Outdoor Plant Segmentation With Deep Learning for High-Throughput Field Phenotyping on a Diverse Wheat Dataset

Robust and automated segmentation of leaves and other backgrounds is a core prerequisite of most approaches in high-throughput field phenotyping. So far, the possibilities of deep learning approaches for this purpose have not been explored adequately, partly due to a lack of publicly available, appropriate datasets. This study presents a workflow based on DeepLab v3+ and on a diverse annotated dataset of 190 RGB (350 x 350 pixels) images. Images of winter wheat plants of 76 different genotypes and developmental stages have been acquired throughout multiple years at high resolution in outdoor conditions using nadir view, encompassing a wide range of imaging conditions. Inconsistencies of human annotators in complex images have been quantified, and metadata information of camera settings has been included. The proposed approach achieves an intersection over union (IoU) of 0.77 and 0.90 for plants and soil, respectively. This outperforms the benchmarked machine learning methods which use Support Vector Classifier and/or Random Forrest. The results show that a small but carefully chosen and annotated set of images can provide a good basis for a powerful segmentation pipeline. Compared to earlier methods based on machine learning, the proposed method achieves better performance on the selected dataset in spite of using a deep learning approach with limited data. Increasing the amount of publicly available data with high human agreement on annotations and further development of deep neural network architectures will provide high potential for robust field-based plant segmentation in the near future. This, in turn, will be a cornerstone of data-driven improvement in crop breeding and agricultural practices of global benefit.

High-throughput phenotyping for drought tolerance in rice

Most lowland rice in West Africa depends mainly on rainfall for water supply. Drought is consequently one of the major constraints on rice production, drastically affecting both plant growth and development. The objective of this work was to study the impact of water deficit both on canopy temperature and on chlorophyll fluorescence level, used as indicators of transpiration and photosynthetic activity. Measurements using infrared thermography and fluorimetry were taken on both 17 lines resulting from the cross IR64 X B6144F-MR-6-0-0 and their two parents plus one tolerant (APO) controls. These 20 lines were phenotyped after applying a drought constraint in a controlled laboratory environment in Montpellier (France) in 2013 and - 2014 and in field in the lowlands of Banfora and Farako-ba (INERA Burkina Faso) in 2014. Results showed that the drought stress sustained by the plants increased canopy temperature in all lines, entailing differential disturbance of the photosynthetic process, markedly depressed in susceptible lines. A classification of the lines with respect to their sensitivity to stress could be established by using the Drought Factor Index (DFI), and Crop Water Stress Index (CWSI) as was established a correlation between the phenotyping methods by infrared thermography and fluorimetry. This article propose an efficient application of combined imaging as a rapid and accurate phenotyping tool for crop yield improvement, in particular by monitoring the efficiency of plant responses to the fluctuating of environmental conditions. This study proved the efficiency of the method combining IR thermographie and fluorimetry as a field phenotyping tools for drought resistance.

Potential Phenotyping Methodologies to Assess Inter- and Intravarietal Variability and to Select Grapevine Genotypes Tolerant to Abiotic Stress

Plant phenotyping is an emerging science that combines multiple methodologies and protocols to measure plant traits (e.g., growth, morphology, architecture, function, and composition) at multiple scales of organization. Manual phenotyping remains as a major bottleneck to the advance of plant and crop breeding. Such constraint fostered the development of high throughput plant phenotyping (HTPP), which is largely based on imaging approaches and automatized data retrieval and processing. Field phenotyping still poses major challenges and the progress of HTPP for field conditions can be relevant to support selection and breeding of grapevine. The aim of this review is to discuss potential and current methods to improve field phenotyping of grapevine to support characterization of inter- and intravarietal diversity. Vitis vinifera has a large genetic diversity that needs characterization, and the availability of methods to support selection of plant material (polyclonal or clonal) able to withstand abiotic stress is paramount. Besides being time consuming, complex and expensive, field experiments are also affected by heterogeneous and uncontrolled climate and soil conditions, mostly due to the large areas of the trials and to the high number of traits to be observed in a number of individuals ranging from hundreds to thousands. Therefore, adequate field experimental design and data gathering methodologies are crucial to obtain reliable data. Some of the major challenges posed to grapevine selection programs for tolerance to water and heat stress are described herein. Useful traits for selection and related field phenotyping methodologies are described and their adequacy for large scale screening is discussed.

Application of Genomics Approaches for the Improvement in Ascochyta Blight Resistance in Chickpea

Advancements in high-throughput genotyping and sequencing technologies are enabling the development of a vast range of genomic tools and resources for a new revolution in plant breeding. Several genotyping-by-sequencing (GBS) methods including capture-based, genome complexity reduction and sequencing of cDNA (GBS-t) are available for application in trait dissection, association mapping, and genomic selection (GS) in crop plants. The aims of this study were to identify genomic regions conferring resistance to Ascochyta blight (AB) introgressed from the wild Cicer echinospernum into the domesticated C. arietinum, through a conventional recombinant inbred population genotyped using a variety of GBS methods. Evaluation of GBS methods revealed that capture-based approaches are robust and reproducible while GBS-t is rapid and flexible. A genetic linkage map consisting of 5886 polymorphic loci spanning 717.26 cM was generated. Using field phenotyping data from two years, a single genomic region on LG4 was identified with quantitative trait loci (QTL) mapping. Both GBS methods reported in this study are well suited for applications in genomics assisted plant breeding. Linked markers for AB resistance, identified in the current study, provide an important resource for the deployment into chickpea breeding programs for marker-assisted selection (MAS).