Plant Phenomics

Plant disease detection using deep learning is essential for precision agriculture, enabling early and automated crop health monitoring. This study proposes an end-to-end transfer learning pipeline, LeafyVGG-16, for multi-class classification of plant diseases and nutrient deficiencies using a tomato leaf dataset. The framework integrates data preprocessing, augmentation, and a VGG-16 backbone with a two-stage fine-tuning strategy. The proposed model is evaluated against CNN, DenseNet-121, Inception-V3, EfficientNetB0, and ResNet-50, achieving an accuracy of 0.93 with precision, recall, and F1-scores of 0.93, 0.90, and 0.92, respectively. These results demonstrate the effectiveness of transfer learning for fine-grained plant disease recognition. We further evaluate model robustness under adversarial cyber attacks to assess deployment reliability in agricultural systems. Under Fast Gradient Sign Method (FGSM) attacks ({epsilon} = 0.01- 0.05), the model shows an accuracy drop of 1%-7.5%, while Projected Gradient Descent (PGD) attacks ({epsilon} = 0.05, step size = 0.005, 10 iterations) produce similar degradation, highlighting the models vulnerability to adversarial perturbations. These findings highlight potential security and reliability risks in AI-based agricultural decision-making systems. Future work will focus on improving robustness and cyber-resilience and extending this framework to other crops for secure and context-aware deployment in resource-constrained environments.

Accurate quantification of leaf lesion severity is essential for plant disease research and phenotyping but is often limited by subjective visual scoring and time-intensive manual image analysis. We present LIME, a fully automated, open-source image analysis pipeline for high-throughput quantification of leaf lesions from disease assay images. LIME integrates zero-shot leaf segmentation using the Segment Anything Model with a convolutional neural network for lesion area estimation. Applied to Arabidopsis thaliana leaves infected with Sclerotinia sclerotiorum, the proposed approach achieved a mean absolute percentage error of 12.9%, comparable to observed intrarater variability in manual scoring. Stratified evaluation across lesion-size groups demonstrated consistent prediction accuracy for small, intermediate, and large lesions, and comparative analysis showed that the deep learning-based model substantially outperformed color-based baseline methods. Under GPU-accelerated execution, LIME processed complete assays containing approximately 200 leaves in 15 minutes, representing an approximate 13-fold reduction in processing time relative to manual annotation. Together, these results indicate that LIME enables objective, reproducible, and scalable quantification of leaf lesion severity in standardized plant pathology assays. The pipeline is released as an open-source tool to support quantitative phenotyping studies.

Though currently a minor crop, faba bean is a promising source of plant-based protein as global diets shift towards more plant-based nutrition. To realise this potential, advances in breeding and cultivation are crucial. To exploit heterosis, faba bean breeding frequently utilises synthetic cultivars, which involves open pollination of inbred lines to produce a mixture of F1 hybrid seeds and self-pollinated offspring. Pure F1 hybrid cultivars are currently unavailable due to unstable cytoplasmic male sterility (CMS) systems. An ability to distinguish F1 seeds from their parental inbreds via characteristics associated with xenia effects could change this. The xenia effect refers to the influence of paternal pollen on seed traits, for example seed weight and cotyledon cells in faba bean. In this study, we exploited the xenia effect captured in hyperspectral imaging data to develop machine learning scenarios for discriminating between parental and F1 seeds of open pollinated synthetic combinations (Syn-1). The hyperspectral data were pre-processed using Savitzky-Golay filtering to reduce noise and smooth the spectra. Various machine learning algorithms were applied, incorporating Bayesian hyperparameter optimisation. The scenarios achieved up to 98.9 % accuracy in separating parental components of Syn-1. When including all seeds, the model achieved 40.7 %, indicating moderate detection and classification performance. As the harmonic mean of precision and recall, the F1 score accounts for both the correctness of F1 seed detections and the completeness with which F1 seeds were detected. While this approach does not yet enable the development of full hybrid cultivars, it paves the way for hybrid-enriched cultivars. These could help to streamline breeding for synthetic cultivars and potentially increase yields, for example by increasing the proportion of F1 hybrid seeds in synthetic cultivars. This study extends knowledge of the xenia effect in faba bean and provides a basis for further research aimed at enhancing breeding methods and productivity.

Accurate and reproducible assessment of foliar disease severity is essential for evaluating the performance of heterogeneous plant communities and understanding host-pathogen interactions. However, traditional visual scoring methods remain subjective, with limited precision, and difficult to scale in large phenotyping experiments. Here, we present a semi-automated image analysis workflow designed to quantify multiple foliar disease symptoms simultaneously on wheat flag leaves sampled from varietal mixtures. The workflow combines three methodological components: (i) a standardized protocol for leaf sampling and imaging, (ii) supervised machine learning segmentation using Random Forest implemented in Ilastik to classify multiple symptoms (powdery mildew and yellow rust), and (iii) a graphical user interface facilitating pipeline deployment by non-specialist operators. To evaluate the influence of image representation on classification performance, four color spaces (RGB, HSV, HLS, LAB) were systematically compared. The approach was validated using images of durum wheat flag leaves collected from a field experiment assessing eight-way varietal mixtures under natural fungal pressure. Cross-validation against manually annotated images demonstrated high segmentation accuracy across all symptom. Comparison among color spaces revealed only minor differences in performance. Overall, this workflow offers a cost-effective, annotation-efficient and reproducible alternative to deep learning approaches, leveraging open-source and actively maintained tools while requiring limited training data and enabling objective, reproducible and scalable disease phenotyping.

Accurate modeling of genotype-by-environment (GxE) interaction is critical for genomic prediction in plant breeding but remains challenging due to complex interaction structures. Conventional models often use the Hadamard product of genotype and environment covariance matrices to capture joint similarity, which may not fully represent GxE complexity. Here we propose a novel framework that derives covariance structures from the matrix multiplication of genotype and environment kernels, decomposing these into symmetric components incorporated as random effects in mixed models. Evaluated for 11 wheat and rice multi-environment datasets and across, this approach consistently outperformed the traditional Hadamard-based model, improving prediction accuracy by up to 13.2% in Pearsons correlation and enhancing top-selection accuracy. Combining both methods yielded the highest performance, indicating complementary information capture. This framework offers a flexible, interpretable, and computationally feasible extension for modeling GxE interaction, potentially enhancing genomic selection effectiveness under diverse environmental conditions.

Potato crop is highly vulnerable to abiotic stresses like salinity and low nutrient availability. Rapid identification of stress-resilient genotypes is therefore essential for breeding, yet conventional phenotyping is often slow, space-demanding and expensive. We present LOCOPOTS -- a LOw-COst high-throughput screening platform for in vitro POTatoes under abiotic Stress -- which combines individual in vitro plant culture, low-cost RGB imaging and machine-learning-based automatic segmentation using a trained model of a convolutional neural network, based on U-Net architecture. LOCOPOTS enabled the automated extraction of growth, colour, and vegetation-index traits and demonstrated robust performance across independent phenotyping rounds. We screened 30 potato varieties under control, low-nutrient and saltinity conditions, identifying contrasting growth and physiological responses. Integrated traits such as final area and height, Area_AUC and height_AUC, together with GLI, Chol, cive and chlorophyll fluorescence parameters, discriminated genotype performance under stress. Metabolic profiling further revealed genotype-specific reprogramming in carbon and nitrogen metabolism under low nutrition and salt stress, including changes in fructose, myo-inositol, {beta}-aminobutyric acid, {gamma}-aminobutyric acid, proline, and certain polyamines, identifying them as specific chemical biomarkers of plant stress responses. LOCOPOTS provides a scalable, affordable and space-efficient platform for early screening of potato genetic diversity and identification of candidate traits associated with stress resilience.

Phenomic prediction (PP) is a breeding value prediction method using near infrared spectroscopy (NIRS). Spectra pre-processing is a key step in the analysis pipeline of PP and generally involves chemometrics methods. However, there is still little understanding in the genetics community of what pre-processing does and why it increases performances. Consequently, the choice of pre-processing is done either arbitrarily or through a search of the optimal set of methods and associated parameters. In this study, we propose a PCA-based pre-processing method where genetic values of spectra are estimated on a set of principal components instead of individual wavelengths. This way, estimations are based on a few informative and orthogonal features of spectra instead of many correlated, uninformative wavelengths. We tested this new pre-processing method on five data sets representing four plant species (maize, rice, sorghum and grapevine). Results show that it performs as good, or better than the best classical chemometric pre-processing methods in almost all cases. Combining PCA-based and classical chemometric pre-processing methods maximizes predictive ability. Moreover, this pre-processing method opens up possibilities of better understanding and selecting parts of the spectral information that are relevant for the prediction of breeding values. Indeed, components representing together about 1% of spectral variability were found to be responsible for most of PP predictive ability. Plain language summaryCultivated plants are the result of a breeding process during which their genetic values are used to select those to breed. Estimation of breeding values requires heavy experimental means and is time consuming. Phenomic prediction is a low cost and high throughput genetic value estimation method that is increasingly being used. It often uses near infrared spectroscopy measurements as predictors of genetic values that are easy to collect and thus routinely used in many species. However, near infrared spectra generally require pre-processing before being used in prediction. Currently used pre-processing methods arise from the chemometrics community, and still deserve a better in-depth appropriation by geneticists. In this study, we propose a new pre-processing approach that performs as good as or better than the best chemometric pre-processing generally used, reduces computation time, and allows for a better understanding of what parts of spectral information are relevant for prediction. Core IdeasO_LIWorking on principal components of spectra instead of wavelengths increases predictive ability of phenomic prediction and performs as good as or better than classical chemometrics pre-processing C_LIO_LIWorking on principal components of spectra requires less optimization of parameters than chemometrics pre-processing C_LIO_LIAbout 1% of spectral variance is responsible for most of the predictive power of phenomic prediction C_LIO_LIWorking on principal components of spectra pre-processed with classical chemometrics pre-processing can increase predictive ability even more C_LIO_LIPCA-based methods are valuable to optimize predictive ability of phenomic prediction and could be used more widely in the quantitative genetics field C_LI

This study integrated morphometric characterization and machine-learning modelling to identify key predictors of yield in Annona reticulata under semi-arid conditions. Thirty-one canopy, fruit, seed, and biochemical traits were evaluated across 62 genotypes, revealing substantial phenotypic diversity, particularly in structural attributes such as tree growth nature and branch angle. Principal Component Analysis and hierarchical clustering differentiated genotypes into three ideotypes representing high-yielding, structurally stable, and quality-oriented groups. Random Forest modelling and SHapley Additive exPlanations (SHAP) interpretation consistently highlighted leaf breadth, leaf length, fruit shape, and pulp-associated traits as dominant yield predictors, underscoring the coordinated influence of source-sink balance. Integration of SHAP importances with trait stability (CV%) further revealed that moderately variable traits provide reliable selection indices. These findings demonstrate that yield performance is governed by multivariate trait networks rather than isolated descriptors. The proposed framework provides a robust basis for precision phenotyping and strategic parent selection to develop high-yielding, nutritionally enriched, and climate-resilient custard apple cultivars.

The Digital Pedon (DP) is an open-source Python framework that represents a soil profile as a continuously updated digital twin, bridging three persistent gaps in soil science: disconnected models and observations, cross-database interoperability, and the inference gap between raw sensor signals and agronomically meaningful variables. Integrating real-time sensor streams, model-based solver chains (Model-Zoo), GLOSIS-compliant ontology mapping, and a novel LLM agentic interface layer enabling natural language soil queries, the DP supports applications spanning precision agriculture, digital soil mapping, and environmental sustainability assessment. Four proof-of-concept experiments confirm automatic profile initialisation fidelity, solver chain consistency, ontology compliance, and user-defined solver extensibility.

Genomic prediction (GP) across diverse environments has a potential to accelerate genetic gain in cotton breeding programs. A major challenge in GP is modelling genotype-by-environment interactions (GEI), which is essential for selecting stable and high-performing genotypes under variable production conditions. However, incorporating GEI into GP models increases the dimensionality and computational complexity, risking complex models that are impractical to use on commercial breeding-scale data sets because of run times and computational demands. This study addresses two primary aims. Firstly, we evaluate the practical benefits of GEI-informed GP for predicting economically important cotton traits. Second, advanced statistical modelling strategies are developed and assessed for integrating genomic and environmental data at scale. We propose a dimensionality reduction approach that combines linkage disequilibrium network analysis with principal component techniques to reduce redundancy while preserving informative variation. Using this reduced dataset, we implement Bayesian linear regression models and, for comparison, deep residual neural networks for genomic prediction. Analyses were conducted on a large multi-environment dataset from the CSIRO cotton breeding program, comprising 3,236 breeding lines, 54 environmental covariates, and 8,049 yield and fibre quality phenotype records collected over 10 years and 9 locations representing 41 year-location combinations. Results demonstrate that generally Bayesian linear regression approaches outperform BG-BLUP models, with all three linear/linear mixed methods providing clearly more reliable performance than the deep learning models. These findings highlight the value of using interpretable statistical models for integrating genomic and environmental information to support selection decisions under diverse environmental conditions.

Intercropping is a promising strategy to improve productivity and sustainability in agricultural systems, but designing effective genotype combinations remains a major challenge owing to the rapid increase in possible pairings as the number of candidate genotypes increases. This creates a practical bottleneck because field evaluation of all combinations is infeasible under realistic resource constraints. Here, we propose a framework that integrates genomic prediction and Bayesian optimization to support efficient decision-making for intercropping system design. Using genome-wide marker data from sorghum and soybean, we simulated intercropping performance across 5,214 genotype pairs under certain genetic architectures, including variation in heritability, correlations between direct and indirect genetic effects, and the contribution of pair-specific interactions. Genomic prediction models incorporating direct and indirect genetic effects substantially improved prediction accuracy compared with models based on direct genetic effects alone, and inclusion of specific mixing ability further enhanced the performance under high-heritability conditions. When coupled with Bayesian optimization, the models rapidly identified superior genotype pairs, requiring fewer evaluation cycles than random or prediction-only search strategies. Acquisition functions that account for predicted uncertainty were most effective in complex scenarios involving interaction effects or negative correlations between direct and indirect effects. These results demonstrate that combining genomic prediction with Bayesian optimization can substantially reduce the experimental burden associated with intercropping design, while improving the efficiency of identifying high-performing genotype pairs. The proposed framework provides a practical approach for prioritizing candidate mixtures in breeding and field evaluation, and contributes to the development of data-driven strategies for sustainable agricultural systems. HighlightsO_LIA data-driven framework was developed to optimize genotype pairs in intercropping. C_LIO_LIModeling indirect effects improved prediction accuracy across genotype pairs. C_LIO_LIPair-specific interactions enhanced prediction under high-heritability conditions. C_LIO_LIBayesian optimization identified superior pairs under limited evaluation capacity. C_LIO_LIThe framework reduces field-testing requirements for intercropping system design. C_LI

Ensuring global food security under rapid climate change demands accelerated genetic gain and breeding strategies that address complex Genotype-by-Environment (GxE) interactions. Traditional genomic selection models often fail to account for novel or extreme climates.Furthermore, integrating mechanistic crop growth models (CGMs) using traditional Bayesian frameworks to solve this issue presents severe computational bottlenecks. Here, we introduce DeepBioGS, a novel hybrid framework that integrates genomic selection with biophysical growth modelling via a fully differentiable deep learning architecture. DeepBioGS utilises a parameter-prediction multi-layer perceptron to map high-dimensional genomic markers to latent, highly heritable physiological traits (Genotype-Specific Parameters; GSP). These parameters mechanistically predict crop phenology across diverse environments. Using two multi-environment wheat datasets comprising over 6,000 genotypes, DeepBioGS extracted latent traits with near-perfect SNP-based heritability values (0.95-1.00). Crucially, the framework demonstrated superior or comparable predictive accuracy (up to r2 = 0.77) against standard genomic best linear unbiased prediction (GBLUP) and traditional Bayesian CGM-WGP models. Its architecture drastically improved computational scalability by enabling standard backpropagation, effectively bypassing the stochastic sampling limitations of approximate Bayesian methods. Most importantly for climate adaptation, DeepBioGS allowed accurate forecasting of genotype performance in entirely unobserved environmental conditions. By merging the representational power of deep learning with the structural constraints of biophysics, DeepBioGS provides a highly scalable, interpretable tool to navigate GxE interactions, enabling the assessment of cultivars under future climate scenarios, thus optimising crop breeding for a changing global environment.

Genomic prediction models that account genotype-by-environment (GxE) have the potential to accelerate the rate of genetic gain for yield and agronomic performance, yet relatively few studies have applied GxE prediction in public soft red winter wheat (Triticum aestivum) breeding programs. In this study, we extended a reaction norm-based genomic prediction framework by integrating weather-based environmental covariates to more effectively capture genotype- environment interactions. Key agronomic traits, including seed yield, plant height, test weight, and heading date, were evaluated across 33 environments (location-year) using over 3,200 breeding lines from the North Carolina State University small grains breeding program. Multiple genomic prediction models were compared using several cross-validation (CV) schemes representing common breeding scenarios. Across traits, the reaction norm M5 model, which incorporates both GxE and genotype-by-environmental covariate interactions (GxO), achieved the highest prediction accuracy (PA) in CV2 (predicting incomplete field trials) and CV1 for yield and test weight (predicting new lines). The highest PA was observed for test weight under CV2 (0.54) and for yield under CV1 (0.41). Under CV0 (predicting new environments), the M3 model incorporating GxE produced highest PA across traits, with the greatest accuracy for plant height (0.45), although differences among M2, M3, and M4 were small. Prediction under CV00 (predicting new lines in new environments) remained more challenging, with PA values 0.10 - 0.20 across traits. Overall, our results demonstrate that integrating environmental covariates into genomic prediction models can improve predictive performance across diverse wheat-growing environments in North Carolina, supporting their utility for applied breeding efforts. CORE IDEASO_LIIntegrating genotype-by-environment (GxE) interactions with environmental covariates improves prediction accuracy across environments. C_LIO_LIModel performance varies by prediction scenario, with different approaches performing best for new lines, incomplete trials, or new environments. C_LIO_LIPrediction of new lines in new environments remains challenging. C_LI PLAIN LANGUAGE SUMMARYThis study explores how adding environmental information to genomic prediction models can improve prediction accuracy in a public winter wheat breeding program. Using data from multi-environment trials conducted across diverse conditions in North Carolina, we evaluated statistical models that capture how different wheat lines respond to changing environments. By incorporating weather data, we improved the ability to predict performance across locations and years. These findings provide practical insights for refining selection strategies and accelerating genetic gain in wheat breeding.

Achieving high-throughput and precise phenotypic quantification and imaging modalities of stomatal and epidermal cells across diverse species remains a primary bottleneck in elucidating the mechanisms of stomatal dynamics, epidermal patterning, and environmental adaptation of plants. Here, we developed EpiReasoner, an artificial intelligence framework comprising a vision module, EpiVision, and a knowledge-based reasoning module, EpiBrain, for the quantitative phenotypic analysis and domain-specific knowledge reasoning of stomatal complexes and pavement cells in plants. Operating across bright-field, scanning electron microscopy, and differential interference contrast modalities, EpiVision achieves precise instance segmentation in various monocotyledonous, dicotyledonous, and fern species. Its performance significantly surpasses current state-of-the-art models. Moreover, we defined 23 quantitative indices describing stomatal cell morphology and spatial distribution. For domain-specific tasks such as phenotype prediction, genotype deduction, and molecular mechanism reasoning, EpiBrain demonstrates a human preference rate significantly higher than that of general-purpose large language models, including GPT-5 and Claude Sonnet 4. The application of EpiReasoner to phenotypic data of stomatal density derived from a tomato natural population of 170 accessions successfully identified a major quantitative trait locus on chromosome 8. The candidate gene, SKP1-interaction partner 19L (SKIP19L), encoding an F-box family protein, exhibited severe allele frequency drift during tomato domestication, which is highly consistent with the adaptive trend of reduced stomatal density under artificial selection. EpiReasoner provides a novel paradigm that unifies visual phenomics and knowledge-driven reasoning for the biology of stomata and pavement cells, thereby significantly accelerating scientific discovery in plant science.

PurposeGenotype-by-environment (G x E) interactions represent a major obstacle to increasing genetic gain in crop breeding, with the underlying physiological drivers often remaining obscured within conventional statistical models. This case study presents a novel framework that transforms the latent factors from Factor Analytic (FA) multi-environment trial (MET) models into heritable quantitative traits, enabling the genetic dissection of adaptive response patterns. MethodsA Factor Analytical Linear Mixed Model (FA-LMM) was fit to plot-level yield data for 1,036 barley genotypes across eight Australian trials. ResultsCorrelation of the factor loadings with APSIM-simulated environmental covariates demonstrated that the second latent factor FA2 was strongly correlated with the Water Stress Index (r = -0.83) during the critical flowering period, establishing water availability as the main biological axis of crossover Gx E. Genotypic scores for the derived traits, Overall Performance (OP) and Water Stress Response (WSR), were subjected to high-resolution haplotype-based mapping using local Genomic Estimated Breeding Values (GEBV). ConclusionThis analysis successfully identified major genomic regions that accounted for a substantial proportion of the additive genetic variance. Gene Ontology enrichment of candidate genes within the top haploblocks implicated fundamental pathways related to energy homeostasis, root development, and stress response, with notable candidates including FTsH11, BPS1, and TDP1. The distribution of favourable Haplotypes of Interest (HOI) in elite cultivars suggested a historical signature of inadvertent selection for these adaptive mechanisms. This framework provides an explicit bridge between statistical modelling and functional genomics, offering breeders actionable genetic targets for accelerated development of climate-resilient cereals.

Micro-dwarf tomato cultivars are increasingly considered for urban and controlled-environment agriculture due to their compact architecture and suitability for high-density planting. However, optimal canopy management strategies for these cultivars remain poorly defined. In this study, we evaluated the effects of different leaf removal intensities on leaf-level physiological performance, fruit yield, and fruit quality in three micro-dwarf tomato cultivars (Mohammed, Hahms Gelbe Topftomate, and Red Robin) grown under contrasting seasonal light conditions. Plants were subjected to low (15%), moderate (30%), or severe (90%) leaf removal, and leaf-level gas exchange was measured across canopy layers, along with yield and fruit quality assessments. Severe leaf removal (90%) increased carbon assimilation, transpiration, and stomatal conductance in middle and lower canopy leaves by up to approximately twofold compared with control plants, indicating improved light availability at the leaf level. However, these physiological enhancements did not consistently translate into higher yield, reflecting reduced whole-plant source capacity under excessive leaf removal. Low to moderate leaf removal (15-30%) generally increased or maintained yield and fruit number, whereas severe leaf removal reduced yield in Hahms Gelbe and Red Robin, particularly under low seasonal radiation. In contrast, Mohammed exhibited yield increases of up to 220% under low leaf removal and maintained increased yield even under severe leaf removal under high-light conditions. Fruit quality was largely unaffected by leaf removal, except for total soluble solids, which declined by approximately 12% under severe leaf removal across cultivars, consistent with sugar dilution under source limitation. Overall, these results demonstrate that optimal leaf removal in micro-dwarf tomatoes requires balancing improved canopy light distribution with maintenance of sufficient leaf area for carbon assimilation. Leaf removal thresholds are strongly cultivar- and light-dependent, emphasizing the need for cultivar-specific canopy management strategies in compact tomato systems and controlled-environment agriculture.

Light is a modifiable determinant of health, yet real-world exposure assessment is often reduced to illuminance alone, lacks environmental context, or relies on privacy-sensitive sensing. We present SpectraVita, a low-cost, compact multispectral wearable that continuously samples 11 ultraviolet-to-near-infrared bands and, through a privacy-preserving pipeline without cameras or location tracking, produces interpretable digital phenotypes of lighting environment (natural vs. artificial and source type) and vegetation context alongside standard visual and non-visual light metrics. In extensive in-the-wild recordings spanning diverse scenes, times of day, weather conditions, and light sources, we observe distinctive spectral signatures that enable supervised models to achieve a macro-averaged F1 score of 0.988{+/-}0.004 for light-source classification and green-space detection in boundary-free environments. A sensor-derived normalized difference vegetation index (NDVI) emerges as an explainable, physically grounded marker linking natural light exposure and greenness. Robustness is supported by scenario-shift testing, image-segmentation validation, and mixed-environment experiments that demonstrate sensitivity to partial and transient exposures, as well as by longitudinal stationary monitoring and deployment in a cohort of thousands of participants capturing seasonal and behavioral variability. SpectraVita enables individualized, privacy-preserving, longitudinal monitoring of light and greenness exposure at scale, addressing a key measurement gap for precision and population health studies of daily photic environments.

Kernel composition traits in maize, including protein accumulation, are of broad interest. The amount of the most abundant proteins in maize endosperm, the -zeins, can vary dramatically among genotypes and in response to soil nitrogen supply. Targeted reductions in -zein accumulation can improve nitrogen utilization and the nutritional quality of maize grain but have traditionally required expensive and destructive phenotyping methods. The Floury2-RFP (Fl2-RFP) reporter gene enables rapid, non-destructive visualization of -zein accumulation in individual maize kernels under white light. This feature is due to the high expression level programmed by the Fl2 promoter, the stability of zein proteins, and the use of monomeric RFP, which emits fluorescence without the need for multimerization. This study aimed to develop a method to quickly document and quantify Fl2-RFP accumulation using camera or smartphone images of either ears or shelled kernels. Results show images of shelled kernels processed with FIJI software capture the Fl2-RFP reporter phenotype better than images of ears. Fl2-RFP confirms the strong maternal control of -zein accumulation and, like grain protein concentration, responds to soil nitrogen supply. The Fl2-RFP phenotyping pipeline effectively quantified Fl2-RFP accumulation by color features from both camera and smartphone images. Smartphone imaging of Fl2-RFP in a diverse population of inbreds followed by elastic net regression of extracted image features predicted kernel protein concentration, as measured by near-infrared spectroscopy, with moderate accuracy (R2 = 0.68, MAE = 0.76, RMSE = 0.93). The spectral features that were most predictive of kernel protein concentration varied depending on whether the background endosperm color was white or yellow. The integrated analysis of Fl2-RFP intensity and grain protein concentration indicates genetic variation for kernel protein accumulation and N-responsiveness that is distinct from the well-studied -zeins. Our findings highlight the Fl2-RFP reporter gene as a valuable tool for investigating the genetic complexity of grain protein concentration and associated traits in maize.

Understanding plant growth dynamics requires imaging across day-and-night cycles to quantify growth, movement and development in the aerial plant body and to capture the rhythmic nature of these processes. This requires imaging in light during the day and in darkness at night without perturbing plant physiology. Nighttime imaging has typically depended on infrared (IR) illumination, producing monochrome datasets that require specialised hardware and separate analysis pipelines when combined with daytime RGB imaging. Here, we evaluated very low-intensity green (dimG) illumination from standard LEDs as a practical alternative for colour-consistent nighttime imaging and assessed its physiological impact in Arabidopsis thaliana and Lactuca sativa (lettuce). We show that high resolution colour images can be obtained under dimG using low- cost cameras, with sufficient consistency between full-spectrum and dimG images to allow direct comparison and unified image analysis. We show that very low-fluence green light (<0.5 mol m-2 s-1) does not sustain circadian oscillations of gene activity under continuous exposure and does not perturb rhythms when applied during the dark phase of diel cycles. DimG imaging enabled accurate detection of diel leaf movement profiles in Arabidopsis circadian mutants, revealing genotype-specific phase differences under varying photoperiods. In lettuce, dimG pulses and continuous dimG enabled accurate quantification of diel leaf movement without affecting growth, stomatal opening, electron transport rate or chlorophyll content. Motion profiles under continuous dimG mirrored those under darkness. Our findings establish dim green illumination as a cost-effective solution for night-time imaging, simplifying phenotyping workflows with minimal impact on physiology.

Foundation models pre-trained on massive datasets have demonstrated impressive performance, but in some specialised domains have been found to have lower accuracy. Domain-specific foundation models target a particular domain such as retinal or plant images. These domain-specific models have shown inconsistent results and the benefit to root segmentation is unknown. We train and evaluate the first domain-specific foundation model for root segmentation. Evaluation uses a leave-one-dataset-out design across nine diverse root datasets with two architectures. The domain-specific model segments unseen root datasets zero-shot (without any fine-tuning on the unseen dataset), achieving a mean Dice of 0.636 versus 0.698 for individually fine-tuned models, that is, 92% of fine-tuned Dice on average and above 90% for 5 of 9 datasets. We also test few-shot transfer learning. Fine-tuning on only 10 patches, the domain-specific model recovers 95% of its full-data Dice on average, versus 69% for a general pre-trained model. With full target-data fine-tuning, the two perform comparably, with mean improvements of +0.011 Dice for MobileSAM and +0.022 for M2F Swin-S, neither significant (Wilcoxon p = 0.150 and 0.064). We release our pre-trained MobileSAM root foundation model for use with RootPainter, enabling fully automatic root segmentation on new datasets with an ordinary laptop or desktop computer, with no need for annotation or training.