Combining High-Resolution Imaging,Deep Learning,and Dynamic Modeling to Separate Disease and Senescence in Wheat Canopies

Maintenance of sufficiently healthy green leaf area after anthesis is key to ensuring an adequate assimilate supply for grain filling.Tightly regulated age-related physiological senescence and various biotic and abiotic stressors drive overall greenness decay dynamics under field conditions.Besides direct effects on green leaf area in terms of leaf damage,stressors often anticipate or accelerate physiological senescence,which may multiply their negative impact on grain filling.Here,we present an image processing methodology that enables the monitoring of chlorosis and necrosis separately for ears and shoots(stems+leaves)based on deep learning models for semantic segmentation and color properties of vegetation.A vegetation segmentation model was trained using semisynthetic training data generated using image composition and generative adversarial neural networks,which greatly reduced the risk of annotation uncertainties and annotation effort.Application of the models to image time series revealed temporal patterns of greenness decay as well as the relative contributions of chlorosis and necrosis.Image-based estimation of greenness decay dynamics was highly correlated with scoring-based estimations(r≈0.9).Contrasting patterns were observed for plots with different levels of foliar diseases,particularly septoria tritici blotch.Our results suggest that tracking the chlorotic and necrotic fractions separately may enable(a)a separate quantification of the contribution of biotic stress and physiological senescence on overall green leaf area dynamics and(b)investigation of interactions between biotic stress and physiological senescence.The high-throughput nature of our methodology paves the way to conducting genetic studies of disease resistance and tolerance.

Frost Damage Index:The Antipode of Growing Degree Days

Abiotic stresses such as heat and frost limit plant growth and productivity.Image-based field phenotyping methods allow quantifying not only plant growth but also plant senescence.Winter crops show senescence caused by cold spells,visible as declines in leaf area.We accurately quantified such declines by monitoring changes in canopy cover based on time-resolved high-resolution imagery in the field.Thirty-six winter wheat genotypes were measured in multiple years.A concept termed"frost damage index"(FDI)was developed that,in analogy to growing degree days,summarizes frost events in a cumulative way.The measured sensitivity of genotypes to the FDI correlated with visual scorings commonly used in breeding to assess winter hardiness.The FDI concept could be adapted to other factors such as drought or heat stress.While commonly not considered in plant growth modeling,integrating such degradation processes may be key to improving the prediction of plant performance for future climate scenarios.

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.

Repeated Multiview Imaging for Estimating Seedling Tiller Counts of Wheat Genotypes Using Drones

Early generation breeding nurseries with thousands of genotypes in single-row plots are well suited to capitalize on high throughput phenotyping.Nevertheless,methods to monitor the intrinsically hard-to-phenotype early development of wheat are yet rare.We aimed to develop proxy measures for the rate of plant emergence,the number of tillers,and the beginning of stem elongation using drone-based imagery.We used RGB images(ground sampling distance of 3mm pixel-1)acquired by repeated flights(≥2 flights per week)to quantify temporal changes of visible leaf area.To exploit the information contained in the multitude of viewing angles within the RGB images,we processed them to multiview ground cover images showing plant pixel fractions.Based on these images,we trained a support vector machine for the beginning of stem elongation(GS30).Using the GS30 as key point,we subsequently extracted plant and tiller counts using a watershed algorithm and growth modeling,respectively.Our results show that determination coefficients of predictions are moderate for plant count(R^(2)=0:52),but strong for tiller count(R^(2)=0:86)and GS30(R^(2)=0:77).Heritabilities are superior to manual measurements for plant count and tiller count,but inferior for GS30 measurements.Increasing the selection intensity due to throughput may overcome this limitation.Multiview image traits can replace hand measurements with high efficiency(85-223%).We therefore conclude that multiview images have a high potential to become a standard tool in plant phenomics.

Precision Phenotyping Reveals Novel Loci for Quantitative Resistance to Septoria Tritici Blotch

Accurate,high-throughput phenotyping for quantitative traits is a limiting factor for progress in plant breeding.We developed an automated image analysis to measure quantitative resistance to septoria tritici blotch(STB),a globally important wheat disease,enabling identification of small chromosome intervals containing plausible candidate genes for STB resistance.335 winter wheat cultivars were included in a replicated field experiment that experienced natural epidemic development by a highly diverse but fungicide-resistant pathogen population.More than 5.4 million automatically generated phenotypes were associated with 13,648 SNP markers to perform the GWAS.We identified 26 chromosome intervals explaining 1.9-10.6%of the variance associated with four independent resistance traits.Sixteen of the intervals overlapped with known STB resistance intervals,suggesting that our phenotyping approach can identify simultaneously(i.e.,in a single experiment)many previously defined STB resistance intervals.Seventeen of the intervals were less than 5 Mbp in size and encoded only 173 genes,including many genes associated with disease resistance.Five intervals contained four or fewer genes,providing high priority targets for functional validation.Ten chromosome intervals were not previously associated with STB resistance,perhaps representing resistance to pathogen strains that had not been tested in earlier experiments.The SNP markers associated with these chromosome intervals can be used to recombine different forms of quantitative STB resistance that are likely to be more durable than pyramids of major resistance genes.Our experiment illustrates how high-throughput automated phenotyping can accelerate breeding for quantitative disease resistance.