A Deep Learning Framework for Processing and Classification of Hyperspectral Rice Seed Images Grown under High Day and Night Temperatures.

A framework combining two powerful tools of hyperspectral imaging and deep learning for the processing and classification of hyperspectral images (HSI) of rice seeds is presented. A seed-based approach that trains a three-dimensional convolutional neural network (3D-CNN) using the full seed spectral hypercube for classifying the seed images from high day and high night temperatures, both including a control group, is developed. A pixel-based seed classification approach is implemented using a deep neural network (DNN). The seed and pixel-based deep learning architectures are validated and tested using hyperspectral images from five different rice seed treatments with six different high temperature exposure durations during day, night, and both day and night. A stand-alone application with Graphical User Interfaces (GUI) for calibrating, preprocessing, and classification of hyperspectral rice seed images is presented. The software application can be used for training two deep learning architectures for the classification of any type of hyperspectral seed images. The average overall classification accuracy of 91.33% and 89.50% is obtained for seed-based classification using 3D-CNN for five different treatments at each exposure duration and six different high temperature exposure durations for each treatment, respectively. The DNN gives an average accuracy of 94.83% and 91% for five different treatments at each exposure duration and six different high temperature exposure durations for each treatment, respectively. The accuracies obtained are higher than those presented in the literature for hyperspectral rice seed image classification. The HSI analysis presented here is on the Kitaake cultivar, which can be extended to study the temperature tolerance of other rice cultivars.

Graph Convolutional Network Using Adaptive Neighborhood Laplacian Matrix for Hyperspectral Images with Application to Rice Seed Image Classification.

Graph convolutional neural network architectures combine feature extraction and convolutional layers for hyperspectral image classification. An adaptive neighborhood aggregation method based on statistical variance integrating the spatial information along with the spectral signature of the pixels is proposed for improving graph convolutional network classification of hyperspectral images. The spatial-spectral information is integrated into the adjacency matrix and processed by a single-layer graph convolutional network. The algorithm employs an adaptive neighborhood selection criteria conditioned by the class it belongs to. Compared to fixed window-based feature extraction, this method proves effective in capturing the spectral and spatial features with variable pixel neighborhood sizes. The experimental results from the Indian Pines, Houston University, and Botswana Hyperion hyperspectral image datasets show that the proposed AN-GCN can significantly improve classification accuracy. For example, the overall accuracy for Houston University data increases from 81.71% (MiniGCN) to 97.88% (AN-GCN). Furthermore, the AN-GCN can classify hyperspectral images of rice seeds exposed to high day and night temperatures, proving its efficacy in discriminating the seeds under increased ambient temperature treatments.

Evaluating metabolic and genomic data for predicting grain traits under high night temperature stress in rice.

The asymmetric increase in average nighttime temperatures relative to increase in average daytime temperatures due to climate change is decreasing grain yield and quality in rice. Therefore, a better genome-level understanding of the impact of higher night temperature stress on the weight of individual grains is essential for future development of more resilient rice. We investigated the utility of metabolites obtained from grains to classify high night temperature (HNT) conditions of genotypes, and metabolites and single-nucleotide polymorphisms (SNPs) to predict grain length, width, and perimeter phenotypes using a rice diversity panel. We found that the metabolic profiles of rice genotypes alone could be used to classify control and HNT conditions with high accuracy using random forest or extreme gradient boosting. Best linear unbiased prediction and BayesC showed greater metabolic prediction performance than machine learning models for grain-size phenotypes. Metabolic prediction was most effective for grain width, resulting in the highest prediction performance. Genomic prediction performed better than metabolic prediction. Integrating metabolites and genomics simultaneously in a prediction model slightly improved prediction performance. We did not observe a difference in prediction between the control and HNT conditions. Several metabolites were identified as auxiliary phenotypes that could be used to enhance the multi-trait genomic prediction of grain-size phenotypes. Our results showed that, in addition to SNPs, metabolites collected from grains offer rich information to perform predictive analyses, including classification modeling of HNT responses and regression modeling of grain-size-related phenotypes in rice.

Stress-induced deeper rooting introgression enhances wheat yield under terminal drought.

Water scarcity is the primary environmental constraint affecting wheat growth and production and is increasingly exacerbated due to climatic fluctuation, which jeopardizes future food security. Most breeding efforts to improve wheat yields under drought have focused on above-ground traits. Root traits are closely associated with various drought adaptability mechanisms, but the genetic variation underlying these traits remains untapped, even though it holds tremendous potential for improving crop resilience. Here, we examined this potential by re-introducing ancestral alleles from wild emmer wheat (Triticum turgidum ssp. dicoccoides) and studied their impact on root architecture diversity under terminal drought stress. We applied an active sensing electrical resistivity tomography approach to compare a wild emmer introgression line (IL20) and its drought-sensitive recurrent parent (Svevo) under field conditions. IL20 exhibited greater root elongation under drought, which resulted in higher root water uptake from deeper soil layers. This advantage initiated at the pseudo-stem stage and increased during the transition to the reproductive stage. The increased water uptake promoted higher gas exchange rates and enhanced grain yield under drought. Overall, we show that this presumably 'lost' drought-induced mechanism of deeper rooting profile can serve as a breeding target to improve wheat productiveness under changing climate.

Leaf-Counting in Monocot Plants Using Deep Regression Models.

Leaf numbers are vital in estimating the yield of crops. Traditional manual leaf-counting is tedious, costly, and an enormous job. Recent convolutional neural network-based approaches achieve promising results for rosette plants. However, there is a lack of effective solutions to tackle leaf counting for monocot plants, such as sorghum and maize. The existing approaches often require substantial training datasets and annotations, thus incurring significant overheads for labeling. Moreover, these approaches can easily fail when leaf structures are occluded in images. To address these issues, we present a new deep neural network-based method that does not require any effort to label leaf structures explicitly and achieves superior performance even with severe leaf occlusions in images. Our method extracts leaf skeletons to gain more topological information and applies augmentation to enhance structural variety in the original images. Then, we feed the combination of original images, derived skeletons, and augmentations into a regression model, transferred from Inception-Resnet-V2, for leaf-counting. We find that leaf tips are important in our regression model through an input modification method and a Grad-CAM method. The superiority of the proposed method is validated via comparison with the existing approaches conducted on a similar dataset. The results show that our method does not only improve the accuracy of leaf-counting, with overlaps and occlusions, but also lower the training cost, with fewer annotations compared to the previous state-of-the-art approaches.The robustness of the proposed method against the noise effect is also verified by removing the environmental noises during the image preprocessing and reducing the effect of the noises introduced by skeletonization, with satisfactory outcomes.

Growth and transcriptional response of wheat and rice to the tertiary amine BMVE.

Introduction: Seed vigor is largely a product of sound seed development, maturation processes, genetics, and storage conditions. It is a crucial factor impacting plant growth and crop yield and is negatively affected by unfavorable environmental conditions, which can include drought and heat as well as cold wet conditions. The latter leads to slow germination and increased seedling susceptibility to pathogens. Prior research has shown that a class of plant growth regulators called substituted tertiary amines (STAs) can enhance seed germination, seedling growth, and crop productivity. However, inconsistent benefits have limited STA adoption on a commercial scale. Methods: We developed a novel seed treatment protocol to evaluate the efficacy of 2-(N-methyl benzyl aminoethyl)-3-methyl butanoate (BMVE), which has shown promise as a crop seed treatment in field trials. Transcriptomic analysis of rice seedlings 24 h after BMVE treatment was done to identify the molecular basis for the improved seedling growth. The impact of BMVE on seed development was also evaluated by spraying rice panicles shortly after flower fertilization and subsequently monitoring the impact on seed traits. Results: BMVE treatment of seeds 24 h after imbibition consistently improved wheat and rice seedling shoot and root growth in lab conditions. Treated wheat seedlings grown to maturity in a greenhouse also resulted in higher biomass than controls, though only under drought conditions. Treated seedlings had increased levels of transcripts involved in reactive oxygen species scavenging and auxin and gibberellic acid signaling. Conversely, several genes associated with increased reactive oxygen species/ROS load, abiotic stress responses, and germination hindering processes were reduced. BMVE spray increased both fresh and mature seed weights relative to the control for plants exposed to 96 h of heat stress. BMVE treatment during seed development also benefited germination and seedling growth in the next generation, under both ambient and heat stress conditions. Discussion: The optimized experimental conditions we developed provide convincing evidence that BMVE does indeed have efficacy in plant growth enhancement. The results advance our understanding of how STAs work at the molecular level and provide insights for their practical application to improve crop growth.

A non-destructive approach for measuring rice panicle-level photosynthetic responses using 3D-image reconstruction.

BACKGROUND: Our understanding of the physiological responses of rice inflorescence (panicle) to environmental stresses is limited by the challenge of accurately determining panicle photosynthetic parameters and their impact on grain yield. This is primarily due to the lack of a suitable gas exchange methodology for panicles and non-destructive methods to accurately determine panicle surface area. RESULTS: To address these challenges, we have developed a custom panicle gas exchange cylinder compatible with the LiCor 6800 Infra-red Gas Analyzer. Accurate surface area measurements were determined using 3D panicle imaging to normalize the panicle-level photosynthetic measurements. We observed differential responses in both panicle and flag leaf for two temperate Japonica rice genotypes (accessions TEJ-1 and TEJ-2) exposed to heat stress during early grain filling. There was a notable divergence in the relative photosynthetic contribution of flag leaf and panicles for the heat-tolerant genotype (TEJ-2) compared to the sensitive genotype (TEJ-1). CONCLUSION: The novelty of this method is the non-destructive and accurate determination of panicle area and photosynthetic parameters, enabling researchers to monitor temporal changes in panicle physiology during the reproductive development. The method is useful for panicle-level measurements under diverse environmental stresses and is sensitive enough to evaluate genotypic variation for panicle physiology and architecture in cereals with compact inflorescences.

Rice Chalky Grain 5 regulates natural variation for grain quality under heat stress.

Heat stress occurring during rice (Oryza sativa) grain development reduces grain quality, which often manifests as increased grain chalkiness. Although the impact of heat stress on grain yield is well-studied, the genetic basis of rice grain quality under heat stress is less explored as quantifying grain quality is less tractable than grain yield. To address this, we used an image-based colorimetric assay (Red, R; and Green, G) for genome-wide association analysis to identify genetic loci underlying the phenotypic variation in rice grains exposed to heat stress. We found the R to G pixel ratio (RG) derived from mature grain images to be effective in distinguishing chalky grains from translucent grains derived from control (28/24°C) and heat stressed (36/32°C) plants. Our analysis yielded a novel gene, rice Chalky Grain 5 (OsCG5) that regulates natural variation for grain chalkiness under heat stress. OsCG5 encodes a grain-specific, expressed protein of unknown function. Accessions with lower transcript abundance of OsCG5 exhibit higher chalkiness, which correlates with higher RG values under stress. These findings are supported by increased chalkiness of OsCG5 knock-out (KO) mutants relative to wildtype (WT) under heat stress. Grains from plants overexpressing OsCG5 are less chalky than KOs but comparable to WT under heat stress. Compared to WT and OE, KO mutants exhibit greater heat sensitivity for grain size and weight relative to controls. Collectively, these results show that the natural variation at OsCG5 may contribute towards rice grain quality under heat stress.

Gene Co-expression Network Analysis and Linking Modules to Phenotyping Response in Plants.

Environmental factors, including different stresses, can have an impact on the expression of genes and subsequently the phenotype and development of plants. Since a large number of genes are involved in response to the perturbation of the environment, identifying groups of co-expressed genes is meaningful. The gene co-expression network models can be used for the exploration, interpretation, and identification of genes responding to environmental changes. Once a gene co-expression network is constructed, one can determine gene modules and the association of gene modules to the phenotypic response. To link modules to phenotype, one approach is to find the correlated eigengenes of given modules or to integrate all eigengenes in regularized linear model. This manuscript describes the method from construction of co-expression network, module discovery, association between modules and phenotypic data, and finally to annotation/visualization.

Pervasive misannotation of microexons that are evolutionarily conserved and crucial for gene function in plants.

It is challenging to identify the smallest microexons (≤15-nt) due to their small size. Consequently, these microexons are often misannotated or missed entirely during genome annotation. Here, we develop a pipeline to accurately identify 2,398 small microexons in 10 diverse plant species using 990 RNA-seq datasets, and most of them have not been annotated in the reference genomes. Analysis reveals that microexons tend to have increased detained flanking introns that require post-transcriptional splicing after polyadenylation. Examination of 45 conserved microexon clusters demonstrates that microexons and associated gene structures can be traced back to the origin of land plants. Based on these clusters, we develop an algorithm to genome-wide model coding microexons in 132 plants and find that microexons provide a strong phylogenetic signal for plant organismal relationships. Microexon modeling reveals diverse evolutionary trajectories, involving microexon gain and loss and alternative splicing. Our work provides a comprehensive view of microexons in plants.

Modifying root-to-shoot ratio improves root water influxes in wheat under drought stress.

Drought intensity as experienced by plants depends upon soil moisture status and atmospheric variables such as temperature, radiation, and air vapour pressure deficit. Although the role of shoot architecture with these edaphic and atmospheric factors is well characterized, the extent to which shoot and root dynamic interactions as a continuum are controlled by genotypic variation is less well known. Here, we targeted these interactions using a wild emmer wheat introgression line (IL20) with a distinct drought-induced shift in the shoot-to-root ratio and its drought-sensitive recurrent parent Svevo. Using a gravimetric platform, we show that IL20 maintained higher root water influx and gas exchange under drought stress, which supported a greater growth. Interestingly, the advantage of IL20 in root water influx and transpiration was expressed earlier during the daily diurnal cycle under lower vapour pressure deficit and therefore supported higher transpiration efficiency. Application of a structural equation model indicates that under drought, vapour pressure deficit and radiation are antagonistic to transpiration rate, whereas the root water influx operates as a feedback for the higher atmospheric responsiveness of leaves. Collectively, our results suggest that a drought-induced shift in root-to-shoot ratio can improve plant water uptake potential in a short preferable time window during early morning when vapour pressure deficit is low and the light intensity is not a limiting factor for assimilation.

Ferrihydrite enrichment in the rhizosphere of unsaturated soil improves nutrient retention while limiting arsenic and uranium plant uptake.

Improvement of nutrient use efficiency and limiting trace elements such as arsenic and uranium bioavailability is critical for sustainable agriculture and food safety. Arsenic and uranium possess different properties and mobility in soils, which complicates the effort to reduce their uptake by plants. Here, we postulate that unsaturated soil amended with ferrihydrite nanominerals leads to improved nutrient retention and helps reduce uptake of these geogenic contaminants. Unsaturated soil is primarily oxic and can provide a stable environment for ferrihydrite nanominerals. To demonstrate the utility of ferrihydrite soil amendment, maize was grown in an unsaturated agricultural soil that is known to contain geogenic arsenic and uranium. The soil was maintained at a gravimetric moisture content of 15.1 ± 2.5%, typical of periodically irrigated soils of the US Corn Belt. Synthetic 2-line ferrihydrite was used in low doses as a soil amendment at three levels (0.00% w/w (control), 0.05% w/w and 0.10% w/w). Further, the irrigation water was fortified (~50 µg L-1 each) with elevated arsenic and uranium levels. Plant dry biomass at maturity was ~13.5% higher than that grown in soil not receiving ferrihydrite, indicating positive impact of ferrihydrite on plant growth. Arsenic and uranium concentrations in maize crops (root, shoot and grain combined) were ~ 20% lower in amended soils than that in control soils. Our findings suggest that the addition of low doses of iron nanomineral soil amendment can positively influence rhizosphere geochemical processes, enhancing nutrient plant availability and reduce trace contaminants plant uptake in sprinkler irrigated agroecosystem, which is 55% of total irrigated area in the United States.

HyperSeed: An End-to-End Method to Process Hyperspectral Images of Seeds.

High-throughput, nondestructive, and precise measurement of seeds is critical for the evaluation of seed quality and the improvement of agricultural productions. To this end, we have developed a novel end-to-end platform named HyperSeed to provide hyperspectral information for seeds. As a test case, the hyperspectral images of rice seeds are obtained from a high-performance line-scan image spectrograph covering the spectral range from 600 to 1700 nm. The acquired images are processed via a graphical user interface (GUI)-based open-source software for background removal and seed segmentation. The output is generated in the form of a hyperspectral cube and curve for each seed. In our experiment, we presented the visual results of seed segmentation on different seed species. Moreover, we conducted a classification of seeds raised in heat stress and control environments using both traditional machine learning models and neural network models. The results show that the proposed 3D convolutional neural network (3D CNN) model has the highest accuracy, which is 97.5% in seed-based classification and 94.21% in pixel-based classification, compared to 80.0% in seed-based classification and 85.67% in seed-based classification from the support vector machine (SVM) model. Moreover, our pipeline enables systematic analysis of spectral curves and identification of wavelengths of biological interest.

Wild emmer introgression alters root-to-shoot growth dynamics in durum wheat in response to water stress.

Water deficit during the early vegetative growth stages of wheat (Triticum) can limit shoot growth and ultimately impact grain productivity. Introducing diversity in wheat cultivars to enhance the range of phenotypic responses to water limitations during vegetative growth can provide potential avenues for mitigating subsequent yield losses. We tested this hypothesis in an elite durum wheat background by introducing a series of introgressions from a wild emmer (Triticum turgidum ssp. dicoccoides) wheat. Wild emmer populations harbor rich phenotypic diversity for drought-adaptive traits. To determine the effect of these introgressions on vegetative growth under water-limited conditions, we used image-based phenotyping to catalog divergent growth responses to water stress ranging from high plasticity to high stability. One of the introgression lines exhibited a significant shift in root-to-shoot ratio in response to water stress. We characterized this shift by combining genetic analysis and root transcriptome profiling to identify candidate genes (including a root-specific kinase) that may be linked to the root-to-shoot carbon reallocation under water stress. Our results highlight the potential of introducing functional diversity into elite durum wheat for enhancing the range of water stress adaptation.

Interactive Visualization of Hyperspectral Images Based on Neural Networks.

It is challenging to interpret hyperspectral images in an intuitive and meaningful way, as they usually contain hundreds of dimensions. We develop a visualization tool for hyperspectral images based on neural networks, which allows a user to specify the regions of interest, select bands of interest, and obtain hyperspectral classification results in a scatterplot generated from hyperspectral features. A cascade neural network is trained to generate a scatterplot that matches the cluster centers labeled by the user. The inferred scatterplot not only shows the clusters of points, but also reveals relationships of substances. The trained neural network can be reused for time-varying hyperspectral data analysis without retraining. Our visualization solution can keep domain experts in the analytical loop and provide an intuitive analysis of hyperspectral images while identifying different substances, which are difficult to be realized using existing hyperspectral image analysis techniques.

Transmission Routes of the Microbiome and Resistome from Manure to Soil and Lettuce.

The land application of animal manure can introduce manure microbiome and resistome to croplands where food crops are grown. The objective of this study was to characterize the microbiome and resistome on and in the leaves of lettuce grown in manured soil and identify the main transmission routes of microbes and antibiotic resistance genes (ARGs) from soil to the episphere and endosphere of lettuce. Shotgun metagenomic results show that manure application significantly altered the composition of the microbiome and resistome of surface soil. SourceTracker analyses indicate that manure and original soil were the main source of the microbiome and resistome of the surface soil and rhizosphere soil, respectively. Manure application altered the microbiome and resistome in the episphere of lettuce (ADONIS p < 0.05), and surface soil accounted for ∼81% of the microbes and ∼62% of the ARGs in episphere. Manure application had limited impacts on the microbiome and resistome in the endosphere (ADONIS p > 0.05). Our results show that manure-borne microbes and ARGs reached the episphere primarily through surface soil and some epiphytic microbes and ARGs further entered the endosphere. Our findings can inform the development of pre- and postharvest practices to minimize the transmission of manure-borne resistome from food crops to consumers.

Endoplasmic reticulum stress pathway mediates the early heat stress response of developing rice seeds.

A transient heat stress occurring during early seed development in rice (Oryza sativa) reduces seed size by altering endosperm development. However, the relationship between the timing of the stress and specific developmental stage on heat sensitivity is not well-understood. To address this, we imposed a series of non-overlapping heat stress treatments and found that young seeds are most sensitive during the first two days after flowering. Temporal transcriptome analysis of developing, heat stressed (35°C) seeds during this window shows that Inositol-requiring enzyme 1 (IRE1)-mediated endoplasmic reticulum (ER) stress response and jasmonic acid (JA) pathways are the early (1-3 h) drivers of heat stress response. We propose that increased JA levels under heat stress may precede ER stress response as JA application promotes the spliced form of OsbZIP50, an ER response marker gene linked to IRE1-specific pathway. This study presents temporal and mechanistic insights into the role of JA and ER stress signalling during early heat stress response of rice seeds that impact both grain size and quality. Modulating the heat sensitivity of the early sensing pathways and downstream endosperm development genes can enhance rice resilience to transient heat stress events.

Novel and Transgressive Salinity Tolerance in Recombinant Inbred Lines of Rice Created by Physiological Coupling-Uncoupling and Network Rewiring Effects.

The phenomenon of transgressive segregation, where a small minority of recombinants are outliers relative to the range of parental phenotypes, is commonly observed in plant breeding populations. While this phenomenon has been attributed to complementation and epistatic effects, the physiological and developmental synergism involved have not been fully illuminated by the QTL mapping approach alone, especially for stress-adaptive traits involving highly complex interactions. By systems-level profiling of the IR29 × Pokkali recombinant inbred population of rice, we addressed the hypothesis that novel salinity tolerance phenotypes are created by reconfigured physiological networks due to positive or negative coupling-uncoupling of developmental and physiological attributes of each parent. Real-time growth and hyperspectral profiling distinguished the transgressive individuals in terms of stress penalty to growth. Non-parental network signatures that led to either optimal or non-optimal integration of developmental with stress-related mechanisms were evident at the macro-physiological, biochemical, metabolic, and transcriptomic levels. Large positive net gain in super-tolerant progeny was due to ideal complementation of beneficial traits while shedding antagonistic traits. Super-sensitivity was explained by the stacking of multiple antagonistic traits and loss of major beneficial traits. The synergism uncovered by the phenomics approach in this study supports the modern views of the Omnigenic Theory, emphasizing the synergy or lack thereof between core and peripheral components. This study also supports a breeding paradigm rooted on genomic modeling from multi-dimensional genetic, physiological, and phenotypic profiles to create novel adaptive traits for new crop varieties of the 21st century.

Deciphering the genetic basis of wheat seminal root anatomy uncovers ancestral axial conductance alleles.

Root axial conductance, which describes the ability of water to move through the xylem, contributes to the rate of water uptake from the soil throughout the whole plant lifecycle. Under the rainfed wheat agro-system, grain-filling is typically occurring during declining water availability (i.e., terminal drought). Therefore, preserving soil water moisture during grain filling could serve as a key adaptive trait. We hypothesized that lower wheat root axial conductance can promote higher yields under terminal drought. A segregating population derived from a cross between durum wheat and its direct progenitor wild emmer wheat was used to underpin the genetic basis of seminal root architectural and functional traits. We detected 75 QTL associated with seminal roots morphological, anatomical and physiological traits, with several hotspots harbouring co-localized QTL. We further validated the axial conductance and central metaxylem QTL using wild introgression lines. Field-based characterization of genotypes with contrasting axial conductance suggested the contribution of low axial conductance as a mechanism for water conservation during grain filling and consequent increase in grain size and yield. Our findings underscore the potential of harnessing wild alleles to reshape the wheat root system architecture and associated hydraulic properties for greater adaptability under changing climate.

High night temperature effects on wheat and rice: Current status and way forward.

Rapid increases in minimum night temperature than in maximum day temperature is predicted to continue, posing significant challenges to crop productivity. Rice and wheat are two major staples that are sensitive to high night-temperature (HNT) stress. This review aims to (i) systematically compare the grain yield responses of rice and wheat exposed to HNT stress across scales, and (ii) understand the physiological and biochemical responses that affect grain yield and quality. To achieve this, we combined a synthesis of current literature on HNT effects on rice and wheat with information from a series of independent experiments we conducted across scales, using a common set of genetic materials to avoid confounding our findings with differences in genetic background. In addition, we explored HNT-induced alterations in physiological mechanisms including carbon balance, source-sink metabolite changes and reactive oxygen species. Impacts of HNT on grain developmental dynamics focused on grain-filling duration, post-flowering senescence, changes in grain starch and protein composition, starch metabolism enzymes and chalk formation in rice grains are summarized. Finally, we highlight the need for high-throughput field-based phenotyping facilities for improved assessment of large-diversity panels and mapping populations to aid breeding for increased resilience to HNT in crops.