G × E × M analysis to define allometric rules between leaves and stems in wheat.

Allometric rules provide insights into the structure-function relationships across species and scales and are commonly used in ecology. The fields of agronomy, plant phenotyping and modeling also need simplifications such as allometric rules to reconcile data at different temporal and spatial levels (organs/canopy). This paper explores the variations in relationships for wheat regarding (i) the distribution of crop green area between leaves and stems, and (ii) the allocation of above-ground biomass between leaves and stems during the vegetative period, using a large dataset covering different years, countries, genotypes and management practices. Our results show that the relationship between leaf and stem area was linear, genotype-specific, and sensitive to radiation. The relationship between leaf and stem biomass depended on genotype and nitrogen fertilization. The mass per area, associating area and biomass for both leaf and stem, varied strongly by developmental stage and was significantly affected by environment and genotype. These allometric rules were evaluated with satisfactory performance, and their potential use is discussed with regard to current phenotyping techniques and plant/crop models. Our results enable the definition of models and minimum datasets required for characterizing diversity panels and making predictions in various G × E × M contexts.

Analyzing Changes in Maize Leaves Orientation due to GxExM Using an Automatic Method from RGB Images.

The sowing pattern has an important impact on light interception efficiency in maize by determining the spatial distribution of leaves within the canopy. Leaves orientation is an important architectural trait determining maize canopies light interception. Previous studies have indicated how maize genotypes may adapt leaves orientation to avoid mutual shading with neighboring plants as a plastic response to intraspecific competition. The goal of the present study is 2-fold: firstly, to propose and validate an automatic algorithm (Automatic Leaf Azimuth Estimation from Midrib detection [ALAEM]) based on leaves midrib detection in vertical red green blue (RGB) images to describe leaves orientation at the canopy level; and secondly, to describe genotypic and environmental differences in leaves orientation in a panel of 5 maize hybrids sowing at 2 densities (6 and 12 plants.m-2) and 2 row spacing (0.4 and 0.8 m) over 2 different sites in southern France. The ALAEM algorithm was validated against in situ annotations of leaves orientation, showing a satisfactory agreement (root mean square [RMSE] error = 0.1, R2 = 0.35) in the proportion of leaves oriented perpendicular to rows direction across sowing patterns, genotypes, and sites. The results from ALAEM permitted to identify significant differences in leaves orientation associated to leaves intraspecific competition. In both experiments, a progressive increase in the proportion of leaves oriented perpendicular to the row is observed when the rectangularity of the sowing pattern increases from 1 (6 plants.m-2, 0.4 m row spacing) towards 8 (12 plants.m-2, 0.8 m row spacing). Significant differences among the 5 cultivars were found, with 2 hybrids exhibiting, systematically, a more plastic behavior with a significantly higher proportion of leaves oriented perpendicularly to avoid overlapping with neighbor plants at high rectangularity. Differences in leaves orientation were also found between experiments in a squared sowing pattern (6 plants.m-2, 0.4 m row spacing), indicating a possible contribution of illumination conditions inducing a preferential orientation toward east-west direction when intraspecific competition is low.

Global Wheat Head Detection Challenges: Winning Models and Application for Head Counting.

Data competitions have become a popular approach to crowdsource new data analysis methods for general and specialized data science problems. Data competitions have a rich history in plant phenotyping, and new outdoor field datasets have the potential to embrace solutions across research and commercial applications. We developed the Global Wheat Challenge as a generalization competition in 2020 and 2021 to find more robust solutions for wheat head detection using field images from different regions. We analyze the winning challenge solutions in terms of their robustness when applied to new datasets. We found that the design of the competition had an influence on the selection of winning solutions and provide recommendations for future competitions to encourage the selection of more robust solutions.

VegAnn, Vegetation Annotation of multi-crop RGB images acquired under diverse conditions for segmentation.

Applying deep learning to images of cropping systems provides new knowledge and insights in research and commercial applications. Semantic segmentation or pixel-wise classification, of RGB images acquired at the ground level, into vegetation and background is a critical step in the estimation of several canopy traits. Current state of the art methodologies based on convolutional neural networks (CNNs) are trained on datasets acquired under controlled or indoor environments. These models are unable to generalize to real-world images and hence need to be fine-tuned using new labelled datasets. This motivated the creation of the VegAnn - Vegetation Annotation - dataset, a collection of 3775 multi-crop RGB images acquired for different phenological stages using different systems and platforms in diverse illumination conditions. We anticipate that VegAnn will help improving segmentation algorithm performances, facilitate benchmarking and promote large-scale crop vegetation segmentation research.

Global Wheat Head Detection 2021: An Improved Dataset for Benchmarking Wheat Head Detection Methods.

The Global Wheat Head Detection (GWHD) dataset was created in 2020 and has assembled 193,634 labelled wheat heads from 4700 RGB images acquired from various acquisition platforms and 7 countries/institutions. With an associated competition hosted in Kaggle, GWHD_2020 has successfully attracted attention from both the computer vision and agricultural science communities. From this first experience, a few avenues for improvements have been identified regarding data size, head diversity, and label reliability. To address these issues, the 2020 dataset has been reexamined, relabeled, and complemented by adding 1722 images from 5 additional countries, allowing for 81,553 additional wheat heads. We now release in 2021 a new version of the Global Wheat Head Detection dataset, which is bigger, more diverse, and less noisy than the GWHD_2020 version.

Global Wheat Head Detection (GWHD) Dataset: A Large and Diverse Dataset of High-Resolution RGB-Labelled Images to Develop and Benchmark Wheat Head Detection Methods.

The detection of wheat heads in plant images is an important task for estimating pertinent wheat traits including head population density and head characteristics such as health, size, maturity stage, and the presence of awns. Several studies have developed methods for wheat head detection from high-resolution RGB imagery based on machine learning algorithms. However, these methods have generally been calibrated and validated on limited datasets. High variability in observational conditions, genotypic differences, development stages, and head orientation makes wheat head detection a challenge for computer vision. Further, possible blurring due to motion or wind and overlap between heads for dense populations make this task even more complex. Through a joint international collaborative effort, we have built a large, diverse, and well-labelled dataset of wheat images, called the Global Wheat Head Detection (GWHD) dataset. It contains 4700 high-resolution RGB images and 190000 labelled wheat heads collected from several countries around the world at different growth stages with a wide range of genotypes. Guidelines for image acquisition, associating minimum metadata to respect FAIR principles, and consistent head labelling methods are proposed when developing new head detection datasets. The GWHD dataset is publicly available at http://www.global-wheat.com/and aimed at developing and benchmarking methods for wheat head detection.

Architectural Response of Wheat Cultivars to Row Spacing Reveals Altered Perception of Plant Density.

Achieving novel improvements in crop management may require changing interrow distance in cultivated fields. Such changes would benefit from a better understanding of plant responses to the spatial heterogeneity in their environment. Our work investigates the architectural plasticity of wheat plants in response to increasing row spacing and evaluates the hypothesis of a foraging behavior in response to neighboring plants. A field experiment was conducted with five commercial winter wheat cultivars possessing unique architectures, grown under narrow (NI, 17.5 cm) or wide interrows (WI, 35 cm) at the same population density (170 seeds/m2). We characterized the development (leaf emergence, tillering), the morphology (dimension of organs, leaf area index), and the geometry (ground cover, leaf angle, organ spreading, and orientation). All cultivars showed a lower number of emerged tillers in WI compared to NI, which was later partly compensated by lower tiller mortality. Besides, the upper leaf blades were larger in WI. Finally the leaf area index at flowering showed little difference between WI and NI treatments. The rate of leaf emergence and the final leaf number were higher in WI compared to NI, except for one cultivar. Around the start of stem elongation, pseudo-stems were more erect in WI, while around the time of flowering, stems were more inclined and leaves were more planophile. Cultivars differed in their degrees of responses, with one appearing to prospect more specifically within the interrow space in WI treatment. Altogether, our results suggest that altering interrow distance leads to changes in the perceived extent of competition by plants, with responses first mimicking the effect of a higher plant density and later the effect of a lower plant density. Only one cultivar showed responses that suggested a perception of the heterogeneity of the environment. These findings improve our understanding of plant responses to spatial heterogeneity and provide novel information to simulate light capture in plant 3D models, depending on cultivar behavior.

High-Throughput Measurements of Stem Characteristics to Estimate Ear Density and Above-Ground Biomass.

Total above-ground biomass at harvest and ear density are two important traits that characterize wheat genotypes. Two experiments were carried out in two different sites where several genotypes were grown under contrasted irrigation and nitrogen treatments. A high spatial resolution RGB camera was used to capture the residual stems standing straight after the cutting by the combine machine during harvest. It provided a ground spatial resolution better than 0.2 mm. A Faster Regional Convolutional Neural Network (Faster-RCNN) deep-learning model was first trained to identify the stems cross section. Results showed that the identification provided precision and recall close to 95%. Further, the balance between precision and recall allowed getting accurate estimates of the stem density with a relative RMSE close to 7% and robustness across the two experimental sites. The estimated stem density was also compared with the ear density measured in the field with traditional methods. A very high correlation was found with almost no bias, indicating that the stem density could be a good proxy of the ear density. The heritability/repeatability evaluated over 16 genotypes in one of the two experiments was slightly higher (80%) than that of the ear density (78%). The diameter of each stem was computed from the profile of gray values in the extracts of the stem cross section. Results show that the stem diameters follow a gamma distribution over each microplot with an average diameter close to 2.0 mm. Finally, the biovolume computed as the product of the average stem diameter, the stem density, and plant height is closely related to the above-ground biomass at harvest with a relative RMSE of 6%. Possible limitations of the findings and future applications are finally discussed.

Management and Characterization of Abiotic Stress via PhénoField®, a High-Throughput Field Phenotyping Platform.

In order to evaluate the impact of water deficit in field conditions, researchers or breeders must set up large experiment networks in very restrictive field environments. Experience shows that half of the field trials are not relevant because of climatic conditions that do not allow the stress scenario to be tested. The PhénoField® platform is the first field based infrastructure in the European Union to ensure protection against rainfall for a large number of plots, coupled with the non-invasive acquisition of crops' phenotype. In this paper, we will highlight the PhénoField® production capability using data from 2017-wheat trial. The innovative approach of the PhénoField® platform consists in the use of automatic irrigating rainout shelters coupled with high throughput field phenotyping to complete conventional phenotyping and micrometeorological densified measurements. Firstly, to test various abiotic stresses, automatic mobile rainout shelters allow fine management of fertilization or irrigation by driving daily the intensity and period of the application of the desired limiting factor on the evaluated crop. This management is based on micro-meteorological measurements coupled with a simulation of a carbon, water and nitrogen crop budget. Furthermore, as high-throughput plant-phenotyping under controlled conditions is well advanced, comparable evaluation in field conditions is enabled through phenotyping gantries equipped with various optical sensors. This approach, giving access to either similar or innovative variables compared manual measurements, is moreover distinguished by its capacity for dynamic analysis. Thus, the interactions between genotypes and the environment can be deciphered and better detailed since this gives access not only to the environmental data but also to plant responses to limiting hydric and nitrogen conditions. Further data analyses provide access to the curve parameters of various indicator kinetics, all the more integrative and relevant of plant behavior under stressful conditions. All these specificities of the PhénoField® platform open the way to the improvement of various categories of crop models, the fine characterization of variety behavior throughout the growth cycle and the evaluation of particular sensors better suited to a specific research question.

High-Throughput Phenotyping of Plant Height: Comparing Unmanned Aerial Vehicles and Ground LiDAR Estimates.

The capacity of LiDAR and Unmanned Aerial Vehicles (UAVs) to provide plant height estimates as a high-throughput plant phenotyping trait was explored. An experiment over wheat genotypes conducted under well watered and water stress modalities was conducted. Frequent LiDAR measurements were performed along the growth cycle using a phénomobile unmanned ground vehicle. UAV equipped with a high resolution RGB camera was flying the experiment several times to retrieve the digital surface model from structure from motion techniques. Both techniques provide a 3D dense point cloud from which the plant height can be estimated. Plant height first defined as the z-value for which 99.5% of the points of the dense cloud are below. This provides good consistency with manual measurements of plant height (RMSE = 3.5 cm) while minimizing the variability along each microplot. Results show that LiDAR and structure from motion plant height values are always consistent. However, a slight under-estimation is observed for structure from motion techniques, in relation with the coarser spatial resolution of UAV imagery and the limited penetration capacity of structure from motion as compared to LiDAR. Very high heritability values (H2> 0.90) were found for both techniques when lodging was not present. The dynamics of plant height shows that it carries pertinent information regarding the period and magnitude of the plant stress. Further, the date when the maximum plant height is reached was found to be very heritable (H2> 0.88) and a good proxy of the flowering stage. Finally, the capacity of plant height as a proxy for total above ground biomass and yield is discussed.

A semi-automatic system for high throughput phenotyping wheat cultivars in-field conditions: description and first results.

A semi-automatic system was developed to monitor micro-plots of wheat cultivars in field conditions for phenotyping. The system is based on a hyperspectral radiometer and 2 RGB cameras observing the canopy from ~1.5m distance to the top of the canopy. The system allows measurement from both nadir and oblique views inclined at 57.5° zenith angle perpendicularly to the row direction. The system is fixed to a horizontal beam supported by a tractor that moves along the micro-plots. About 100 micro-plots per hour were sampled by the system, the data being automatically collected and registered thanks to a centimetre precision geo-location. The green fraction (GF, the fraction of green area per unit ground area as seen from a given direction) was derived from the images with an automatic segmentation process and the reflectance spectra recorded by the radiometers were transformed into vegetation indices (VI) such as MCARI2 and MTCI. Results showed that MCARI2 is a good proxy of the GF, the MTCI as observed from 57° inclination is expected to be mainly sensitive to leaf chlorophyll pigments. The frequent measurements achieved allowed a good description of the dynamics of each micro-plot along the growth cycle. It is characterised by two periods: the first period corresponding to the vegetative stages exhibits a small rate of change of VI with time; followed by the senescence period characterised by a high rate of change. The dynamics were simply described by a bilinear model with its parameters providing high throughput metrics (HTM). A variance analysis achieved over these HTMs showed that several HTMs were highly heritable, particularly those corresponding to MCARI2 as observed from nadir, and those corresponding to the first period. Potentials of such semi-automatic measurement system are discussed for in field phenotyping applications.