A Comprehensive Review of High Throughput Phenotyping and Machine Learning for Plant Stress Phenotyping

Confronting the data deluge: How artificial intelligence can be used in the study of plant stress

The advent of the genomics era enabled the generation of high-throughput data and computational methods that serve as powerful hypothesis-generating tools to understand the genomic and gene functional basis of plant stress resilience. The proliferation of experimental and analytical methods used in biology has resulted in a situation where plentiful data exists, but the volume and heterogeneity of this data has made analysis a significant challenge. Current advanced deep-learning models have displayed an unprecedented level of comprehension and problem-solving ability, and have been used to predict gene structure, function and expression based on DNA or protein sequence, and prominently also their use in high-throughput phenomics in agriculture. However, the application of deep-learning models to understand gene regulatory and signalling behaviour is still in its infancy. We discuss in this review the availability of data resources and bioinformatic tools, and several applications of these advanced ML/AI models in the context of plant stress response, and demonstrate the use of a publicly available LLM (ChatGPT) to derive a knowledge graph of various experimental and computational methods used in the study of plant stress. We hope this will stimulate further interest in collaboration between computer scientists, computational biologists and plant scientists to distil the deluge of genomic, transcriptomic, proteomic, metabolomic and phenomic data into meaningful knowledge that can be used for the benefit of humanity.

Explainable light-weight deep learning pipeline for improved drought stress identification

Introduction

Early identification of drought stress in crops is vital for implementing effective mitigation measures and reducing yield loss. Non-invasive imaging techniques hold immense potential by capturing subtle physiological changes in plants under water deficit. Sensor-based imaging data serves as a rich source of information for machine learning and deep learning algorithms, facilitating further analysis that aims to identify drought stress. While these approaches yield favorable results, real-time field applications require algorithms specifically designed for the complexities of natural agricultural conditions.

Methods

Our work proposes a novel deep learning framework for classifying drought stress in potato crops captured by unmanned aerial vehicles (UAV) in natural settings. The novelty lies in the synergistic combination of a pre-trained network with carefully designed custom layers. This architecture leverages the pre-trained network's feature extraction capabilities while the custom layers enable targeted dimensionality reduction and enhanced regularization, ultimately leading to improved performance. A key innovation of our work is the integration of gradient-based visualization inspired by Gradient-Class Activation Mapping (Grad-CAM), an explainability technique. This visualization approach sheds light on the internal workings of the deep learning model, often regarded as a "black box". By revealing the model's focus areas within the images, it enhances interpretability and fosters trust in the model's decision-making process.

Results and discussion

Our proposed framework achieves superior performance, particularly with the DenseNet121 pre-trained network, reaching a precision of 97% to identify the stressed class with an overall accuracy of 91%. Comparative analysis of existing state-of-the-art object detection algorithms reveals the superiority of our approach in achieving higher precision and accuracy. Thus, our explainable deep learning framework offers a powerful approach to drought stress identification with high accuracy and actionable insights.

Application of Image-Based Phenotyping for QTL Identification of Tiller Angle in Rice (Oryza sativa L.)

Rice tiller angle is a key agronomic trait that regulates plant architecture and plays a critical role in determining rice yield. Given that tiller angle is regulated by multiple genes, it is important to identify quantitative trait loci (QTL) associated with tiller angle. Recently, with the advancement of imaging technology for plant phenotyping, it has become possible to quickly and accurately measure agronomic traits of breeding populations. In this study, we extracted tiller angle and various image-based parameters from Red-Green-Blue (RGB) images of a recombinant inbred line (RIL) population derived from a cross between Milyang23 (Indica) and Giho (Japonica). Correlations among the obtained data were analyzed, and through dynamic QTL mapping, five major QTLs (qTA1, qTA1-1, qTA2, qTA2-1, and qTA9) related to tiller angle were detected on chromosomes 1, 2, and 9. Among them, 26 candidate genes related to auxin signaling and plant growth, including the TAC1 (Tiller Angle Control 1) gene, were identified in qTA9 (RM257-STS09048). These results demonstrate the potential of image-based phenotyping to overcome the limitations of traditional manual measurements in crop structure research. Furthermore, the identification of key QTLs and candidate genes related to tiller angle provides valuable genetic insights for the development of high-yielding varieties through crop morphology control.

Phenotyping cotton leaf chlorophyll via in situ hyperspectral reflectance sensing, spectral vegetation indices, and machine learning

Cotton (Gossypium hirsutum L.) leaf chlorophyll (Chl) has been targeted as a phenotype for breeding selection to improve cotton tolerance to environmental stress. However, high-throughput phenotyping methods based on hyperspectral reflectance sensing are needed to rapidly screen cultivars for chlorophyll in the field. The objectives of this study were to deploy a cart-based field spectroradiometer to measure cotton leaf reflectance in two field experiments over four growing seasons at Maricopa, Arizona and to evaluate 148 spectral vegetation indices (SVI's) and 14 machine learning methods (MLM's) for estimating leaf chlorophyll from spectral information. Leaf tissue was sampled concurrently with reflectance measurements, and laboratory processing provided leaf Chl a, Chl b, and Chl a+b as both areas-basis (µg cm-2) and mass-basis (mg g-1) measurements. Leaf reflectance along with several data transformations involving spectral derivatives, log-inverse reflectance, and SVI's were evaluated as MLM input. Models trained with 2019-2020 data performed poorly in tests with 2021-2022 data (e.g., RMSE=23.7% and r2 = 0.46 for area-basis Chl a+b), indicating difficulty transferring models between experiments. Performance was more satisfactory when training and testing data were based on a random split of all data from both experiments (e.g., RMSE=10.5% and r2 = 0.88 for area basis Chl a+b), but performance beyond the conditions of the present study cannot be guaranteed. Performance of SVI's was in the middle (e.g., RMSE=16.2% and r2 = 0.69 for area-basis Chl a+b), and SVI's provided more consistent error metrics compared to MLM's. Ensemble MLM's which combined estimates from several base estimators (e.g., random forest, gradient booting, and AdaBoost regressors) and a multi-layer perceptron neural network method performed best among MLM's. Input features based on spectral derivatives or SVI's improved MLM's performance compared to inputting reflectance data. Spectral reflectance data and SVI's involving red edge radiation were the most important inputs to MLM's for estimation of cotton leaf chlorophyll. Because MLM's struggled to perform beyond the constraints of their training data, SVI's should not be overlooked as practical plant trait estimators for high-throughput phenotyping, whereas MLM's offer great opportunity for data mining to develop more robust indices.

Integrating non-invasive VIS-NIR and bioimpedance spectroscopies for stress classification of sweet basil (Ocimum basilicum L.) with machine learning

Plant stress diagnosis is essential for efficient crop management and productivity increase. Under stress, plants undergo physiological and compositional changes. Vegetation indices obtained from leaf reflectance spectra and bioimpedance spectroscopy provide information about the external and internal aspects of plant responses, respectively. In this study, bioimpedance and vegetation indices were noninvasively acquired from sweet basil (Ocimum basilicum L.) leaves exposed to three types of stress (drought, salinity, and chilling). Integrating the vegetation index, a novel approach, contains information about the surface of plants and bioimpedance data, which indicates the internal changes of plants. The fusion of these two datasets was examined to classify the types and severity of stress. Among the eight supervised machine learning models (three linear and five non-linear), the support vector machine (SVM) exhibited the highest accuracy in classifying stress types. Bioimpedance spectroscopy alone exhibited an accuracy of 0.86 and improved to 0.90 when fused with vegetation indices. Additionally, for drought and salinity stresses, it was possible to classify the early stage of stress with accuracies of 0.95 and 0.93, respectively. This study will allow us to classify the different types and severity of plant stress, prescribe appropriate treatment methods for efficient cost and time management of crop production, and potentially apply them to low-cost field measurement systems.

Complementary approaches to dissect late leaf rust resistance in an interspecific raspberry population

Over the last 10 years, global raspberry production has increased by 47.89%, based mainly on the red raspberry species (Rubus idaeus). However, the black raspberry (Rubus occidentalis), although less consumed, is resistant to one of the most important diseases for the crop, the late leaf rust caused by Acculeastrum americanum fungus. In this context, genetic resistance is the most sustainable way to control the disease, mainly because there are no registered fungicides for late leaf rust in Brazil. Therefore, the aim was to understand the genetic architecture that controls resistance to late leaf rust in raspberries. For that, we used an interspecific multiparental population using the species mentioned above as parents, 2 different statistical approaches to associate the phenotypes with markers [GWAS (genome-wide association studies) and copula graphical models], and 2 phenotyping methodologies from the first to the 17th day after inoculation (high-throughput phenotyping with a multispectral camera and traditional phenotyping by disease severity scores). Our findings indicate that a locus of higher effect, at position 13.3 Mb on chromosome 5, possibly controls late leaf rust resistance, as both GWAS and the network suggested the same marker. Of the 12 genes flanking its region, 4 were possible receptors, 3 were likely defense executors, 1 gene was likely part of signaling cascades, and 4 were classified as nondefense related. Although the network and GWAS indicated the same higher effect genomic region, the network identified other different candidate regions, potentially complementing the genetic control comprehension.

Identification of diterpenoids from Salvia castanea Diels f. tomentosa Stib and their antitumor activities

Four new diterpenoid tropolones, salvirrddones A-D (1-4), and four new icetexanes, salvirrddices A-D (9-12), along with thirteen new 11,12-seco-norabietane diterpenoids, salvirrddnor A-M (14-24, 31, 32) and sixteen known compounds (5-8, 13, 25-30, 33-37), were isolated from the roots and rhizomes of Salvia castanea Diels f. tomentosa Stib. Their structures were elucidated by comprehensive spectroscopic analyses, quantum chemical calculations, and X-ray crystallography. Structurally, compounds 1-8 represent a class of rare natural products featuring a unique cyclohepta-2,4,6-trienone moiety with diterpenoid skeletons. Bioassays showed that only diterpenoid tropolones 3, 5, 6, and 7 exhibited significant activity against several human cancer cell lines with IC50 values ranging from 3.01 to 11.63 μM. Additionally, 3 was shown to inhibit Hep3B cell proliferation, block the G0/G1 phase of the cell cycle, induce mitochondrial dysfunction and oxidative stress, promote apoptosis, as well as inhibit migration and invasion in vitro. Meanwhile, 3 demonstrated anti-proliferative, pro-apoptotic, and migration-inhibitory effects in the Hep3B xenograft zebrafish model in vivo. Network pharmacological analysis and molecular docking results suggested that 3 may treat hepatocellular carcinoma (HCC) through the PI3K-Akt signaling pathway, as well as by binding PARP1 and CDK2 targets. Overall, the present results extremely expand the repertoire of diterpenoids from natural products and may provide a novel chemical scaffold for the discovery of new antitumor drugs.

High-Throughput Phenotyping of Soybean Biomass: Conventional Trait Estimation and Novel Latent Feature Extraction Using UAV Remote Sensing and Deep Learning Models

High-throughput phenotyping serves as a framework to reduce chronological costs and accelerate breeding cycles. In this study, we developed models to estimate the phenotypes of biomass-related traits in soybean (Glycine max) using unmanned aerial vehicle (UAV) remote sensing and deep learning models. In 2018, a field experiment was conducted using 198 soybean germplasm accessions with known whole-genome sequences under 2 irrigation conditions: drought and control. We used a convolutional neural network (CNN) as a model to estimate the phenotypic values of 5 conventional biomass-related traits: dry weight, main stem length, numbers of nodes and branches, and plant height. We utilized manually measured phenotypes of conventional traits along with RGB images and digital surface models from UAV remote sensing to train our CNN models. The accuracy of the developed models was assessed through 10-fold cross-validation, which demonstrated their ability to accurately estimate the phenotypes of all conventional traits simultaneously. Deep learning enabled us to extract features that exhibited strong correlations with the output (i.e., phenotypes of the target traits) and accurately estimate the values of the features from the input data. We considered the extracted low-dimensional features as phenotypes in the latent space and attempted to annotate them based on the phenotypes of conventional traits. Furthermore, we validated whether these low-dimensional latent features were genetically controlled by assessing the accuracy of genomic predictions. The results revealed the potential utility of these low-dimensional latent features in actual breeding scenarios.

Insights into the responses of Akabare chili landraces to drought, heat, and their combined stress during pre-flowering and fruiting stages

Drought, heat, and their combined stress have increasingly become common phenomena in horticulture, significantly reducing chili production worldwide. The current study aimed to phenotype Akabare chili landraces (Capsicum spp.) in climate chambers subjected to drought and heat treatments during their early generative stage, focusing on PSII efficacy (Fv/Fm), net photosynthetic rate (P N), stomatal conductance (g s), leaf cooling, and biomass production. Six landraces were examined under heat and control conditions at 40/32 °C for 4 days and at 30/22 °C under drought and control conditions followed by a 5-day recovery under control conditions (30/22 °C, irrigated). Two landraces with higher (>0.77) and two with lower (<0.763) Fv/Fm during the stress treatments were later evaluated in the field under 55-day-long drought stress at the fruiting stage. In both treatments, stress-tolerant landraces maintained high Fv/Fm, P N, and better leaf cooling leading to improved biomass compared to the sensitive landraces. Agro-morpho-physiological responses of the tolerant and sensitive landraces during the early generative stage echoed those during the fruiting stage in the field. A climate chamber experiment revealed a 13.9 % decrease in total biomass under heat stress, a further 21.5 % reduction under drought stress, and a substantial 38.7 % decline under combine stress. In field conditions, drought stress reduced total biomass by 28.1 % and total fruit dry weight by 26.2 %. Tolerant landraces showed higher Fv/Fm, demonstrated better wilting scores, displayed a higher chlorophyll content index (CCI), and accumulated more biomass. This study validated lab-based results through field trials and identified two landraces, C44 and DKT77, as potential stress-tolerant genotypes. It recommends Fv/Fm, P N, and CCI as physiological markers for the early detection of stress tolerance.

Prediction accuracy and repeatability of UAV based biomass estimation in wheat variety trials as affected by variable type, modelling strategy and sampling location

BACKGROUND

This study explores the use of Unmanned Aerial Vehicles (UAVs) for estimating wheat biomass, focusing on the impact of phenotyping and analytical protocols in the context of late-stage variety selection programs. It emphasizes the importance of variable selection, model specificity, and sampling location within the experimental plot in predicting biomass, aiming to refine UAV-based estimation techniques for enhanced selection accuracy and throughput in variety testing programs.

RESULTS

The research uncovered that integrating geometric and spectral traits led to an increase in prediction accuracy, whilst a recursive feature elimination (RFE) based variable selection workflowled to slight reductions in accuracy with the benefit of increased interpretability. Models, tailored to specific experiments were more accurate than those modelling all experiments together, while models trained for broad-growth stages did not significantly increase accuracy. The comparison between a permanent and a precise region of interest (ROI) within the plot showed negligible differences in biomass prediction accuracy, indicating the robustness of the approach across different sampling locations within the plot. Significant differences in the within-season repeatability (w2) of biomass predictions across different experiments highlighted the need for further investigation into the optimal timing of measurement for prediction.

CONCLUSIONS

The study highlights the promising potential of UAV technology in biomass prediction for wheat at a small plot scale. It suggests that the accuracy of biomass predictions can be significantly improved through optimizing analytical and modelling protocols (i.e., variable selection, algorithm selection, stage-specific model development). Future work should focus on exploring the applicability of these findings under a wider variety of conditions and from a more diverse set of genotypes.

Affordable Phenotyping at the Edge for High-Throughput Detection of Hypersensitive Reaction Involving Cotyledon Loss

The use of low-cost depth imaging sensors is investigated to automate plant pathology tests. Spatial evolution is explored to discriminate plant resistance through the hypersensitive reaction involving cotyledon loss. A high temporal frame rate and a protocol operating with batches of plants enable to compensate for the low spatial resolution of depth cameras. Despite the high density of plants, a spatial drop of the depth is observed when the cotyledon loss occurs. We introduce a small and simple spatiotemporal feature space which is shown to carry enough information to automate the discrimination between batches of resistant (loss of cotyledons) and susceptible plants (no loss of cotyledons) with 97% accuracy and with a timing 30 times faster than for human annotation. The robustness of the method-in terms of density of plants in the batch and possible internal batch desynchronization-is assessed successfully with hundreds of varieties of Pepper in various environments. A study on the generalizability of the method suggests that it can be extended to other pathosystems and also to segregating plants, i.e., intermediate state with batches composed of resistant and susceptible plants. The imaging system developed, combined with the feature extraction method and classification model, provides a full pipeline with unequaled throughput and cost efficiency by comparison with the state-of-the-art one. This system can be deployed as a decision-support tool but is also compatible with a standalone technology where computation is done at the edge in real time.

Controlled Environment Ecosystem: A Cutting-Edge Technology in Speed Breeding

The controlled environment ecosystem is a meticulously designed plant growing chamber utilized for cultivating biofortified crops and microgreens, addressing hidden hunger and malnutrition prevalent in the growing population. The integration of speed breeding within such controlled environments effectively eradicates morphological disruptions encountered in traditional breeding methods such as inbreeding depression, male sterility, self-incompatibility, embryo abortion, and other unsuccessful attempts. In contrast to the unpredictable climate conditions that often prolong breeding cycles to 10-15 years in traditional breeding and 4-5 years in transgenic breeding within open ecosystems, speed breeding techniques expedite the achievement of breeding objectives and F1-F6 generations within 2-3 years under controlled growing conditions. In comparison, traditional breeding may take 5-10 years for plant population line creation, 3-5 years for field trials, and 1-2 years for variety release. The effectiveness of speed breeding in trait improvement and population line development varies across different crops, requiring approximately 4 generations in rice and groundnut, 5 generations in soybean, pea, and oat, 6 generations in sorghum, Amaranthus sp., and subterranean clover, 6-7 generations in bread wheat, durum wheat, and chickpea, 7 generations in broad bean, 8 generations in lentil, and 10 generations in Arabidopsis thaliana annually within controlled environment ecosystems. Artificial intelligence leverages neural networks and algorithm models to screen phenotypic traits and assess their role in diverse crop species. Moreover, in controlled environment systems, mechanistic models combined with machine learning effectively regulate stable nutrient use efficiency, water use efficiency, photosynthetic assimilation product, metabolic use efficiency, climatic factors, greenhouse gas emissions, carbon sequestration, and carbon footprints. However, any negligence, even minor, in maintaining optimal photoperiodism, temperature, humidity, and controlling pests or diseases can lead to the deterioration of crop trials and speed breeding techniques within the controlled environment system. Further comparative studies are imperative to comprehend and justify the efficacy of climate management techniques in controlled environment ecosystems compared to natural environments, with or without soil.

Quantifying aluminum toxicity effects on corn phenotype using advanced imaging technologies

Soil acidity (pH <5.5) limits agricultural production due to aluminum (Al) toxicity. The primary target of Al toxicity is the plant root. However, symptoms can be observed on the shoots. This study aims to determine the potential use of chlorophyll fluorescence imaging, multispectral imaging, and 3D multispectral scanning technology to quantify the effects of Al toxicity on corn. Corn seedlings were grown for 13 days in nutrient solutions (pH 4.0) with four Al treatments: 50, 100, 200, and 400 μM and a control (0 μM AlCl3 L-1). During the experiment, four measurements were performed: four (MT1), six (MT2), 11 (MT3), and 13 (MT4) days after the application of Al treatments. The most sensitive traits affected by Al toxicity were the reduction of plant growth and increased reflectance in the visible wavelength (affected at MT1). The reflectance of red wavelengths increased more significantly compared to near-infrared and green wavelengths, leading to a decrease in the normalized difference vegetation index and the Green Leaf Index. The most sensitive chlorophyll fluorescence traits, effective quantum yield of PSII, and photochemical quenching coefficient were affected after prolonged Al exposure (MT3). This study demonstrates the usability of selected phenotypic traits in remote sensing studies to map Al-toxic soils and in high-throughput phenotyping studies to screen Al-tolerant genotypes.

IHUP: An Integrated High-Throughput Universal Phenotyping Software Platform to Accelerate Unmanned-Aerial-Vehicle-Based Field Plant Phenotypic Data Extraction and Analysis

With the threshold for crop growth data collection having been markedly decreased by sensor miniaturization and cost reduction, unmanned aerial vehicle (UAV)-based low-altitude remote sensing has shown remarkable advantages in field phenotyping experiments. However, the requirement of interdisciplinary knowledge and the complexity of the workflow have seriously hindered researchers from extracting plot-level phenotypic data from multisource and multitemporal UAV images. To address these challenges, we developed the Integrated High-Throughput Universal Phenotyping (IHUP) software as a data producer and study accelerator that included 4 functional modules: preprocessing, data extraction, data management, and data analysis. Data extraction and analysis requiring complex and multidisciplinary knowledge were simplified through integrated and automated processing. Within a graphical user interface, users can compute image feature information, structural traits, and vegetation indices (VIs), which are indicators of morphological and biochemical traits, in an integrated and high-throughput manner. To fulfill data requirements for different crops, extraction methods such as VI calculation formulae can be customized. To demonstrate and test the composition and performance of the software, we conducted case-related rice drought phenotype monitoring experiments. In combination with a rice leaf rolling score predictive model, leaf rolling score, plant height, VIs, fresh weight, and drought weight were efficiently extracted from multiphase continuous monitoring data. Despite the significant impact of image processing during plot clipping on processing efficiency, the software can extract traits from approximately 500 plots/min in most application cases. The software offers a user-friendly graphical user interface and interfaces for customizing or integrating various feature extraction algorithms, thereby significantly reducing barriers for nonexperts. It holds the promise of significantly accelerating data production in UAV phenotyping experiments.

High-throughput phenotyping using VIS/NIR spectroscopy in the classification of soybean genotypes for grain yield and industrial traits

Employing visible and near infrared sensors in high-throughput phenotyping provides insight into the relationship between the spectral characteristics of the leaf and the content of grain properties, helping soybean breeders to direct their program towards improving grain traits according to researchers' interests. Our research hypothesis is that the leaf reflectance of soybean genotypes can be directly related to industrial grain traits such as protein and fiber contents. Thus, the objectives of the study were: (i) to classify soybean genotypes according to the grain yield and industrial traits; (ii) to identify the algorithm(s) with the highest accuracy for classifying genotypes using leaf reflectance as model input; (iii) to identify the best input data for the algorithms to improve their performance. A field experiment was carried out in randomized block design with three replications and 32 soybean genotypes. At 60 days after emergence, spectral analysis was carried out on three leaf samples from each plot. A hyperspectral sensor was used to capture reflectance between the wavelengths from 450 to 824 nm. Representative spectral bands were selected and grouped into means. After harvest, grain yield was assessed and laboratory analyses of industrial traits were carried out. Spectral, industrial traits and yield data were subjected to statistical analysis. Data were analyzed by the following machine learning algorithms: J48 (J48) and REPTree (DT) decision trees, Random Forest (RF), Artificial Neural Networks (ANN), Support Vector Machine (SVM), and conventional Logistic Regression (LR) analysis. The clusters formed were used as the output of the models, while two groups of input data were used for the input of the models: the spectral variables (WL) noise-free obtained by the sensor (450-828 nm) and the spectral means of the selected bands (SB) (450.0-720.6 nm). Soybean genotypes were grouped according to their grain yield and industrial traits, in which the SVM and J48 algorithms performed better at classifying them. Using the spectral bands selected in the study improved the classification accuracy of the algorithms.

Strong culm: a crucial trait for developing next-generation climate-resilient rice lines

Lodging, a phenomenon characterized by the bending or breaking of rice plants, poses substantial constraints on productivity, particularly during the harvesting phase in regions susceptible to strong winds. The rice strong culm trait is influenced by the intricate interplay of genetic, physiological, epigenetic, and environmental factors. Stem architecture, encompassing morphological and anatomical attributes, alongside the composition of both structural and non-structural carbohydrates, emerges as a critical determinant of lodging resistance. The adaptive response of the rice culm to various biotic and abiotic environmental factors further modulates the propensity for lodging. Advancements in next-generation sequencing technologies have expedited the genetic dissection of lodging resistance, enabling the identification of pertinent genes, quantitative trait loci, and novel alleles. Concurrently, contemporary breeding strategies, ranging from biparental approaches to more sophisticated methods such as multi-parent-based breeding, gene pyramiding, genomic selection, genome-wide association studies, and haplotype-based breeding, offer perspectives on the genetic underpinnings of culm strength. This review comprehensively delves into physiological attributes, culm histology, epigenetic determinants, and gene expression profiles associated with lodging resistance, with a specialized focus on leveraging next-generation sequencing for candidate gene discovery.

Deciphering temporal growth patterns in maize: integrative modeling of phenotype dynamics and underlying genomic variations

Quantifying the temporal or longitudinal growth dynamics of crops in diverse environmental conditions is crucial for understanding plant development, requiring further modeling techniques. In this study, we analyzed the growth patterns of two different maize (Zea mays L.) populations using high-throughput phenotyping with a maize population consisting of 515 recombinant inbred lines (RILs) grown in Texas and a hybrid population containing 1090 hybrids grown in Missouri. Two models, Gaussian peak and functional principal component analysis (FPCA), were employed to study the Normalized Green-Red Difference Index (NGRDI) scores. The Gaussian peak model showed strong correlations (c. 0.94 for RILs and c. 0.97 for hybrids) between modeled and non-modeled temporal trajectories. Functional principal component analysis differentiated NGRDI trajectories in RILs under different conditions, capturing substantial variability (75%, 20%, and 5% for RILs; 88% and 12% for hybrids). By comparing these models with conventional BLUP values, common quantitative trait loci (QTLs) were identified, containing candidate genes of brd1, pin11, zcn8 and rap2. The harmony between these loci's additive effects and growing degree days, as well as the differentiation of RIL haplotypes across growth stages, underscores the significant interplay of these loci in driving plant development. These findings contribute to advancing understanding of plant-environment interactions and have implications for crop improvement strategies.

Climate Change-The Rise of Climate-Resilient Crops

Climate change disrupts food production in many regions of the world. The accompanying extreme weather events, such as droughts, floods, heat waves, and cold snaps, pose threats to crops. The concentration of carbon dioxide also increases in the atmosphere. The United Nations is implementing the climate-smart agriculture initiative to ensure food security. An element of this project involves the breeding of climate-resilient crops or plant cultivars with enhanced resistance to unfavorable environmental conditions. Modern agriculture, which is currently homogeneous, needs to diversify the species and cultivars of cultivated plants. Plant breeding programs should extensively incorporate new molecular technologies, supported by the development of field phenotyping techniques. Breeders should closely cooperate with scientists from various fields of science.

Cyber-agricultural systems for crop breeding and sustainable production

The cyber-agricultural system (CAS) represents an overarching framework of agriculture that leverages recent advances in ubiquitous sensing, artificial intelligence, smart actuators, and scalable cyberinfrastructure (CI) in both breeding and production agriculture. We discuss the recent progress and perspective of the three fundamental components of CAS - sensing, modeling, and actuation - and the emerging concept of agricultural digital twins (DTs). We also discuss how scalable CI is becoming a key enabler of smart agriculture. In this review we shed light on the significance of CAS in revolutionizing crop breeding and production by enhancing efficiency, productivity, sustainability, and resilience to changing climate. Finally, we identify underexplored and promising future directions for CAS research and development.

Plant science in the age of simulation intelligence

Historically, plant and crop sciences have been quantitative fields that intensively use measurements and modeling. Traditionally, researchers choose between two dominant modeling approaches: mechanistic plant growth models or data-driven, statistical methodologies. At the intersection of both paradigms, a novel approach referred to as "simulation intelligence", has emerged as a powerful tool for comprehending and controlling complex systems, including plants and crops. This work explores the transformative potential for the plant science community of the nine simulation intelligence motifs, from understanding molecular plant processes to optimizing greenhouse control. Many of these concepts, such as surrogate models and agent-based modeling, have gained prominence in plant and crop sciences. In contrast, some motifs, such as open-ended optimization or program synthesis, still need to be explored further. The motifs of simulation intelligence can potentially revolutionize breeding and precision farming towards more sustainable food production.

Can Grapevine Leaf Water Potential Be Modelled from Physiological and Meteorological Variables? A Machine Learning Approach

Climate change is affecting global viticulture, increasing heatwaves and drought. Precision irrigation, supported by robust water status indicators (WSIs), is inevitable in most of the Mediterranean basin. One of the most reliable WSIs is the leaf water potential (Ψleaf), which is determined via an intrusive and time-consuming method. The aim of this work is to discern the most effective variables that are correlated with plants' water status and identify the variables that better predict Ψleaf. Five grapevine varieties grown in the Alentejo region (Portugal) were selected and subjected to three irrigation treatments, starting in 2018: full irrigation (FI), deficit irrigation (DI), and no irrigation (NI). Plant monitoring was performed in 2023. Measurements included stomatal conductance (gs), predawn water potential Ψpd, stem water potential (Ψstem), thermal imaging, and meteorological data. The WSIs, namely Ψpd and gs, responded differently according to the irrigation treatment. Ψstem measured at mid-morning (MM) and mid-day (MD) proved unable to discern between treatments. MM measurements presented the best correlations between WSIs. gs showed the best correlations between the other WSIs, and consequently the best predictive capability to estimate Ψpd. Machine learning regression models were trained on meteorological, thermal, and gs data to predict Ψpd, with ensemble models showing a great performance (ExtraTrees: R2=0.833, MAE=0.072; Gradient Boosting: R2=0.830; MAE=0.073).

Redesigning crop varieties to win the race between climate change and food security

Climate change poses daunting challenges to agricultural production and food security. Rising temperatures, shifting weather patterns, and more frequent extreme events have already demonstrated their effects on local, regional, and global agricultural systems. Crop varieties that withstand climate-related stresses and are suitable for cultivation in innovative cropping systems will be crucial to maximize risk avoidance, productivity, and profitability under climate-changed environments. We surveyed 588 expert stakeholders to predict current and novel traits that may be essential for future pearl millet, sorghum, maize, groundnut, cowpea, and common bean varieties, particularly in sub-Saharan Africa. We then review the current progress and prospects for breeding three prioritized future-essential traits for each of these crops. Experts predict that most current breeding priorities will remain important, but that rates of genetic gain must increase to keep pace with climate challenges and consumer demands. Importantly, the predicted future-essential traits include innovative breeding targets that must also be prioritized; for example, (1) optimized rhizosphere microbiome, with benefits for P, N, and water use efficiency, (2) optimized performance across or in specific cropping systems, (3) lower nighttime respiration, (4) improved stover quality, and (5) increased early vigor. We further discuss cutting-edge tools and approaches to discover, validate, and incorporate novel genetic diversity from exotic germplasm into breeding populations with unprecedented precision, accuracy, and speed. We conclude that the greatest challenge to developing crop varieties to win the race between climate change and food security might be our innovativeness in defining and boldness to breed for the traits of tomorrow.

An Integrated Multi-Omics and Artificial Intelligence Framework for Advance Plant Phenotyping in Horticulture

This review discusses the transformative potential of integrating multi-omics data and artificial intelligence (AI) in advancing horticultural research, specifically plant phenotyping. The traditional methods of plant phenotyping, while valuable, are limited in their ability to capture the complexity of plant biology. The advent of (meta-)genomics, (meta-)transcriptomics, proteomics, and metabolomics has provided an opportunity for a more comprehensive analysis. AI and machine learning (ML) techniques can effectively handle the complexity and volume of multi-omics data, providing meaningful interpretations and predictions. Reflecting the multidisciplinary nature of this area of research, in this review, readers will find a collection of state-of-the-art solutions that are key to the integration of multi-omics data and AI for phenotyping experiments in horticulture, including experimental design considerations with several technical and non-technical challenges, which are discussed along with potential solutions. The future prospects of this integration include precision horticulture, predictive breeding, improved disease and stress response management, sustainable crop management, and exploration of plant biodiversity. The integration of multi-omics and AI holds immense promise for revolutionizing horticultural research and applications, heralding a new era in plant phenotyping.

High-throughput phenotyping for non-destructive estimation of soybean fresh biomass using a machine learning model and temporal UAV data

BACKGROUND

Biomass accumulation as a growth indicator can be significant in achieving high and stable soybean yields. More robust genotypes have a better potential for exploiting available resources such as water or sunlight. Biomass data implemented as a new trait in soybean breeding programs could be beneficial in the selection of varieties that are more competitive against weeds and have better radiation use efficiency. The standard techniques for biomass determination are invasive, inefficient, and restricted to one-time point per plot. Machine learning models (MLMs) based on the multispectral (MS) images were created so as to overcome these issues and provide a non-destructive, fast, and accurate tool for in-season estimation of soybean fresh biomass (FB). The MS photos were taken during two growing seasons of 10 soybean varieties, using six-sensor digital camera mounted on the unmanned aerial vehicle (UAV). For model calibration, canopy cover (CC), plant height (PH), and 31 vegetation index (VI) were extracted from the images and used as predictors in the random forest (RF) and partial least squares regression (PLSR) algorithm. To create a more efficient model, highly correlated VIs were excluded and only the triangular greenness index (TGI) and green chlorophyll index (GCI) remained.

RESULTS

More precise results with a lower mean absolute error (MAE) were obtained with RF (MAE = 0.17 kg/m2) compared to the PLSR (MAE = 0.20 kg/m2). High accuracy in the prediction of soybean FB was achieved using only four predictors (CC, PH and two VIs). The selected model was additionally tested in a two-year trial on an independent set of soybean genotypes in drought simulation environments. The results showed that soybean grown under drought conditions accumulated less biomass than the control, which was expected due to the limited resources.

CONCLUSION

The research proved that soybean FB could be successfully predicted using UAV photos and MLM. The filtration of highly correlated variables reduced the final number of predictors, improving the efficiency of remote biomass estimation. The additional testing conducted in the independent environment proved that model is capable to distinguish different values of soybean FB as a consequence of drought. Assessed variability in FB indicates the robustness and effectiveness of the proposed model, as a novel tool for the non-destructive estimation of soybean FB.

Recent advances in artificial intelligence, mechanistic models, and speed breeding offer exciting opportunities for precise and accelerated genomics-assisted breeding

Given the challenges of population growth and climate change, there is an urgent need to expedite the development of high-yielding stress-tolerant crop cultivars. While traditional breeding methods have been instrumental in ensuring global food security, their efficiency, precision, and labour intensiveness have become increasingly inadequate to address present and future challenges. Fortunately, recent advances in high-throughput phenomics and genomics-assisted breeding (GAB) provide a promising platform for enhancing crop cultivars with greater efficiency. However, several obstacles must be overcome to optimize the use of these techniques in crop improvement, such as the complexity of phenotypic analysis of big image data. In addition, the prevalent use of linear models in genome-wide association studies (GWAS) and genomic selection (GS) fails to capture the nonlinear interactions of complex traits, limiting their applicability for GAB and impeding crop improvement. Recent advances in artificial intelligence (AI) techniques have opened doors to nonlinear modelling approaches in crop breeding, enabling the capture of nonlinear and epistatic interactions in GWAS and GS and thus making this variation available for GAB. While statistical and software challenges persist in AI-based models, they are expected to be resolved soon. Furthermore, recent advances in speed breeding have significantly reduced the time (3-5-fold) required for conventional breeding. Thus, integrating speed breeding with AI and GAB could improve crop cultivar development within a considerably shorter timeframe while ensuring greater accuracy and efficiency. In conclusion, this integrated approach could revolutionize crop breeding paradigms and safeguard food production in the face of population growth and climate change.

Phenotyping Key Fruit Quality Traits in Olive Using RGB Images and Back Propagation Neural Networks

To predict oil and phenol concentrations in olive fruit, the combination of back propagation neural networks (BPNNs) and contact-less plant phenotyping techniques was employed to retrieve RGB image-based digital proxies of oil and phenol concentrations. Fruits of cultivars (×3) differing in ripening time were sampled (~10-day interval, ×2 years), pictured and analyzed for phenol and oil concentrations. Prior to this, fruit samples were pictured and images were segmented to extract the red (R), green (G), and blue (B) mean pixel values that were rearranged in 35 RGB-based colorimetric indexes. Three BPNNs were designed using as input variables (a) the original 35 RGB indexes, (b) the scores of principal components after a principal component analysis (PCA) pre-processing of those indexes, and (c) a reduced number (28) of the RGB indexes achieved after a sparse PCA. The results show that the predictions reached the highest mean R² values ranging from 0.87 to 0.95 (oil) and from 0.81 to 0.90 (phenols) across the BPNNs. In addition to the R², other performance metrics were calculated (root mean squared error and mean absolute error) and combined into a general performance indicator (GPI). The resulting rank of the GPI suggests that a BPNN with a specific topology might be designed for cultivars grouped according to their ripening period. The present study documented that an RGB-based image phenotyping can effectively predict key quality traits in olive fruit supporting the developing olive sector within a digital agriculture domain.

Genome-wide association mapping of genomic regions associated with drought stress tolerance at seedling and reproductive stages in bread wheat

Understanding the genetic architecture of drought stress tolerance in bread wheat at seedling and reproductive stages is crucial for developing drought-tolerant varieties. In the present study, 192 diverse wheat genotypes, a subset from the Wheat Associated Mapping Initiative (WAMI) panel, were evaluated at the seedling stage in a hydroponics system for chlorophyll content (CL), shoot length (SLT), shoot weight (SWT), root length (RLT), and root weight (RWT) under both drought and optimum conditions. Following that, a genome-wide association study (GWAS) was carried out using the phenotypic data recorded during the hydroponics experiment as well as data available from previously conducted multi-location field trials under optimal and drought stress conditions. The panel had previously been genotyped using the Infinium iSelect 90K SNP array with 26,814 polymorphic markers. Using single as well as multi-locus models, GWAS identified 94 significant marker-trait associations (MTAs) or SNPs associated with traits recorded at the seedling stage and 451 for traits recorded at the reproductive stage. The significant SNPs included several novel, significant, and promising MTAs for different traits. The average LD decay distance for the whole genome was approximately 0.48 Mbp, ranging from 0.07 Mbp (chromosome 6D) to 4.14 Mbp (chromosome 2A). Furthermore, several promising SNPs revealed significant differences among haplotypes for traits such as RLT, RWT, SLT, SWT, and GY under drought stress. Functional annotation and in silico expression analysis revealed important putative candidate genes underlying the identified stable genomic regions such as protein kinases, O-methyltransferases, GroES-like superfamily proteins, NAD-dependent dehydratases, etc. The findings of the present study may be useful for improving yield potential, and stability under drought stress conditions.

Meta-QTLs, ortho-meta QTLs and related candidate genes for yield and its component traits under water stress in wheat (Triticum aestivum L.)

Meta-QTLs (MQTLs), ortho-MQTLs, and related candidate genes (CGs) for yield and its seven component traits evaluated under water deficit conditions were identified in wheat. For this purpose, a high density consensus map and 318 known QTLs were used for identification of 56 MQTLs. Confidence intervals (CIs) of the MQTLs were narrower (0.7-21 cM; mean = 5.95 cM) than the CIs of the known QTLs (0.4-66.6 cM; mean = 12.72 cM). Forty-seven MQTLs were co-located with marker trait associations reported in previous genome-wide association studies. Nine selected MQTLs were declared as 'breeders MQTLs' for use in marker-assisted breeding (MAB). Utilizing known MQTLs and synteny/collinearity among wheat, rice and maize, 12 ortho-MQTLs were also identified. A total of 1497 CGs underlying MQTLs were also identified, which were subjected to in-silico expression analysis, leading to identification of 64 differentially expressed CGs (DECGs) under normal and water deficit conditions. These DECGs encoded a variety of proteins, including the following: zinc finger, cytochrome P450, AP2/ERF domain-containing proteins, plant peroxidase, glycosyl transferase, glycoside hydrolase. The expression of 12 CGs at seedling stage (3 h stress) was validated using qRT-PCR in two wheat genotypes, namely Excalibur (drought tolerant) and PBW343 (drought sensitive). Nine of the 12 CGs were up-regulated and three down-regulated in Excalibur. The results of the present study should prove useful for MAB, for fine mapping of promising MQTLs and for cloning of genes across the three cereals studied.

Supplementary Information

The online version contains supplementary material available at 10.1007/s12298-023-01301-z.

Multi-omics assisted breeding for biotic stress resistance in soybean

Biotic stress is a critical factor limiting soybean growth and development. Soybean responses to biotic stresses such as insects, nematodes, fungal, bacterial, and viral pathogens are governed by complex regulatory and defense mechanisms. Next-generation sequencing has availed research techniques and strategies in genomics and post-genomics. This review summarizes the available information on marker resources, quantitative trait loci, and marker-trait associations involved in regulating biotic stress responses in soybean. We discuss the differential expression of related genes and proteins reported in different transcriptomics and proteomics studies and the role of signaling pathways and metabolites reported in metabolomic studies. Recent advances in omics technologies offer opportunities to reshape and improve biotic stress resistance in soybean by altering gene regulation and/or other regulatory networks. We suggest using 'integrated omics' to precisely understand how soybean responds to different biotic stresses. We also discuss the potential challenges of integrating multi-omics for the functional analysis of genes and their regulatory networks and the development of biotic stress-resistant cultivars. This review will help direct soybean breeding programs to develop resistance against different biotic stresses.

Important wheat diseases in the US and their management in the 21st century

Wheat is a crop of historical significance, as it marks the turning point of human civilization 10,000 years ago with its domestication. Due to the rapid increase in population, wheat production needs to be increased by 50% by 2050 and this growth will be mainly based on yield increases, as there is strong competition for scarce productive arable land from other sectors. This increasing demand can be further achieved using sustainable approaches including integrated disease pest management, adaption to warmer climates, less use of water resources and increased frequency of abiotic stress tolerances. Out of 200 diseases of wheat, 50 cause economic losses and are widely distributed. Each year, about 20% of wheat is lost due to diseases. Some major wheat diseases are rusts, smut, tan spot, spot blotch, fusarium head blight, common root rot, septoria blotch, powdery mildew, blast, and several viral, nematode, and bacterial diseases. These diseases badly impact the yield and cause mortality of the plants. This review focuses on important diseases of the wheat present in the United States, with comprehensive information of causal organism, economic damage, symptoms and host range, favorable conditions, and disease management strategies. Furthermore, major genetic and breeding efforts to control and manage these diseases are discussed. A detailed description of all the QTLs, genes reported and cloned for these diseases are provided in this review. This study will be of utmost importance to wheat breeding programs throughout the world to breed for resistance under changing environmental conditions.

Multi-locus genome-wide association studies reveal genomic regions and putative candidate genes associated with leaf spot diseases in African groundnut (Arachis hypogaea L.) germplasm

Early leaf spot (ELS) and late leaf spot (LLS) diseases are the two most destructive groundnut diseases in Ghana resulting in ≤ 70% yield losses which is controlled largely by chemical method. To develop leaf spot resistant varieties, the present study was undertaken to identify single nucleotide polymorphism (SNP) markers and putative candidate genes underlying both ELS and LLS. In this study, six multi-locus models of genome-wide association study were conducted with the best linear unbiased predictor obtained from 294 African groundnut germplasm screened for ELS and LLS as well as image-based indices of leaf spot diseases severity in 2020 and 2021 and 8,772 high-quality SNPs from a 48 K SNP array Axiom platform. Ninety-seven SNPs associated with ELS, LLS and five image-based indices across the chromosomes in the 2 two sub-genomes. From these, twenty-nine unique SNPs were detected by at least two models for one or more traits across 16 chromosomes with explained phenotypic variation ranging from 0.01 - 62.76%, with exception of chromosome (Chr) 08 (Chr08), Chr10, Chr11, and Chr19. Seventeen potential candidate genes were predicted at ± 300 kbp of the stable/prominent SNP positions (12 and 5, down- and upstream, respectively). The results from this study provide a basis for understanding the genetic architecture of ELS and LLS diseases in African groundnut germplasm, and the associated SNPs and predicted candidate genes would be valuable for breeding leaf spot diseases resistant varieties upon further validation.

OMICS in Fodder Crops: Applications, Challenges, and Prospects

Biomass yield and quality are the primary targets in forage crop improvement programs worldwide. Low-quality fodder reduces the quality of dairy products and affects cattle's health. In multipurpose crops, such as maize, sorghum, cowpea, alfalfa, and oat, a plethora of morphological and biochemical/nutritional quality studies have been conducted. However, the overall growth in fodder quality improvement is not on par with cereals or major food crops. The use of advanced technologies, such as multi-omics, has increased crop improvement programs manyfold. Traits such as stay-green, the number of tillers per plant, total biomass, and tolerance to biotic and/or abiotic stresses can be targeted in fodder crop improvement programs. Omic technologies, namely genomics, transcriptomics, proteomics, metabolomics, and phenomics, provide an efficient way to develop better cultivars. There is an abundance of scope for fodder quality improvement by improving the forage nutrition quality, edible quality, and digestibility. The present review includes a brief description of the established omics technologies for five major fodder crops, i.e., sorghum, cowpea, maize, oats, and alfalfa. Additionally, current improvements and future perspectives have been highlighted.

Consensus genomic regions associated with grain protein content in hexaploid and tetraploid wheat

A meta-analysis of QTLs associated with grain protein content (GPC) was conducted in hexaploid and tetraploid wheat to identify robust and stable meta-QTLs (MQTLs). For this purpose, as many as 459 GPC-related QTLs retrieved from 48 linkage-based QTL mapping studies were projected onto the newly developed wheat consensus map. The analysis resulted in the prediction of 57 MQTLs and 7 QTL hotspots located on all wheat chromosomes (except chromosomes 1D and 4D) and the average confidence interval reduced 2.71-fold in the MQTLs and QTL hotspots compared to the initial QTLs. The physical regions occupied by the MQTLs ranged from 140 bp to 224.02 Mb with an average of 15.2 Mb, whereas the physical regions occupied by QTL hotspots ranged from 1.81 Mb to 36.03 Mb with a mean of 8.82 Mb. Nineteen MQTLs and two QTL hotspots were also found to be co-localized with 45 significant SNPs identified in 16 previously published genome-wide association studies in wheat. Candidate gene (CG) investigation within some selected MQTLs led to the identification of 705 gene models which also included 96 high-confidence CGs showing significant expressions in different grain-related tissues and having probable roles in GPC regulation. These significantly expressed CGs mainly involved the genes/gene families encoding for the following proteins: aminotransferases, early nodulin 93, glutamine synthetases, invertase/pectin methylesterase inhibitors, protein BIG GRAIN 1-like, cytochrome P450, glycosyl transferases, hexokinases, small GTPases, UDP-glucuronosyl/UDP-glucosyltransferases, and EamA, SANT/Myb, GNAT, thioredoxin, phytocyanin, and homeobox domains containing proteins. Further, eight genes including GPC-B1, Glu-B1-1b, Glu-1By9, TaBiP1, GSr, TaNAC019-A, TaNAC019-D, and bZIP-TF SPA already known to be associated with GPC were also detected within some of the MQTL regions confirming the efficacy of MQTLs predicted during the current study.

Recent developments in multi-omics and breeding strategies for abiotic stress tolerance in maize (Zea mays L.)

High-throughput sequencing technologies (HSTs) have revolutionized crop breeding. The advent of these technologies has enabled the identification of beneficial quantitative trait loci (QTL), genes, and alleles for crop improvement. Climate change have made a significant effect on the global maize yield. To date, the well-known omic approaches such as genomics, transcriptomics, proteomics, and metabolomics are being incorporated in maize breeding studies. These approaches have identified novel biological markers that are being utilized for maize improvement against various abiotic stresses. This review discusses the current information on the morpho-physiological and molecular mechanism of abiotic stress tolerance in maize. The utilization of omics approaches to improve abiotic stress tolerance in maize is highlighted. As compared to single approach, the integration of multi-omics offers a great potential in addressing the challenges of abiotic stresses of maize productivity.

Ascertaining yield and grain protein content stability in wheat genotypes having the Gpc-B1 gene using univariate, multivariate, and correlation analysis

The high performance and stability of wheat genotypes for yield, grain protein content (GPC), and other desirable traits are critical for varietal development and food and nutritional security. Likewise, the genotype by environment (G × E) interaction (GEI) should be thoroughly investigated and favorably utilized whenever genotype selection decisions are made. The present study was planned with the following two major objectives: 1) determination of GEI for some advanced wheat genotypes across four locations (Ludhiana, Ballowal, Patiala, and Bathinda) of Punjab, India; and 2) selection of the best genotypes with high GPC and yield in various environments. Different univariate [Eberhart and Ruessll's models; Perkins and Jinks' models; Wrike's Ecovalence; and Francis and Kannenberg's models], multivariate (AMMI and GGE biplot), and correlation analyses were used to interpret the data from the multi-environmental trial (MET). Consequently, both the univariate and multivariate analyses provided almost similar results regarding the top-performing and stable genotypes. The analysis of variance revealed that variation due to environment, genotype, and GEI was highly significant at the 0.01 and 0.001 levels of significance for all studied traits. The days to flowering, plant height, spikelets per spike, grain per spike, days to maturity, and 1000-grain weight were specifically affected by the environment, whereas yield was mainly affected by the environment and GEI. Genotypes, on the other hand, had a greater impact on the GPC than environmental conditions. As a result, a multi-environmental investigation was necessary to identify the GEI for wheat genotype selection because the GEI was very significant for all of the evaluated traits. Yield, 1000-grain weight, spikelet per spike, and days to maturity were observed to have positive correlations, implying the feasibility of their simultaneous selection for yield enhancement. However, GPC was observed to have a negative correlation with yield. Patiala was found to be the most discriminating environment for both yield and GPC and also the most effective representative environment for GPC, whereas Ludhiana was found to be the most effective representative environment for yield. Eventually, two NILs (BWL7508, and BWL7511) were selected as the top across all environments for both yield and GPC.

CRISPR/Cas tool designs for multiplex genome editing and its applications in developing biotic and abiotic stress-resistant crop plants

Crop plants are prone to several yield-reducing biotic and abiotic stresses. The crop yield reductions due to these stresses need addressing to maintain an adequate balance between the increasing world population and food production to avoid food scarcities in the future. It is impossible to increase the area under food crops proportionately to meet the rising food demand. In such an adverse scenario overcoming the biotic and abiotic stresses through biotechnological interventions may serve as a boon to help meet the globe's food requirements. Under the current genomic era, the wide availability of genomic resources and genome editing technologies such as Transcription Activator-Like Effector Nucleases (TALENs), Zinc Finger Nucleases (ZFNs), and Clustered-Regularly Interspaced Palindromic Repeats/CRISPR-associated proteins (CRISPR/Cas) has widened the scope of overcoming these stresses for several food crops. These techniques have made gene editing more manageable and accessible with changes at the embryo level by adding or deleting DNA sequences of the target gene(s) from the genome. The CRISPR construct consists of a single guide RNA having complementarity with the nucleotide fragments of the target gene sequence, accompanied by a protospacer adjacent motif. The target sequence in the organism's genome is then cleaved by the Cas9 endonuclease for obtaining a desired trait of interest. The current review describes the components, mechanisms, and types of CRISPR/Cas techniques and how this technology has helped to functionally characterize genes associated with various biotic and abiotic stresses in a target organism. This review also summarizes the application of CRISPR/Cas technology targeting these stresses in crops through knocking down/out of associated genes.

Consensus genomic regions associated with multiple abiotic stress tolerance in wheat and implications for wheat breeding

In wheat, a meta-analysis was performed using previously identified QTLs associated with drought stress (DS), heat stress (HS), salinity stress (SS), water-logging stress (WS), pre-harvest sprouting (PHS), and aluminium stress (AS) which predicted a total of 134 meta-QTLs (MQTLs) that involved at least 28 consistent and stable MQTLs conferring tolerance to five or all six abiotic stresses under study. Seventy-six MQTLs out of the 132 physically anchored MQTLs were also verified with genome-wide association studies. Around 43% of MQTLs had genetic and physical confidence intervals of less than 1 cM and 5 Mb, respectively. Consequently, 539 genes were identified in some selected MQTLs providing tolerance to 5 or all 6 abiotic stresses. Comparative analysis of genes underlying MQTLs with four RNA-seq based transcriptomic datasets unravelled a total of 189 differentially expressed genes which also included at least 11 most promising candidate genes common among different datasets. The promoter analysis showed that the promoters of these genes include many stress responsiveness cis-regulatory elements, such as ARE, MBS, TC-rich repeats, As-1 element, STRE, LTR, WRE3, and WUN-motif among others. Further, some MQTLs also overlapped with as many as 34 known abiotic stress tolerance genes. In addition, numerous ortho-MQTLs among the wheat, maize, and rice genomes were discovered. These findings could help with fine mapping and gene cloning, as well as marker-assisted breeding for multiple abiotic stress tolerances in wheat.

Consensus genomic regions associated with multiple abiotic stress tolerance in wheat and implications for wheat breeding

In wheat, a meta-analysis was performed using previously identified QTLs associated with drought stress (DS), heat stress (HS), salinity stress (SS), water-logging stress (WS), pre-harvest sprouting (PHS), and aluminium stress (AS) which predicted a total of 134 meta-QTLs (MQTLs) that involved at least 28 consistent and stable MQTLs conferring tolerance to five or all six abiotic stresses under study. Seventy-six MQTLs out of the 132 physically anchored MQTLs were also verified with genome-wide association studies. Around 43% of MQTLs had genetic and physical confidence intervals of less than 1 cM and 5 Mb, respectively. Consequently, 539 genes were identified in some selected MQTLs providing tolerance to 5 or all 6 abiotic stresses. Comparative analysis of genes underlying MQTLs with four RNA-seq based transcriptomic datasets unravelled a total of 189 differentially expressed genes which also included at least 11 most promising candidate genes common among different datasets. The promoter analysis showed that the promoters of these genes include many stress responsiveness cis-regulatory elements, such as ARE, MBS, TC-rich repeats, As-1 element, STRE, LTR, WRE3, and WUN-motif among others. Further, some MQTLs also overlapped with as many as 34 known abiotic stress tolerance genes. In addition, numerous ortho-MQTLs among the wheat, maize, and rice genomes were discovered. These findings could help with fine mapping and gene cloning, as well as marker-assisted breeding for multiple abiotic stress tolerances in wheat.

Symptom recognition of disease and insect damage based on Mask R-CNN, wavelet transform, and F-RNet

Brown blight, target spot, and tea coal diseases are three major leaf diseases of tea plants, and Apolygus lucorum is a major pest in tea plantations. The traditional symptom recognition of tea leaf diseases and insect pests is mainly through manual identification, which has some problems, such as low accuracy, low efficiency, strong subjectivity, and so on. Therefore, it is very necessary to find a method that could effectively identify tea plants diseases and pests. In this study, we proposed a recognition framework of tea leaf disease and insect pest symptoms based on Mask R-CNN, wavelet transform and F-RNet. First, Mask R-CNN model was used to segment disease spots and insect spots from tea leaves. Second, the two-dimensional discrete wavelet transform was used to enhance the features of the disease spots and insect spots images, so as to obtain the images with four frequencies. Finally, the images of four frequencies were simultaneously input into the four-channeled residual network (F-RNet) to identify symptoms of tea leaf diseases and insect pests. The results showed that Mask R-CNN model could detect 98.7% of DSIS, which ensure that almost disease spots and insect spots can be extracted from leaves. The accuracy of F-RNet model is 88%, which is higher than that of the other models (like SVM, AlexNet, VGG16 and ResNet18). Therefore, this experimental framework can accurately segment and identify diseases and insect spots of tea leaves, which not only of great significance for the accurate identification of tea plant diseases and insect pests, but also of great value for further using artificial intelligence to carry out the comprehensive control of tea plant diseases and insect pests.

Exploring Soybean Flower and Pod Variation Patterns During Reproductive Period Based on Fusion Deep Learning

The soybean flower and the pod drop are important factors in soybean yield, and the use of computer vision techniques to obtain the phenotypes of flowers and pods in bulk, as well as in a quick and accurate manner, is a key aspect of the study of the soybean flower and pod drop rate (PDR). This paper compared a variety of deep learning algorithms for identifying and counting soybean flowers and pods, and found that the Faster R-CNN model had the best performance. Furthermore, the Faster R-CNN model was further improved and optimized based on the characteristics of soybean flowers and pods. The accuracy of the final model for identifying flowers and pods was increased to 94.36 and 91%, respectively. Afterward, a fusion model for soybean flower and pod recognition and counting was proposed based on the Faster R-CNN model, where the coefficient of determinationR2 between counts of soybean flowers and pods by the fusion model and manual counts reached 0.965 and 0.98, respectively. The above results show that the fusion model is a robust recognition and counting algorithm that can reduce labor intensity and improve efficiency. Its application will greatly facilitate the study of the variable patterns of soybean flowers and pods during the reproductive period. Finally, based on the fusion model, we explored the variable patterns of soybean flowers and pods during the reproductive period, the spatial distribution patterns of soybean flowers and pods, and soybean flower and pod drop patterns.