Background: Root system architecture (RSA) traits are of interest for breeding selection; however, measurement of these traits is difficult, resource intensive, and results in large variability. The advent of computer vision and machine learning (ML) enabled trait extraction and measurement has renewed interest in utilizing RSA traits for genetic enhancement to develop more robust and resilient crop cultivars. We developed a mobile, low-cost, and high-resolution root phenotyping system composed of an imaging platform with computer vision and ML based segmentation approach to establish a seamless end-to-end pipeline-from obtaining large quantities of root samples through image based trait processing and analysis. Results: This high throughput phenotyping system, which has the capacity to handle hundreds to thousands of plants, integrates time series image capture coupled with automated image processing that uses optical character recognition (OCR) to identify seedlings via barcode, followed by robust segmentation integrating convolutional autoencoder (CAE) method prior to feature extraction. The pipeline includes an updated and customized version of the Automatic Root Imaging Analysis (ARIA) root phenotyping software. Using this system, we studied diverse soybean accessions from a wide geographical distribution and report genetic variability for RSA traits, including root shape, length, number, mass, and angle. Conclusions: This system provides a high-throughput, cost effective, non-destructive methodology that delivers biologically relevant time-series data on root growth and development for phenomics, genomics, and plant breeding applications. This phenotyping platform is designed to quantify root traits and rank genotypes in a common environment thereby serving as a selection tool for use in plant breeding. Root phenotyping platforms and image based phenotyping are essential to mirror the current focus on shoot phenotyping in breeding efforts.

Root phenotypes are increasingly explored as predictors of crop performance but are still challenging to characterize. Media that mimic field conditions (e.g., soil, sand) are opaque to most forms of radiation, while transparent media do not provide field-relevant growing conditions and phenotypes. We describe here a "transparent soil" formed by the spherification of hydrogels of biopolymers. It is specifically designed to support root growth in the presence of air, water, and nutrients, and allows the time-resolved phenotyping of roots in vivo by both photography and microscopy. The roots developed by soybean plants in this medium are significantly more similar to those developed in real soil than those developed in hydroponic conditions and do not show signs of hypoxia. Lastly, we show that the granular nature and tunable properties of these hydrogel beads can be leveraged to investigate the response of roots to gradients in water availability and soil stiffness. soil | transparent | hydrogels | plants | microbiome G rowing plants for research is constrained by an apparently necessary compromise. On one hand, media that are representative of field soil (e.g., soil, sand) are opaque to most forms of radiation (1) and offer limited control over heterogeneities that affect the development of roots (e.g., gradients in water availability, nutrient concentrations, mechanical properties, porosity). On the other hand, transparent media (e.g., hydroponics, aeroponics, gels) do not provide field-relevant phenotypes and growing conditions (2).Media that have air-filled, connected pores display several physiologically relevant characteristics of soil, such as aeration and physical interfaces (3). Unfortunately, these porous media are usually opaque to most electromagnetic radiation because each interface changes the direction of propagation of photons, due to refraction and reflection. The magnitude of these deflections increases with the difference between the refractive indices (a physical property of matter dependent on electronic density and susceptibility) of the medium and the material contained in the pores (4). Therefore, a porous medium can become transparent to light if it is fully saturated with a fluid whose refractive index matches that of the porous medium (5).Index matching of granular materials, including hydrogels, was used successfully to study hydrology, soil physics, and fluid dynamics in porous media (6, 7). Nonetheless, the use of this approach to study root development is subject to numerous complex constraints that have made this task notoriously challenging. The medium must be (i) produced simply and inexpensively in large quantities (hectoliters), (ii) nontoxic to plants, (iii) transparent enough in common nutrient solutions to allow for the phenotyping of a whole root system in vivo, and (iv) strong enough to not collapse under its own weight. Furthermore, it should provide water and nutrition to the growing plant and have a fully connected porosity to prevent the formation of air pockets. A rece...

Because structural variation in the inflorescence architecture of cereal crops can influence yield, it is of interest to identify the genes responsible for this variation. However, the manual collection of inflorescence phenotypes can be time consuming for the large populations needed to conduct genome-wide association studies (GWAS) and is difficult for multidimensional traits such as volume. A semiautomated phenotyping pipeline, TIM (Toolkit for Inflorescence Measurement), was developed and used to extract unidimensional and multidimensional features from images of 1,064 sorghum (Sorghum bicolor) panicles from 272 genotypes comprising a subset of the Sorghum Association Panel. GWAS detected 35 unique single-nucleotide polymorphisms associated with variation in inflorescence architecture. The accuracy of the TIM pipeline is supported by the fact that several of these trait-associated single-nucleotide polymorphisms (TASs) are located within chromosomal regions associated with similar traits in previously published quantitative trait locus and GWAS analyses of sorghum. Additionally, sorghum homologs of maize (Zea mays) and rice (Oryza sativa) genes known to affect inflorescence architecture are enriched in the vicinities of TASs. Finally, our TASs are enriched within genomic regions that exhibit high levels of divergence between converted tropical lines and cultivars, consistent with the hypothesis that these chromosomal intervals were targets of selection during modern breeding.

Deep learning models have been successfully deployed for a diverse array of image-based plant phenotyping applications including disease detection and classification. However, successful deployment of supervised deep learning models requires large amount of labeled data, which is a significant challenge in plant sciences (and most biological) domain due to the inherent complexities. Specifically, data annotation is costly, laborious, time consuming and needs domain expertise for phenotyping tasks, especially for diseases. To overcome this challenge, active learning algorithms have been proposed to reduce the amount of labeling needed by deep learning models to achieve good predictive performance. Active learning methods work by adaptively suggesting samples to annotate using an acquisition function to achieve maximum (classification) performance under a fixed labeling budget. We report the performance of four different active learning methods, (1) Deep Bayesian Active Learning (DBAL), (2) Entropy, (3) Least Confidence, and (4) core-set, with conventional random sampling-based annotation for two vastly different image-based classification datasets. The first image dataset consists of soybean [Glycine max L. (Merr.)] leaves belonging to eight different soybean stresses and a healthy class, and the second consists of nine different weed species from the field. For a fixed labeling budget, we observed that the classification performance of deep learning models using active learning based acquisition strategies is better than random sampling-based acquisition for both datasets. The integration of active learning strategies for data annotation can help mitigate labelling challenges in the plant sciences applications particularly where resources dedicated to annotations are limited. INTRODUCTIONWith the advent of high throughput phenotyping in plant sciences (

Background Making powder from whey is one of the most challenging parts of whey processing. The present study investigates the performance of a spray dryer for the preparation of whey powder. Its main objective is to categorize unknown samples using analysis of discrimination function between the operating variables and powder properties in two or more naturally occurring groups. In this work, spray drying was performed in a pilot-scale cocurrent spray dryer. The amount of solid content, inlet, and outlet air temperature was chosen as independent variables. The titratable acidity, PH, EC, TDS, analytical elements, particle size diameter, ingredients, and morphology were the response variables that quantify the powder quality. Results The PH of whey powder with 15 % solid content was lower than the PH of whey powder with 30 % solid content. Furthermore, the PH of the whey dried at inlet (outlet) air temperature of 180°C (106°C) was lower than the whey dried at 145°C (87°C). Substances with higher acidity had higher electrical conductivity (EC) as well. The mean particle diameters of the powders produced by pilotplant spray dryer were in the range of 11.26-18.23 lm. SEM picture showed that in pilot-plant spray dryer, there were a few shallow holes on the particle surfaces as well as a few wizened particles. Conclusions It was observed that in the materials with higher acidity, the EC was high and the PH was low. More solid content caused higher viscosities in the feed, which increased the droplet size and consequently, the particle size. By increasing the temperature and heating duration, the amount of PH reduced and the diameter of the particles increased. Moreover, by increasing the percentage of the solid content, the PH increased, while the solid mass carried away by the outlet air decreased. Small particles sprayed by the two-fluid nozzles, led to less amount of TDS. From the morphological point of view, as the industrial samples were exposed to heat longer as compared to pilot-plant samples, they produced spherical and smoother particles.