Fast and Efficient Root Phenotyping via Pose Estimation

Image segmentation is commonly used to estimate the location and shape of plants and their external structures. Segmentation masks are then used to localize landmarks of interest and compute other geometric features that correspond to the plant's phenotype. Despite its prevalence, segmentation-based approaches are laborious (requiring extensive annotation to train) and error-prone (derived geometric features are sensitive to instance mask integrity). Here, we present a segmentation-free approach that leverages deep learning-based landmark detection and grouping, also known as pose estimation. We use a tool originally developed for animal motion capture called SLEAP (Social LEAP Estimates Animal Poses) to automate the detection of distinct morphological landmarks on plant roots. Using a gel cylinder imaging system across multiple species, we show that our approach can reliably and efficiently recover root system topology at high accuracy, few annotated samples, and faster speed than segmentation-based approaches. In order to make use of this landmark-based representation for root phenotyping, we developed a Python library (sleap-roots) for trait extraction directly comparable to existing segmentation-based analysis software. We show that pose-derived root traits are highly accurate and can be used for common downstream tasks including genotype classification and unsupervised trait mapping. Altogether, this work establishes the validity and advantages of pose estimation-based plant phenotyping. To facilitate adoption of this easy-to-use tool and to encourage further development, we make sleap-roots, all training data, models, and trait extraction code available at: https://github.com/talmolab/sleap-roots and https://osf.io/k7j9g/.

Fast and efficient root phenotyping via pose estimation

Image segmentation is commonly used to estimate the location and shape of plants and their external structures. Segmentation masks are then used to localize landmarks of interest and compute other geometric features that correspond to the plant's phenotype. Despite its prevalence, segmentation-based approaches are laborious (requiring extensive annotation to train), and error-prone (derived geometric features are sensitive to instance mask integrity). Here we present a segmentation-free approach which leverages deep learning-based landmark detection and grouping, also known as pose estimation. We use a tool originally developed for animal motion capture called SLEAP (Social LEAP Estimates Animal Poses) to automate the detection of distinct morphological landmarks on plant roots. Using a gel cylinder imaging system across multiple species, we show that our approach can reliably and efficiently recover root system topology at high accuracy, few annotated samples, and faster speed than segmentation-based approaches. In order to make use of this landmark-based representation for root phenotyping, we developed a Python library (sleap-roots) for trait extraction directly comparable to existing segmentation-based analysis software. We show that landmark-derived root traits are highly accurate and can be used for common downstream tasks including genotype classification and unsupervised trait mapping. Altogether, this work establishes the validity and advantages of pose estimation-based plant phenotyping. To facilitate adoption of this easy-to-use tool and to encourage further development, we make sleap-roots, all training data, models, and trait extraction code available at: https://github.com/talmolab/sleap-roots and https://osf.io/k7j9g/.

The root system architecture of wheat establishing in soil is associated with varying elongation rates of seminal roots: quantification using 4D magnetic resonance imaging

Seedling establishment is the first stage of crop productivity, and root phenotypes at seed emergence are critical to a successful start of shoot growth as well as for water and nutrient uptake. In this study, we investigate seedling establishment in winter wheat utilizing a newly developed workflow based on magnetic resonance imaging (MRI). Using the eight parents of the MAGIC (multi-parent advanced generation inter-cross) population we analysed the 4D root architecture of 288 individual seedlings grown in natural soils with plant neighbors over 3 d of development. Time of root and shoot emergence, total length, angle, and depth of the axile roots varied significantly among these genotypes. The temporal data resolved rates of elongation of primary roots and first and second seminal root pairs. Genotypes with slowly elongating primary roots had rapidly elongating first and second seminal root pairs and vice versa, resulting in variation in root system architecture mediated not only by root angle but also by initiation and relative elongation of axile roots. We demonstrated that our novel MRI workflow with a unique planting design and automated measurements allowed medium throughput phenotyping of wheat roots in 4D and could give new insights into regulation of root system architecture.

How does the VPD response of isohydric and anisohydric plants depend on leaf surface particles?

Atmospheric vapour pressure deficit (VPD) is the driving force for plant transpiration. Plants have different strategies to respond to this 'atmospheric drought'. Deposited aerosols on leaf surfaces can interact with plant water relations and may influence VPD response. We studied transpiration and water use efficiency of pine, beech and sunflower by measuring sap flow, gas exchange and carbon isotopes, thereby addressing different time scales of plant/atmosphere interaction. Plants were grown (i) outdoors under rainfall exclusion (OD) and in ventilated greenhouses with (ii) ambient air (AA) or (iii) filtered air (FA), the latter containing <1% ambient aerosol concentrations. In addition, some AA plants were sprayed once with 25 mM salt solution of (NH4 )2 SO4 or NaNO3 . Carbon isotope values (δ(13) C) became more negative in the presence of more particles; more negative for AA compared to FA sunflower and more negative for OD Scots pine compared to other growth environments. FA beech had less negative δ(13) C than AA, OD and NaNO3 -treated beech. Anisohydric beech showed linearly increasing sap flow with increasing VPD. The slopes doubled for (NH4 )2 SO4 - and tripled for NaNO3 -sprayed beech compared to control seedlings, indicating decreased ability to resist atmospheric demand. In contrast, isohydric pine showed constant transpiration rates with increasing VPD, independent of growth environment and spray, likely caused by decreasing gs with increasing VPD. Generally, NaNO3 spray had stronger effects on water relations than (NH4 )2 SO4 spray. The results strongly support the role of leaf surface particles as an environmental factor affecting plant water use. Hygroscopic and chaotropic properties of leaf surface particles determine their ability to form wicks across stomata. Such wicks enhance unproductive water loss of anisohydric plant species and decrease CO2 uptake of isohydric plants. They become more relevant with increasing number of fine particles and increasing VPD and are thus related to air pollution and climate change. Wicks cause a deviation from the analogy between CO2 and water pathways through stomata, bringing some principal assumptions of gas exchange theory into question.