used to map and select upon multiple traits simultaneously in structured potato breeding populations.

Cover crops, plants grown during fallow periods between cash crops, are a promising solution to mitigating soil degradation induced by conventional agricultural practices and improving soil health. Cover crops can provide several beneficial ecosystem functions, such as soil structure remediation, soil microbial diversification, and nutrient recycling, depending on the plant species. Interactions between plant roots and the surrounding soil are key to the plant's ability to perform their ecosystem functions. The lack of data on cover crop roots inhibits our understanding of cover crop phenotype-ecosystem function relationships. We combine aboveground and belowground phenotyping measurements with physicochemical soil measurements to evaluate the field performance of 19 different plant species in monocultures and polycultures as winter cover crops in Missouri. Canopy cover imaging reveals significant differences in winter hardiness and weed suppression among cover crop varieties. Root biomass and root length density measured at depths up to 1 meter indicate differences in rooting behavior between cultivars suggesting the ability to breed cover crop varieties with improved root system architecture. I will also highlight our collaborative efforts utilizing remote sensing technologies (aerial RGB and hyperspectral imaging) to model carbon and nitrogen cycling in cover crop systems at a field scale. Finally, we have begun to characterize 3D root system architecture traits at the seedling stage using a gel-imaging system. Better understanding of cover crop rooting behavior will allow us to breed varieties with enhanced performance of beneficial ecosystem functions for sustainable agricultural systems.

Unmanned aerial vehicle (UAV)-based imagery has become widely used in collecting agronomic traits, enabling a much greater volume of data to be generated in a time-series manner. As one of the cutting-edge imagery analysis tools, machine learning-based object detection provides automated techniques to analyze these imagery data. In our previous study, UAVs have been used to collect aerial photography for field trials of 233 diverse inbred lines, grown under different nitrogen treatments. Images were collected during different plant developmental stages throughout the growing season. This dataset of images has here been used in developing machine learning techniques to obtain automated tassel counts at the plot level through the season. To improve detection accuracy, we have developed an image segmentation method to remove non-tassel pixels and then feed these filtered images into machine learning algorithms. As a result, our method showed a significant improvement in the accuracy of maize tassel detection. This method can be used in future research to produce time-series counts of tassels at the plot level, and will allow for accurate estimates of flowering-related traits, such as the earliest detected flowering date and the duration of each plot's flowering period. This phenotypic data and the trait-associated genes provide new opportunities for crop improvement and to facilitate future plant breeding.

BodyText: A significant portion of plant phenotyping research involves development of new instruments and methodology. Thus, a common experiment is to compare new methods to established ones in order to assess the suitability of the new method. Pearson's correlation coefficient, r, is commonly calculated from the correlation between measurements of the two methods on the same subjects, and it is interpreted to assess whether the new method is a suitable replacement for the established one. However, r (and in this context R, and R 2) is not an appropriate statistic for this purpose, and it provides no meaningful information for comparing quality of methods. This is well established, and other alternatives are known. Here we present quantification and statistical tests of bias and variances of two methods that provide a well-founded approach to method comparison. Comparing newly developed methods to measure height and leaf area index (LAI) using lidar, we find that lidar estimates of height are more precise than established methods and lidar estimates of LAI are equivalent or slightly worse. Using r alone it is not possible to make these interpretations. These sorts of statements are possible due to clear, objective approaches to method comparison, which should be the standard for assessing new phenotyping methods.

Minirhizotron imagery can be used to assess plant root health, and the amount of data for analysis motivates automation of root detection through use of neural networks. Building upon previous work, we show that we can use transfer learning from our PRMI dataset to assess root health across twelve classes of a new dataset to answer questions regarding how root health is affected by access of a tree by large herbivores, site infestation by Pheidole megacephala, and location of the tree. This dataset was collected from three paired sites at the Ol Pejeta Conservancy in Laikipia, Kenya, and consists of 20,000 images collected between September 2021 and May 2022. Each paired site represents four locations based on all four possible combinations of site infestation by Pheidole megacephala for at least 20 years and existence of herbivore-exclusion fence to keep large herbivores out. 1,332 images across all twelve classes of site and treatment combination were labeled with respective ground truths for model training. Our work uses the UNet architecture using pretrained weights on the network encoder and decoder which were obtained in 2019 in work which achieved over 99% accuracy on a dataset of peanut and switchgrass imagery. In our work, we found that training the model with our new dataset resulted in consistent performance across all classes of our new dataset, with over 99% accuracy for each class.

High night air temperature stress (HNT) challenges rice production. Findings indicate 10% yield reduction for every 1 o C of increase in night air temperature. The responses of rice to HNT stress have been analyzed in limited number of genotypes mostly under greenhouse conditions. One of the limits for these studies under field conditions is implementing HNT stress on critical rice growth stage. The physiological and metabolic responses of rice to HNT stress under field conditions are not fully understood, thus, field studies are needed. Field-based phenotyping infrastructure that can house rice germplasm and stress imposition using computer-based system basing on ambient temperature still do not exist. In this study, six high tunnel greenhouses were built in a field experimental station in Harrisburg, AR in a split-plot design. These movable infrastructures fitted 310 rice accessions from the Rice Diversity Panel 1 (RDP1) and 10 hybrids from RiceTec. Each high tunnel greenhouse had heating and a cyber-physical system that recorded ambient air temperature and increased night air temperature relative to ambient temperature at the flowering stage. The system successfully imposed HNT stress of 4.01 o C and 3.94 o C as recorded by Raspberry Pi sensors for two weeks in the 2019 and 2020 cropping seasons, respectively. These greenhouses were able to endure constant flooding and resist heavy rain and 40-50 miles/h winds. Grain quality and other biochemical assays are still ongoing to fully assess the effects of HNT in the rice accessions and the hybrids.

The structures of roots play an essential role in plant growth, development, and stress responses. Minirhizotron imaging is one of the widely used approaches to capture and analyze root systems. After segmenting minirhizotron images, every individual root is separated from each other and the background. Root traits, like root lengths and diameter distributions, can provide information about the health of the plants. Current methods to analyze minirhizotron images usually rely on manually annotated labels and commercial software tools, which are time and labor-consuming. Unfortunately, these current methods usually generate a statistical analysis of the input image rather than the features of each root. In this work, we propose a pipeline to automatically use deep neural networks to segment roots from the background and then extract root features like lengths and diameter distributions from the individual segmented root. In detail, we first use a pre-trained U-Net to segment the roots in the minirhizotron images. Then, we separate each individual root with the help of connected component analysis. Finally, we extract the features like diameter distribution or root lengths of every individual root with morphological operations, like skeletonization. For evaluation, we conduct experiments on synthetic roots, which are made of strings and threads, and compare results against a benchmark root dataset (PRMI) of real switchgrass roots and compare the estimated results with the existing commercial software.

Most current phenotype plant research focuses primarily on above-ground traits, like leaves and flowers. Roots often get comparatively less attention because they are challenging to examine and image. Minirhizotron (MR) systems are one of the imaging approaches to studying plant roots underground. In MR systems, a tube is inserted into the ground to allow a camera to be inserted to capture the images of root systems. Unlike minirhizotron imaging, X-ray computed tomography (CT) captures the three-dimensional (3D) information of soil cores extracted from the soil. For a better analysis of roots, the first step is always to segment the roots from the background in the images or image sequences. The results of root segmentation play an essential role in further analysis like root diameter and length estimation. Current fully-supervised segmentation methods mainly use pixel/point-level annotated labels, which require much manual effort and time. In this work, we propose a weakly supervised root segmentation approach with graph convolutional networks. Our model only requires image-level annotations to segment roots from the images or image sequences. In detail, our model first constructs graphs for the neighboring pixels/points and then learns the distinguishable features used as hints for segmentation by training a classifier based on the image-level annotations. Finally, post-processing procedures like principal component analysis (PCA) are applied to refine the final segmentation results. We conduct experiments on the challenging 2D PRMI minirhizotron benchmark and 3D switchgrass root X-ray CT datasets for evaluation.