High-throughput profiling and analysis of plant responses over time to abiotic stress

Explainable deep learning in plant phenotyping

The increasing human population and variable weather conditions, due to climate change, pose a threat to the world's food security. To improve global food security, we need to provide breeders with tools to develop crop cultivars that are more resilient to extreme weather conditions and provide growers with tools to more effectively manage biotic and abiotic stresses in their crops. Plant phenotyping, the measurement of a plant's structural and functional characteristics, has the potential to inform, improve and accelerate both breeders' selections and growers' management decisions. To improve the speed, reliability and scale of plant phenotyping procedures, many researchers have adopted deep learning methods to estimate phenotypic information from images of plants and crops. Despite the successful results of these image-based phenotyping studies, the representations learned by deep learning models remain difficult to interpret, understand, and explain. For this reason, deep learning models are still considered to be black boxes. Explainable AI (XAI) is a promising approach for opening the deep learning model's black box and providing plant scientists with image-based phenotypic information that is interpretable and trustworthy. Although various fields of study have adopted XAI to advance their understanding of deep learning models, it has yet to be well-studied in the context of plant phenotyping research. In this review article, we reviewed existing XAI studies in plant shoot phenotyping, as well as related domains, to help plant researchers understand the benefits of XAI and make it easier for them to integrate XAI into their future studies. An elucidation of the representations within a deep learning model can help researchers explain the model's decisions, relate the features detected by the model to the underlying plant physiology, and enhance the trustworthiness of image-based phenotypic information used in food production systems.

Rice nitrogen nutrition monitoring classification method based on the convolution neural network model: Direct detection of rice nitrogen nutritional status

The nitrogen nutrition status affects the main factors of rice yield. In traditional rice nitrogen nutrition monitoring methods, most experts enter the farmland to observe leaf color and growth and apply an appropriate amount of nitrogen fertilizer according to the results. However, this method is labor- and time-consuming. To realize automatic rice nitrogen nutrition monitoring, we constructed the Jiangxi rice nitrogen nutrition monitoring model based on a convolution neural network (CNN) using the same region rice canopy image in different generation periods. Our CNN model was evaluated using multiple evaluation criteria (Accuracy, Recall, Precision, and F1 score). The results show that the same CNN model could distinguish the rice nitrogen nutrition status in different periods, which can completely realize the automatic discrimination of nitrogen nutrition status so as to guide the scientific nitrogen application of rice in this area. This will greatly improve the discrimination efficiency of the nitrogen nutrition status and reduce the time and labor cost. The application of the proposed method also proved that the CNN model can be applied in the discrimination of the nitrogen nutrition status. Among CNN models, GoogleNet model proposed a CNN architecture named Inception which can improve the depth of the network and extract higher-level features without changing the amount of calculation of the model. The GoogleNet model achieved the highest accuracy, 95.7%.

Identification of beneficial and detrimental bacteria impacting sorghum responses to drought using multi-scale and multi-system microbiome comparisons

Drought is a major abiotic stress limiting agricultural productivity. Previous field-level experiments have demonstrated that drought decreases microbiome diversity in the root and rhizosphere. How these changes ultimately affect plant health remains elusive. Toward this end, we combined reductionist, transitional and ecological approaches, applied to the staple cereal crop sorghum to identify key root-associated microbes that robustly affect drought-stressed plant phenotypes. Fifty-three Arabidopsis-associated bacteria were applied to sorghum seeds and their effect on root growth was monitored. Two Arthrobacter strains caused root growth inhibition (RGI) in Arabidopsis and sorghum. In the context of synthetic communities, Variovorax strains were able to protect plants from Arthrobacter-caused RGI. As a transitional system, high-throughput phenotyping was used to test the synthetic communities. During drought stress, plants colonized by Arthrobacter had reduced growth and leaf water content. Plants colonized by both Arthrobacter and Variovorax performed as well or better than control plants. In parallel, we performed a field trial wherein sorghum was evaluated across drought conditions. By incorporating data on soil properties into the microbiome analysis, we accounted for experimental noise with a novel method and were able to observe the negative correlation between the abundance of Arthrobacter and plant growth. Having validated this approach, we cross-referenced datasets from the high-throughput phenotyping and field experiments and report a list of bacteria with high confidence that positively associated with plant growth under drought stress. In conclusion, a three-tiered experimental system successfully spanned the lab-to-field gap and identified beneficial and deleterious bacterial strains for sorghum under drought.

Increased signal-to-noise ratios within experimental field trials by regressing spatially distributed soil properties as principal components

Environmental variability poses a major challenge to any field study. Researchers attempt to mitigate this challenge through replication. Thus, the ability to detect experimental signals is determined by the degree of replication and the amount of environmental variation, noise, within the experimental system. A major source of noise in field studies comes from the natural heterogeneity of soil properties which create microtreatments throughout the field. In addition, the variation within different soil properties is often nonrandomly distributed across a field. We explore this challenge through a sorghum field trial dataset with accompanying plant, microbiome, and soil property data. Diverse sorghum genotypes and two watering regimes were applied in a split-plot design. We describe a process of identifying, estimating, and controlling for the effects of spatially distributed soil properties on plant traits and microbial communities using minimal degrees of freedom. Importantly, this process provides a method with which sources of environmental variation in field data can be identified and adjusted, improving our ability to resolve effects of interest and to quantify subtle phenotypes.

Capturing crop adaptation to abiotic stress using image-based technologies

Farmers and breeders aim to improve crop responses to abiotic stresses and secure yield under adverse environmental conditions. To achieve this goal and select the most resilient genotypes, plant breeders and researchers rely on phenotyping to quantify crop responses to abiotic stress. Recent advances in imaging technologies allow researchers to collect physiological data non-destructively and throughout time, making it possible to dissect complex plant responses into quantifiable traits. The use of image-based technologies enables the quantification of crop responses to stress in both controlled environmental conditions and field trials. This paper summarizes phenotyping imaging technologies (RGB, multispectral and hyperspectral sensors, among others) that have been used to assess different abiotic stresses including salinity, drought and nitrogen deficiency, while discussing their advantages and drawbacks. We present a detailed review of traits involved in abiotic tolerance, which have been quantified by a range of imaging sensors under high-throughput phenotyping facilities or using unmanned aerial vehicles in the field. We also provide an up-to-date compilation of spectral tolerance indices and discuss the progress and challenges in machine learning, including supervised and unsupervised models as well as deep learning.

Sorghum Ionomics Reveals the Functional SbHMA3a Allele that Limits Excess Cadmium Accumulation in Grains

Understanding uptake and redistribution of essential minerals or sequestering of toxic elements is important for optimized crop production. Although the mechanisms controlling mineral transport have been elucidated in rice and other species, little is understood in sorghum-an important C4 cereal crop. Here, we assessed the genetic factors that govern grain ionome profiles in sorghum using recombinant inbred lines (RILs) derived from a cross between BTx623 and NOG (Takakibi). Pairwise correlation and clustering analysis of 22 elements, measured in sorghum grains harvested under greenhouse conditions, indicated that the parental lines, as well as the RILs, show different ionomes. In particular, BTx623 accumulated significantly higher levels of cadmium (Cd) than NOG, because of differential root-to-shoot translocation factors between the two lines. Quantitative trait locus (QTL) analysis revealed a prominent QTL for grain Cd concentration on chromosome 2. Detailed analysis identified SbHMA3a, encoding a P1B-type ATPase heavy metal transporter, as responsible for low Cd accumulation in grains; the NOG allele encoded a functional HMA3 transporter (SbHMA3a-NOG) whose Cd-transporting activity was confirmed by heterologous expression in yeast. BTx623 possessed a truncated, loss-of-function SbHMA3a allele. The functionality of SbHMA3a in NOG was confirmed by Cd concentrations of F2 grains derived from the reciprocal cross, in which the NOG allele behaved in a dominant manner. We concluded that SbHMA3a-NOG is a Cd transporter that sequesters excess Cd in root tissues, as shown in other HMA3s. Our findings will facilitate the isolation of breeding cultivars with low Cd in grains or in exploiting high-Cd cultivars for phytoremediation.

Exploiting High-Throughput Indoor Phenotyping to Characterize the Founders of a Structured B. napus Breeding Population

Phenotyping is considered a significant bottleneck impeding fast and efficient crop improvement. Similar to many crops, Brassica napus, an internationally important oilseed crop, suffers from low genetic diversity, and will require exploitation of diverse genetic resources to develop locally adapted, high yielding and stress resistant cultivars. A pilot study was completed to assess the feasibility of using indoor high-throughput phenotyping (HTP), semi-automated image processing, and machine learning to capture the phenotypic diversity of agronomically important traits in a diverse B. napus breeding population, SKBnNAM, introduced here for the first time. The experiment comprised 50 spring-type B. napus lines, grown and phenotyped in six replicates under two treatment conditions (control and drought) over 38 days in a LemnaTec Scanalyzer 3D facility. Growth traits including plant height, width, projected leaf area, and estimated biovolume were extracted and derived through processing of RGB and NIR images. Anthesis was automatically and accurately scored (97% accuracy) and the number of flowers per plant and day was approximated alongside relevant canopy traits (width, angle). Further, supervised machine learning was used to predict the total number of raceme branches from flower attributes with 91% accuracy (linear regression and Huber regression algorithms) and to identify mild drought stress, a complex trait which typically has to be empirically scored (0.85 area under the receiver operating characteristic curve, random forest classifier algorithm). The study demonstrates the potential of HTP, image processing and computer vision for effective characterization of agronomic trait diversity in B. napus, although limitations of the platform did create significant variation that limited the utility of the data. However, the results underscore the value of machine learning for phenotyping studies, particularly for complex traits such as drought stress resistance.

Smart Indoor Farms: Leveraging Technological Advancements to Power a Sustainable Agricultural Revolution

Conventional farming necessitates a large number of resources and infrastructure such as land, irrigation, manpower to manage farms, etc. Modern initiatives are required to automate conventional farms. Smart indoor farms offer the potential to remedy the shortfalls of conventional farms by providing a controlled, intelligent, and smart environment. This paper presents a three-dimensional perspective consisting of soilless farming, energy harvesting, and smart technologies, which could be considered as the three important characteristics of smart indoor farms. A six-layer smart indoor farms architecture has also been proposed, which explains how data are collected using various sensors and devices and then transmitted onto the cloud infrastructure for further analysis and control through various layers. Artificial lighting, smart nutrition management, and artificial climate control, to name a few, are some of the important requirements for smart indoor farms while considering control and service management factors. The major bottleneck in installing such systems is both the economical and the technical constraints. However, with the evolution of technology (and when they become widely available in the near future), a more favourable farming scenario may emerge. Furthermore, smart indoor farms could be viewed as a potential answer for meeting the demands of a sustainable agricultural revolution as we move closer to Agriculture 4.0. Finally, in order to adapt smart indoor farms and their study scope, our work has presented various research areas to potential researchers.

Resources for image-based high-throughput phenotyping in crops and data sharing challenges

High-throughput phenotyping (HTP) platforms are capable of monitoring the phenotypic variation of plants through multiple types of sensors, such as red green and blue (RGB) cameras, hyperspectral sensors, and computed tomography, which can be associated with environmental and genotypic data. Because of the wide range of information provided, HTP datasets represent a valuable asset to characterize crop phenotypes. As HTP becomes widely employed with more tools and data being released, it is important that researchers are aware of these resources and how they can be applied to accelerate crop improvement. Researchers may exploit these datasets either for phenotype comparison or employ them as a benchmark to assess tool performance and to support the development of tools that are better at generalizing between different crops and environments. In this review, we describe the use of image-based HTP for yield prediction, root phenotyping, development of climate-resilient crops, detecting pathogen and pest infestation, and quantitative trait measurement. We emphasize the need for researchers to share phenotypic data, and offer a comprehensive list of available datasets to assist crop breeders and tool developers to leverage these resources in order to accelerate crop breeding.

QTL x environment interactions underlie ionome divergence in switchgrass

Ionomics measures elemental concentrations in biological organisms and provides a snapshot of physiology under different conditions. In this study, we evaluate genetic variation of the ionome in outbred, perennial switchgrass in three environments across the species' native range, and explore patterns of genotype-by-environment interactions. We grew 725 clonally replicated genotypes of a large full sib family from a four-way linkage mapping population, created from deeply diverged upland and lowland switchgrass ecotypes, at three common gardens. Concentrations of 18 mineral elements were determined in whole post-anthesis tillers using ion coupled plasma mass spectrometry (ICP-MS). These measurements were used to identify quantitative trait loci (QTL) with and without QTL-by-environment interactions (QTLxE) using a multi-environment QTL mapping approach. We found that element concentrations varied significantly both within and between switchgrass ecotypes, and GxE was present at both the trait and QTL level. Concentrations of 14 of the 18 elements were under some genetic control, and 77 QTL were detected for these elements. 74% of QTL colocalized multiple elements, half of QTL exhibited significant QTLxE, and roughly equal numbers of QTL had significant differences in magnitude and sign of their effects across environments. The switchgrass ionome is under moderate genetic control and by loci with highly variable effects across environments.

Monitoring Plant Status and Fertilization Strategy through Multispectral Images

A crop monitoring system was developed for the supervision of organic fertilization status on tomato plants at early stages. An automatic and nondestructive approach was used to analyze tomato plants with different levels of water-soluble organic fertilizer (3 + 5 NK) and vermicompost. The evaluation system was composed by a multispectral camera with five lenses: green (550 nm), red (660 nm), red edge (735 nm), near infrared (790 nm), RGB, and a computational image processing system. The water-soluble fertilizer was applied weekly in four different treatments: (T0: 0 mL, T1: 6.25 mL, T2: 12.5 mL and T3: 25 mL) and the vermicomposting was added in Weeks 1 and 5. The trial was conducted in a greenhouse and 192 images were taken with each lens. A plant segmentation algorithm was developed and several vegetation indices were calculated. On top of calculating indices, multiple morphological features were obtained through image processing techniques. The morphological features were revealed to be more feasible to distinguish between the control and the organic fertilized plants than the vegetation indices. The system was developed in order to be assembled in a precision organic fertilization robotic platform.

Latent Space Phenotyping: Automatic Image-Based Phenotyping for Treatment Studies

Association mapping studies have enabled researchers to identify candidate loci for many important environmental tolerance factors, including agronomically relevant tolerance traits in plants. However, traditional genome-by-environment studies such as these require a phenotyping pipeline which is capable of accurately measuring stress responses, typically in an automated high-throughput context using image processing. In this work, we present Latent Space Phenotyping (LSP), a novel phenotyping method which is able to automatically detect and quantify response-to-treatment directly from images. We demonstrate example applications using data from an interspecific cross of the model C₄ grass Setaria, a diversity panel of sorghum (S. bicolor), and the founder panel for a nested association mapping population of canola (Brassica napus L.). Using two synthetically generated image datasets, we then show that LSP is able to successfully recover the simulated QTL in both simple and complex synthetic imagery. We propose LSP as an alternative to traditional image analysis methods for phenotyping, enabling the phenotyping of arbitrary and potentially complex response traits without the need for engineering-complicated image-processing pipelines.

Antiviral ARGONAUTEs Against Turnip Crinkle Virus Revealed by Image-Based Trait Analysis

RNA-based silencing functions as an important antiviral immunity mechanism in plants. Plant viruses evolved to encode viral suppressors of RNA silencing (VSRs) that interfere with the function of key components in the silencing pathway. As effectors in the RNA silencing pathway, ARGONAUTE (AGO) proteins are targeted by some VSRs, such as that encoded by Turnip crinkle virus (TCV). A VSR-deficient TCV mutant was used to identify AGO proteins with antiviral activities during infection. A quantitative phenotyping protocol using an image-based color trait analysis pipeline on the PlantCV platform, with temporal red, green, and blue imaging and a computational segmentation algorithm, was used to measure plant disease after TCV inoculation. This process captured and analyzed growth and leaf color of Arabidopsis (Arabidopsis thaliana) plants in response to virus infection over time. By combining this quantitative phenotypic data with molecular assays to detect local and systemic virus accumulation, AGO2, AGO3, and AGO7 were shown to play antiviral roles during TCV infection. In leaves, AGO2 and AGO7 functioned as prominent nonadditive, anti-TCV effectors, whereas AGO3 played a minor role. Other AGOs were required to protect inflorescence tissues against TCV. Overall, these results indicate that distinct AGO proteins have specialized, modular roles in antiviral defense across different tissues, and demonstrate the effectiveness of image-based phenotyping to quantify disease progression.

An automated, high-throughput method for standardizing image color profiles to improve image-based plant phenotyping

High-throughput phenotyping has emerged as a powerful method for studying plant biology. Large image-based datasets are generated and analyzed with automated image analysis pipelines. A major challenge associated with these analyses is variation in image quality that can inadvertently bias results. Images are made up of tuples of data called pixels, which consist of R, G, and B values, arranged in a grid. Many factors, for example image brightness, can influence the quality of the image that is captured. These factors alter the values of the pixels within images and consequently can bias the data and downstream analyses. Here, we provide an automated method to adjust an image-based dataset so that brightness, contrast, and color profile is standardized. The correction method is a collection of linear models that adjusts pixel tuples based on a reference panel of colors. We apply this technique to a set of images taken in a high-throughput imaging facility and successfully detect variance within the image dataset. In this case, variation resulted from temperature-dependent light intensity throughout the experiment. Using this correction method, we were able to standardize images throughout the dataset, and we show that this correction enhanced our ability to accurately quantify morphological measurements within each image. We implement this technique in a high-throughput pipeline available with this paper, and it is also implemented in PlantCV.