Search

Two new remotely sensed Leaf Area Index (LAI) and Surface Soil Moisture (SSM) satellite products are compared with two sets of simulations of the ORCHIDEE and ISBA-A-gs land surface models to investigate how recent droughts affected vegetation over the Euro-Mediterranean area. We analyze the interannual variability over the period 1991-2008. The leaf onset and the Length of the vegetation Growing Period (LGP) are derived from the satellite-derived LAI and from the modelled LAI. The LGP values produced by the photosynthesis-driven phenology model of ISBA-A-gs are closer to the satellite-derived LAI LGP than those produced by ORCHIDEE. In the latter, the phenology is based on a growing degree-day model for leaf onset, and on both climatic conditions and leaf life span for senescence. Further, the interannual variability of LAI is better captured by ISBA-A-gs than by ORCHIDEE. The summer 2003 drought case study shows a relatively good agreement of the modelled LAI anomalies with the observations, but the two models underestimate plant regrowth in the autumn. A better representation of the root-zone soil moisture profile could improve the simulations of both models. The satellite-derived SSM is compared with SSM simulations of ISBA-Ags, only, as ORCHIDEE has no explicit representation of SSM. Overall, the ISBA-A-gs simulations of SSM agree well with the satellite-derived SSM and are used to detect regions where the satellite product could be improved. Finally, a correspondence is found between the interannual variability of detrended SSM and LAI. The predictability of LAI is less pronounced using remote sensing observations than using simulated variables. However, consistent results are found in July for the croplands of Ukraine and southern Russia. [ABSTRACT FROM AUTHOR]

Moderate resolution satellite sensors including MODIS already provide more than 10 yr of observations well suited to describe and understand the dynamics of the Earth surface. However, these time series are incomplete because of cloud cover and associated with significant uncertainties. This study compares eight methods designed to improve the continuity by filling gaps and the consistency by smoothing the time course. It includes methods exploiting the time series as a whole (Iterative caterpillar singular spectrum analysis (ICSSA), empirical mode decomposition (EMD), low pass filtering (LPF) and Whittaker smoother (Whit)) as well as methods working on limited temporal windows of few weeks to few months (Adaptive Savitzky-Golay filter (SGF), temporal smoothing and gap filling (TSGF) and asymmetric Gaussian function (AGF)) in addition to the simple climatological LAI yearly profile (Clim). Methods were applied to MODIS leaf area index product for the period 2000-2008 over 25 sites showing a large range of seasonal patterns. Performances were discussed with emphasis on the balance achieved by each method between accuracy and roughness depending on the fraction of missing observations and the length of the gaps. Results demonstrate that EMD, LPF and AGF methods were failing in case of significant fraction of gaps (%Gap>20%), while ICSSA, Whit and SGF were always providing estimates for dates with missing data. TSGF (respectively Clim) was able to fill more than 50% of the gaps for sites with more than 60% (resp. 80%) fraction of gaps. However, investigation of the accuracy of the reconstructed values shows that it degrades rapidly for sites with more than 20% missing data, particularly for ICSSA, Whit and SGF. In these conditions, TSGF provides the best performances significantly better than the simple Clim for gaps shorter than about 100 days. The roughness of the reconstructed temporal profiles shows large differences between the several methods, with a decrease of the roughness with the fraction of missing data, except for ICSSA. TSGF provides the smoothest temporal profiles for sites with % Gap > 30%. Conversely, ICSSA, LPF, Whit, AGF and Clim provide smoother profiles than TSGF for sites with % Gap < 30%. Impact of the accuracy and smoothness of the reconstructed time series were evaluated on the timing of phenological stages. The dates of start, maximum and end of the season are estimated with an accuracy of about 10 days for the sites with % Gap < 10% and increases rapidly with % Gap. TSGF provides the more accurate estimates of phenological timing up to % Gap < 60%. [ABSTRACT FROM AUTHOR]

The strong societal demand to reduce pesticide use and adaptation to climate change challenges the capacities of phenotyping new varieties in the vineyard. High-throughput phenotyping is a way to obtain meaningful and reliable information on hundreds of genotypes in a limited period. We evaluated traits related to growth in 209 genotypes from an interspecific grapevine biparental cross, between IJ119, a local genitor, and Divona, both in summer and in winter, using several methods: fresh pruning wood weight, exposed leaf area calculated from digital images, leaf chlorophyll concentration, and LiDAR-derived apparent volumes. Using high-density genetic information obtained by the genotyping by sequencing technology (GBS), we detected 6 regions of the grapevine genome [quantitative trait loci (QTL)] associated with the variations of the traits in the progeny. The detection of statistically significant QTLs, as well as correlations ( R 2 ) with traditional methods above 0.46, shows that LiDAR technology is effective in characterizing the growth features of the grapevine. Heritabilities calculated with LiDAR-derived total canopy and pruning wood volumes were high, above 0.66, and stable between growing seasons. These variables provided genetic models explaining up to 47% of the phenotypic variance, which were better than models obtained with the exposed leaf area estimated from images and the destructive pruning weight measurements. Our results highlight the relevance of LiDAR-derived traits for characterizing genetically induced differences in grapevine growth and open new perspectives for high-throughput phenotyping of grapevines in the vineyard., Competing Interests: Competing interests: The authors declare that they have no competing interests., (Copyright © 2023 Elsa Chedid et al.)

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., (Copyright © 2023 Etienne David et al.)

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., (© 2023. The Author(s).)

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, R 2 = 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., (Copyright © 2023 Mario Serouart et al.)

The number of leaves at a given time is important to characterize plant growth and development. In this work, we developed a high-throughput method to count the number of leaves by detecting leaf tips in RGB images. The digital plant phenotyping platform was used to simulate a large and diverse dataset of RGB images and corresponding leaf tip labels of wheat plants at seedling stages (150,000 images with over 2 million labels). The realism of the images was then improved using domain adaptation methods before training deep learning models. The results demonstrate the efficiency of the proposed method evaluated on a diverse test dataset, collecting measurements from 5 countries obtained under different environments, growth stages, and lighting conditions with different cameras (450 images with over 2,162 labels). Among the 6 combinations of deep learning models and domain adaptation techniques, the Faster-RCNN model with cycle-consistent generative adversarial network adaptation technique provided the best performance ( R 2 = 0.94, root mean square error = 8.7). Complementary studies show that it is essential to simulate images with sufficient realism (background, leaf texture, and lighting conditions) before applying domain adaptation techniques. Furthermore, the spatial resolution should be better than 0.6 mm per pixel to identify leaf tips. The method is claimed to be self-supervised since no manual labeling is required for model training. The self-supervised phenotyping approach developed here offers great potential for addressing a wide range of plant phenotyping problems. The trained networks are available at https://github.com/YinglunLi/Wheat-leaf-tip-detection.

Head (panicle) density is a major component in understanding crop yield, especially in crops that produce variable numbers of tillers such as sorghum and wheat. Use of panicle density both in plant breeding and in the agronomy scouting of commercial crops typically relies on manual counts observation, which is an inefficient and tedious process. Because of the easy availability of red-green-blue images, machine learning approaches have been applied to replacing manual counting. However, much of this research focuses on detection per se in limited testing conditions and does not provide a general protocol to utilize deep-learning-based counting. In this paper, we provide a comprehensive pipeline from data collection to model deployment in deep-learning-assisted panicle yield estimation for sorghum. This pipeline provides a basis from data collection and model training, to model validation and model deployment in commercial fields. Accurate model training is the foundation of the pipeline. However, in natural environments, the deployment dataset is frequently different from the training data (domain shift) causing the model to fail, so a robust model is essential to build a reliable solution. Although we demonstrate our pipeline in a sorghum field, the pipeline can be generalized to other grain species. Our pipeline provides a high-resolution head density map that can be utilized for diagnosis of agronomic variability within a field, in a pipeline built without commercial software., (Copyright © 2023 Chrisbin James et al.)

Pixel segmentation of high-resolution RGB images into chlorophyll-active or nonactive vegetation classes is a first step often required before estimating key traits of interest. We have developed the SegVeg approach for semantic segmentation of RGB images into three classes (background, green, and senescent vegetation). This is achieved in two steps: A U-net model is first trained on a very large dataset to separate whole vegetation from background. The green and senescent vegetation pixels are then separated using SVM, a shallow machine learning technique, trained over a selection of pixels extracted from images. The performances of the SegVeg approach is then compared to a 3-class U-net model trained using weak supervision over RGB images segmented with SegVeg as groundtruth masks. Results show that the SegVeg approach allows to segment accurately the three classes. However, some confusion is observed mainly between the background and senescent vegetation, particularly over the dark and bright regions of the images. The U-net model achieves similar performances, with slight degradation over the green vegetation: the SVM pixel-based approach provides more precise delineation of the green and senescent patches as compared to the convolutional nature of U-net. The use of the components of several color spaces allows to better classify the vegetation pixels into green and senescent. Finally, the models are used to predict the fraction of three classes over whole images or regularly spaced grid-pixels. Results show that green fraction is very well estimated ( R 2 = 0.94) by the SegVeg model, while the senescent and background fractions show slightly degraded performances ( R 2 = 0.70 and 0.73, respectively) with a mean 95% confidence error interval of 2.7% and 2.1% for the senescent vegetation and background, versus 1% for green vegetation. We have made SegVeg publicly available as a ready-to-use script and model, along with the entire annotated grid-pixels dataset. We thus hope to render segmentation accessible to a broad audience by requiring neither manual annotation nor knowledge or, at least, offering a pretrained model for more specific use., Competing Interests: The authors declare that there is no conflict of interest regarding the publication of this article., (Copyright © 2022 Mario Serouart et al.)

Background: Gastric per oral endoscopic esophageal myotomy (G-POEM) is a promising procedure to treat refractory gastroparesis. The safety profile of G-POEM is an important topic because gastroparesis is a functional pathology, with a procedure whose effectiveness is between 50 and 65% depending on the studies., Objectives: We present this retrospective multicenter study, with the aim of establishing a safety profile, focusing on serious adverse events (AEs)., Design: This was a multicenter observational cohort study conducted in five French expert centers., Methods: All patients who underwent G-POEM for refractory gastroparesis between 2015 and 2021 were included for analysis. AEs were classified into per endoscopic, early postoperative, and late postoperative, up to 1 month. Their severity was assessed using Dindo-Clavien and American Society for Gastrointestinal Endoscopy classification. The primary objective was to evaluate the rate of G-POEM severe AEs. Secondary objectives were to document other postoperative AEs, and to identify predictive factors., Results: In all, 217 patients were included: 81 men and 136 women, mean age 52 ± 17 years. The average procedural time was 44 ± 14 min (12-78). The average hospital stay was 3.7 ± 2.3 days. The AEs rate classified as Clavien-Dindo ⩾3 was 0.4% (one delayed bleeding requiring blood transfusion and endoscopic management). There were no deaths or patients admitted to intensive care unit. The rates of mucosotomy and capnoperitoneum were 3.7 and 1.8%, respectively, without clinical consequences. Most patients (81.5%) did not experience any AE. Three cases of dumping syndrome occurred, quickly managed by dietary measures., Conclusion: Our study confirms the safety of G-POEM with less than 0.5% of serious AEs, medically managed. This outcome makes this a procedure to have a good benefit-risk ratio., Competing Interests: Competing interests: The authors declare that there is no conflict of interest., (© The Author(s), 2022.)

With the widespread use of high-throughput phenotyping systems, growth process data are expected to become more easily available. By applying genomic prediction to growth data, it will be possible to predict the growth of untested genotypes. Predicting the growth process will be useful for crop breeding, as variability in the growth process has a significant impact on the management of plant cultivation. However, the integration of growth modeling and genomic prediction has yet to be studied in depth. In this study, we implemented new prediction models to propose a novel growth prediction scheme. Phenotype data of 198 soybean germplasm genotypes were acquired for 3 years in experimental fields in Tottori, Japan. The longitudinal changes in the green fractions were measured using UAV remote sensing. Then, a dynamic model was fitted to the green fraction to extract the dynamic characteristics of the green fraction as five parameters. Using the estimated growth parameters, we developed models for genomic prediction of the growth process and tested whether the inclusion of the dynamic model contributed to better prediction of growth. Our proposed models consist of two steps: first, predicting the parameters of the dynamics model with genomic prediction, and then substituting the predicted values for the parameters of the dynamics model. By evaluating the heritability of the growth parameters, the dynamic model was able to effectively extract genetic diversity in the growth characteristics of the green fraction. In addition, the proposed prediction model showed higher prediction accuracy than conventional genomic prediction models, especially when the future growth of the test population is a prediction target given the observed values in the first half of growth as training data. This indicates that our model was able to successfully combine information from the early growth period with phenotypic data from the training population for prediction. This prediction method could be applied to selection at an early growth stage in crop breeding, and could reduce the cost and time of field trials., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2022 Toda, Sasaki, Ohmori, Yamasaki, Takahashi, Takanashi, Tsuda, Kajiya-Kanegae, Lopez-Lozano, Tsujimoto, Kaga, Nakazono, Fujiwara, Baret and Iwata.)

There is currently a strong societal demand for sustainability, quality, and safety in bread wheat production. To address these challenges, new and innovative knowledge, resources, tools, and methods to facilitate breeding are needed. This starts with the development of high throughput genomic tools including single nucleotide polymorphism (SNP) arrays, high density molecular marker maps, and full genome sequences. Such powerful tools are essential to perform genome-wide association studies (GWAS), to implement genomic and phenomic selection, and to characterize the worldwide diversity. This is also useful to breeders to broaden the genetic basis of elite varieties through the introduction of novel sources of genetic diversity. Improvement in varieties particularly relies on the detection of genomic regions involved in agronomical traits including tolerance to biotic (diseases and pests) and abiotic (drought, nutrient deficiency, high temperature) stresses. When enough resolution is achieved, this can result in the identification of candidate genes that could further be characterized to identify relevant alleles. Breeding must also now be approached through in silico modeling to simulate plant development, investigate genotype × environment interactions, and introduce marker-trait linkage information in the models to better implement genomic selection. Breeders must be aware of new developments and the information must be made available to the world wheat community to develop new high-yielding varieties that can meet the challenge of higher wheat production in a sustainable and fluctuating agricultural context. In this review, we compiled all knowledge and tools produced during the BREEDWHEAT project to show how they may contribute to face this challenge in the coming years.