Scott David Noble

High-throughput phenotyping is essential for accelerating genetic gain in cereal breeding; however, field-based measurement of key agronomic traits remains labor-intensive and temporally limited. This study developed and evaluated a multimodal artificial intelligence framework for predictive modelling and in-season forecasting of structural, phenological, and productivity-related traits in spring wheat using integrated proximal sensing and environmental observations. Field experiments were conducted across six Agriculture and Agri-Food Canada research sites representing major wheat-growing regions of Canada. The phenotyping platform combined LiDAR-derived three-dimensional canopy structural measurements with red–green–blue (RGB) and near-infrared (NIR) imagery acquired using an uncrewed ground vehicle, together with environmental weather observations and validated ground-truth trait data. Standardized preprocessing and data integration pipelines transformed heterogeneous sensor outputs into a harmonized multimodal dataset suitable for deep learning–based modelling. Across regression traits, the models demonstrated strong predictive performance. Heading date achieved the highest accuracy (R2 = 0.94; RMSE = 1.03 days), followed by plant height (R2 = 0.92; RMSE = 6.28 cm) and maturity (R2 = 0.91; RMSE = 3.13 days). Grain yield prediction achieved an R2 of 0.87 (RMSE = 581 kg ha-1) despite substantial environmental variability across sites. The framework also enabled reliable in-season forecasting of phenological progression and yield potential. Lodging severity classification achieved an overall accuracy of 0.75 with a quadratic weighted kappa of 0.86, indicating strong ordinal agreement between predicted and observed lodging scores. Feature attribution analyses identified weather variables as primary drivers of phenological development and yield formation, while LiDAR-derived canopy structural information and spectral imagery provided complementary insights into crop architecture and physiological status. These findings demonstrate that multimodal artificial intelligence can support accurate, scalable, and operationally deployable crop trait prediction and forecasting, providing a strong foundation for automated phenotyping and data-driven decision support in modern cereal breeding systems.

Corrigendum: The effects of sampling and instrument orientation on LiDAR data from crop plots

Wheat is one of the most widely consumed grains in the world and improving its yield, especially under severe climate conditions, is of great importance to world food security. Phenotyping methods can evaluate plants according to their different traits, such as yield and growth characteristics. Assessing the vertical stand structure of plants can provide valuable information about plant productivity and processes, mainly if this trait can be tracked throughout the plant’s growth. Light Detection And Ranging (LiDAR) is a method capable of gathering three-dimensional data from wheat field trials and is potentially suitable for providing non-destructive, high-throughput estimations of the vertical stand structure of plants. The current study considers LiDAR and focuses on investigating the effects of sub-sampling plot data and data collection parameters on the canopy vertical profile (CVP). The CVP is a normalized, ground-referenced histogram of LiDAR point cloud data representing a plot or other spatial domain. The effects of sub-sampling of plot data, the angular field of view (FOV) of the LiDAR and LiDAR scan line orientation on the CVP were investigated. Analysis of spatial sub-sampling effects on CVP showed that at least 144000 random points (600 scan lines) or an area equivalent to three plants along the row were adequate to characterize the overall CVP of the aggregate plot. A comparison of CVPs obtained from LiDAR data for different FOV showed that CVPs varied with the angular range of the LiDAR data, with narrow ranges having a larger proportion of returns in the upper canopy and a lower proportion of returns in the lower part of the canopy. These findings will be necessary to establish minimum plot and sample sizes and compare data from studies where scan direction or field of view differ. These advancements will aid in making comparisons and inform best practices for using close-range LiDAR in phenotypic studies in crop breeding and physiology research.

Pea is a grain legume crop commonly grown in semi-arid temperate regions. Pea is susceptible to heat stress that affects development and reduces yield. Leaf pigments and surface wax in a crop canopy make the primary interaction with the environment and can impact plant response to environmental stress. Vegetation indices can be used to indirectly assess canopy performance in regard to pigment, biomass, and water content to indicate overall plant stress. Our objectives were to investigate the contribution of leaf pigments and surface wax to heat avoidance in pea canopies, and their associations with spectral vegetation indices. Canopies represented by 24 pea cultivars varying in leaf traits were tested in field trials across six environments with three stress levels in western Canada. Compared with the control non-stress environments, heat stress reduced leaf lamina and petiole chlorophyll a, chlorophyll b, and carotenoid concentrations by 18–35%, and increased leaf lamina chlorophyll a/b ratio, anthocyanin and wax concentrations by 24–28%. Generally, greater leaf pigment and wax concentrations were associated with cooler canopy temperature and high heat tolerance index (HTI) values. Upright cultivars had higher HTI values, whereas the lowest HTI was associated with normal leafed vining cultivars. Vegetation indices, including photochemical reflectance index (PRI), green normalized vegetation index (GNDVI), normalized pigment chlorophyll ratio index (NPCI), and water band index (WBI), had strong correlations with HTI and with heat avoidance traits. This study highlights the contribution of pigments and wax as heat avoidance traits in crop canopies, and the potential application of spectral measurements for selecting genotypes with more heat resistant vegetation.

Summary: The effects of thermal aging on tensile strength of three Kevlar/PBI blends used in the outer shell layer of firefighters' protective clothing were examined using cone calorimeter exposures of 10‐70 kW/m² for 30‐300 seconds. Lower heat flux exposures of 10‐15 kW/m² did not result in significant change in the tensile strength of the fabrics, but significant losses of tensile strength were first observed as the heat fluxes increased to 20‐30 kW/m² for two ripstop fabrics, and 45 kW/m² for the third fabric. Further decreases in tensile strength were observed with increasing heat flux until there was almost a total loss of original tensile strength following exposure to 70 kW/m². Decreases in tensile strength were explained by comparing fabric temperature measurements made using an infrared thermometer, key temperatures in thermal gravimetric analysis test results, and the appearance of the three fabrics after the exposures. While duration of exposure had little effect on tensile strength after exposures to 10 kW/m², tensile strength decreased with duration of exposure for heat fluxes of 20‐40 kW/m². The effect of duration was greatest for a heat flux of 20 kW/m². These results indicate that one must consider not only the maximum temperature that the fabric reaches, but the complete temperature‐time trace, including the time at which the fabric remains at the maximum temperature, when examining the effects of thermal aging on tensile strength.

Background: Seed coat thickness is a parameter of interest in lentil breeding and processing. Methods described in the literature are destructive and time consuming, limiting the usefulness of this seed characteristic in breeding or grading. In this study, a low-cost optical coherence tomography (OCT) system (OQ Labscope 2.0 from Lumedica, Inc., Durham, NC USA) was used to non-destructively measure lentil seed coat thicknesses. These measurements were compared to destructive measurements obtained via optical microscopy of cross-sectioned seeds. Results: Measurements from the two methods were comparable with consistent trends in thickness and population separability among the five lentil accessions used. The average microscope-based measurements for each accession were higher than those from the OCT, with a linear relationship between the two sets of measurements. The discrepancy in absolute thicknesses is attributed to differences in instrument calibration and in the definition of seed coat boundaries in the two methods. Based on data collected from a larger population, OCT measurements took a mean time of 30 seconds/seed, and a median time of 16 seconds/seed, with no sample preparation required. Conclusions: Optical coherence tomography is a viable method for acquiring comparative data on seed coat thickness of lentil seeds, and presumably other species with similar seed characteristics. The method is non-destructive, and fast enough to be practical for studying large breeding populations. Opportunities for greater efficiencies as part of an automated imaging system are being explored.

A computer vision system and color analysis algorithms were employed to study the influence of UVA (ultraviolet‐A) and visible light on the color of lentils with red, green, and yellow cotyledons. Twenty samples of cotyledons from each of the three‐color classes were subjected to six light treatments (ultraviolet, full‐spectrum visible, red, green, blue, and dark control) for 7 days at room temperature. The International Commission on Illumination L*a*b* (CIE L*a*b*) color values of the individual seeds were obtained before and after each treatment using the computer vision and image analysis system. Results of the analysis showed that light exposure had a statistically significant effect on all three cotyledon color classes. The effect size was largest for green lentils, smaller in yellow, and least in red lentils. By having established that light exposure affects the color of lentil cotyledons, it was hypothesized that seed coats may protect cotyledons against the effects of light exposure and that the degree of protection would vary with seed coat color classification. This hypothesis was tested using green‐cotyledon lentil varieties with different seed coat classes. Results confirmed that light‐induced color loss in the cotyledons was significantly influenced by seed‐coat color class. The order of protective effect of lentil seed coat from least to highest was found to be as follows: gray‐zero tannin, green, normal gray, and black. Thus, breeding for seed coat protection may improve the overall quality of green lentils. The results from this study will be informative to breeding programs that focus on enhancing the cotyledon color of lentils, and in making decisions regarding the dehulling of lentils and the design of dehulled lentil materials handling.

The spectral reflectance of plant leaves has been measured and modeled for decades to inform remote methods for monitoring vegetation health and plant status. Many models and vegetation indices have been developed relating spectral reflectance characteristics to leaf pigment content and changes related to leaf internal structure. However, the wide variability in surface property contributions to leaf reflectance is not explicitly or significantly accounted for in the most prevalent models.¹ Models based on directional measurements use hemispherical leaf measurements in calibration and development. This method is useful for analysis of individual leaf measurements in a laboratory setting and can be applied when averaging canopy angle, but as the spatial resolution of data improves and close-range multiangular modeling of leaf surface–light interactions have more potential value. Some recent work has examined introducing directional effects, modeled as facets.^{2 – 5} Other works have looked at qualitative correlation of surface properties (wax loading, trichomes, and cell cap structure) to reflectance characteristics^6,7 and identified an increase in specular light reflectance with optically smooth and waxy leaves.