Biology subjects

Comar, A.

Publications and source records attributed to Comar, A..

4 recordsLinked to original sources

bioRxiv2026

Phenomic selection enables nursery screening for field performance in maize and pea

Due to economical constraints, breeding programs eliminate most selection candidates at early stages, before their productivity can be evaluated in field trials. Genomic selection partially overcomes this limitation by enabling early prediction of field performance, but its implementation requires large-scale recurrent genotyping that remains inaccessible for many species and breeding programs. Phenomic selection offers a promising alternative by replacing genotyping with inexpensive high-dimensional phenotyping data. However, previous applications have focused on predicting genotypes already evaluated in field trials. We investigated whether phenomic data acquired by unoccupied aerial vehicles (UAVs) from nursery-grown genotypes can be used to predict their performance in field trials. We validated this nursery-screening approach in maize and pea, two species with contrasting biology and canopy structures, supporting its potential transferability to other species. In the most challenging scenarios, average accuracies for yield-related traits were between 0.36 for maize and 0.40 for pea. Simulations indicated that these accuracies can support substantial nursery culling while limiting the risk of discarding superior genotypes. This proof of concept demonstrates that UAV-based phenomic selection can predict the field performance of nursery-grown genotypes without genotyping the selection candidates.

genetics↗

bioRxiv2025

The Global Wheat Full Semantic Organ Segmentation (GWFSS) dataset

Computer vision is increasingly used in farmers fields and agricultural experiments to quantify important traits. Imaging setups with a sub-millimetre ground sampling distance enable the detection and tracking of plant features, including size, shape, and colour. Although todays AI-driven foundation models segment almost any object in an image, they still fail for complex plant canopies. To improve model performance, the global wheat dataset consortium assembled a diverse set of images from experiments around the globe. After the head detection dataset (GWHD), the new dataset targets a full semantic segmentation (GWFSS) of wheat organs (leaves, stems and spikes) covering all developmental stages. Images were collected by 11 institutions using a wide range of imaging setups. Two datasets are provided: i) a set of 1096 diverse images in which all organs were labelled at the pixel level, and (ii) a dataset of 52,078 images without annotations available for additional training. The labelled set was used to train segmentation models based on DeepLabV3Plus and Segformer. Our Segformer model performed slightly better than DeepLabV3Plus with a mIOU for leaves and spikes of ca. 90%. However, the precision for stems with 54% was rather lower. The major advantages over published models are: i) the exclusion of weeds from the wheat canopy, ii) the detection of all wheat features including necrotic and senescent tissues and its separation from crop residues. This facilitates further development in classifying healthy vs. unhealthy tissue to address the increasing need for accurate quantification of senescence and diseases in wheat canopies.

plant biology↗

bioRxiv2021

Plant detection and counting from high-resolution RGB images acquired from UAVs: comparison between deep-learning and handcrafted methods with application to maize, sugar beet, and sunflower crops

Progresses in agronomy rely on accurate measurement of the experimentations conducted to improve the yield component. Measurement of the plant density is required for a number of applications since it drives part of the crop fate. The standard manual measurements in the field could be efficiently replaced by high-throughput techniques based on high-spatial resolution images taken from UAVs. This study compares several automated detection of individual plants in the images from which the plant density can be estimated. It is based on a large dataset of high resolution Red/Green/Blue (RGB) images acquired from Unmanned Aerial Vehicules (UAVs) during several years and experiments over maize, sugar beet and sunflower crops at early stages. A total of 16247 plants have been labelled interactively on the images. Performances of handcrafted method (HC) were compared to those of deep learning (DL). The HC method consists in segmenting the image into green and background pixels, identifying rows, then objects corresponding to plants thanks to knowledge of the sowing pattern as prior information. The DL method is based on the Faster Region with Convolutional Neural Network (Faster RCNN) model trained over 2/3 of the images selected to represent a good balance between plant development stage and sessions. One model is trained for each crop. Results show that simple DL methods generally outperforms simple HC, particularly for maize and sunflower crops. A significant level of variability of plant detection performances is observed between the several experiments. This was explained by the variability of image acquisition conditions including illumination, plant development stage, background complexity and weed infestation. The image quality determines part of the performances for HC methods which makes the segmentation step more difficult. Performances of DL methods are limited mainly by the presence of weeds. A hybrid method (HY) was proposed to eliminate weeds between the rows using the rules developed for the HC method. HY improves slightly DL performances in the case of high weed infestation. When few images corresponding to the conditions of the testing dataset were complementing the training dataset for DL, a drastic increase of performances for all the crops is observed, with relative RMSE below 5% for the estimation of the plant density.

plant biology↗

bioRxiv2017

Leaf rolling in maize crops: from leaf scoring to canopy level measurements for phenotyping

Leaf rolling in maize crops is one of the main plant reactions to water stress that may be visually scored in the field. However, the leaf scoring did not reach the high-throughput desired by breeders for efficient phenotyping. This study investigates the relationship between leaf rolling score and the induced canopy structure changes that may be accessed by high-throughput remote sensing techniques.\n\nResults gathered over a field phenotyping platform run in 2015 and 2016 show that leaf starts to roll for the water stressed conditions around 9:00 and reaches its maximum around 15:00. Conversely, genotypes conducted under well watered conditions do not show any significant rolling during the same day. Leaf level rolling was very strongly correlated to canopy structure changes as described by the fraction of intercepted radiation fIPARWS derived from digital hemispherical photography. The changes in fIPARWS were stronly correlated (R2=0.86, n=50) to the leaf level rolling visual score. Further, a very good consistency of the genotype ranking of the fIPARWS changes during the day was found ({rho}=0.62). This study demonstrating the strong coordination between leaf level rolling and its impact on canopy structure changes poses the basis for new high-throughput remote sensing methods to quantify this water stress trait.\n\nHighlighThe diurnal dynamics of leaf rolling scored visually is strongly related to canopy structure changes that can be documented using Digital hemispherical photography. Consequences for high-throughput field phenotyping are discussed

plant biology↗