RootPainter: deep learning segmentation of biological images with corrective annotation

Convolutional neural networks (CNNs) are a powerful tool for plant image analysis, but challenges remain in making them more accessible to researchers without a machine-learning background. We present RootPainter, an open-source graphical user interface based software tool for the rapid training of deep neural networks for use in biological image analysis. We evaluate RootPainter by training models for root length extraction from chicory (Cichorium intybus L.) roots in soil, biopore counting, and root nodule counting. We also compare dense annotations with corrective ones that are added during the training process based on the weaknesses of the current model. Five out of six times the models trained using RootPainter with corrective annotations created within 2 h produced measurements strongly correlating with manual measurements. Model accuracy had a significant correlation with annotation duration, indicating further improvements could be obtained with extended annotation. Our results show that a deep-learning model can be trained to a high accuracy for the three respective datasets of varying target objects, background, and image quality with < 2 h of annotation time. They indicate that, when using RootPainter, for many datasets it is possible to annotate, train, and complete data processing within 1 d.

Root and xylem anatomy varies with root length, root order, soil depth and environment in intermediate wheatgrass (Kernza®) and alfalfa

BACKGROUND AND AIMS

Deep roots (i.e. &gt;1 m depth) are important for crops to access water when the topsoil is dry. Root anatomy and hydraulic conductance play important roles in the uptake of soil water, particularly water located deep in the soil. We investigated whether root and xylem anatomy vary as a function of root type, order and length, or with soil depth in roots of two deep-rooted perennial crops: intermediate wheatgrass [Thinopyrum intermedium (Kernza®)] and alfalfa (Medicago sativa). We linked the expression of these anatomical traits to the plants' capacity to take up water from deep soil layers.

METHODS

Using laser ablation tomography, we compared the roots of the two crops for cortical area, number and size of metaxylem vessels, and their estimated root axial hydraulic conductance (ERAHCe). The deepest roots investigated were located at soil depths of 2.25 and at 3.5 m in the field and in rhizoboxes, respectively. Anatomical differences were characterized along 1-m-long individual roots, among root types and orders, as well as between environmental conditions.

KEY RESULTS

For both crops, a decrease in the number and diameter, or both, of metaxylem vessels along individual root segments and with soil depth in the field resulted in a decrease in ERAHCe. Alfalfa, with a greater number of metaxylem vessels per root throughout the soil profile and, on average, a 4-fold greater ERAHCe, took up more water from the deep soil layers than intermediate wheatgrass. Root anatomical traits were significantly different across root types, classes and growth conditions.

CONCLUSIONS

Root anatomical traits are important tools for the selection of crops with enhanced exploitation of deep soil water. The development and breeding of perennial crops for improved subsoil exploitation will be aided by greater understanding of root phenotypes linked to deep root growth and activity.

Dynamics of Deep Water and N Uptake of Oilseed Rape (Brassica napus L.) Under Varied N and Water Supply

Enhanced nitrogen (N) and water uptake from deep soil layers may increase resource use efficiency while maintaining yield under stressed conditions. Winter oilseed rape (Brassica napus L.) can develop deep roots and access deep-stored resources such as N and water to sustain its growth and productivity. Less is known of the performance of deep roots under varying water and N availability. In this study, we aimed to evaluate the effects of reduced N and water supply on deep N and water uptake for oilseed rape. Oilseed rape plants grown in outdoor rhizotrons were supplied with 240 and 80 kg N ha-1, respectively, in 2019 whereas a well-watered and a water-deficit treatment were established in 2020. To track deep water and N uptake, a mixture of 2H2O and Ca(15NO3)2 was injected into the soil column at 0.5- and 1.7-m depths. δ2H in transpiration water and δ15N in leaves were measured after injection. δ15N values in biomass samples were also measured. Differences in N or water supply had less effect on root growth. The low N treatment reduced water uptake throughout the soil profile and altered water uptake distribution. The low N supply doubled the 15N uptake efficiency at both 0.5 and 1.7 m. Similarly, water deficit in the upper soil layers led to compensatory deep water uptake. Our findings highlight the increasing importance of deep roots for water uptake, which is essential for maintaining an adequate water supply in the late growing stage. Our results further indicate the benefit of reducing N supply for mitigating N leaching and altering water uptake from deep soil layers, yet at a potential cost of biomass reduction.

Back to our roots: exploring the role of root morphology as a mediator of beneficial plant-microbe interactions

Plant breeding for belowground traits that have a positive impact on the rhizosphere microbiome is a promising strategy to sustainably improve crop yields. Root architecture and morphology are understudied plant breeding targets despite their potential to significantly shape microbial community structure and function in the rhizosphere. In this review, we explore the relationship between various root architectural and morphological traits and rhizosphere interactions, focusing on the potential of root diameter to impact the rhizosphere microbiome structure and function while discussing the potential biological and ecological mechanisms underpinning this process. In addition, we propose three future research avenues to drive this research area in an effort to unravel the effect of belowground traits on rhizosphere microbiology. This knowledge will pave the way for new plant breeding strategies that can be exploited for sustainable and high‐yielding crop cultivars.

Digging Deeper for Agricultural Resources, the Value of Deep Rooting

In the quest for sustainable intensification of crop production, we discuss the option of extending the root depth of crops to increase the volume of soil exploited by their root systems. We discuss the evidence that deeper rooting can be obtained by appropriate choice of crop species, by plant breeding, or crop management and its potential contributions to production and sustainable development goals. Many studies highlight the potentials of deeper rooting, but we evaluate its contributions to sustainable intensification of crop production, the causes of the limited research into deep rooting of crops, and the research priorities to fill the knowledge gaps.

Core-labelling technique (CLT): a novel combination of the ingrowth-core method and tracer technique for deep root study

BACKGROUND

Ingrowth-core method is a useful tool to determine fine root growth of standing crops by inserting root-free soil in mesh-bags for certain period of time. However, the root density observed by the method does not directly explain the nutrient uptake potential of crop plants as it varies over soil depth and incubation time. We have inserted an access-tube up to 4.2 m of soil depth with openings directly under crop plants, through which ingrowth-cores containing labelled soil with nutrient tracers were installed, called core-labelling technique (CLT). The main advantage of CLT would be its capacity to determine both root density and root activity from the same crop plants in deep soil layers. We tested the validity of the new method using a model crop species, alfalfa (Medicago sativa) against three depth-levels (1.0, 2.5 and 4.2 m), three sampling spots with varying distance (0-0.36, 0.36-0.72 and > 5 m from core-labelled spot), two sampling times (week 4 and 8), and two plant parts (young and old leaves) under two field experiments (spring and autumn).

RESULTS

Using CLT, we were able to observe both deep root growth and root activity up to 4.2 m of soil depth. Tracer concentrations revealed that there was no sign of tracer-leakage to adjacent areas which is considered to be advantageous over the generic tracer-injection. Root activity increased with longer incubation period and tracer concentrations were higher in younger leaves only for anionic tracers.

CONCLUSIONS

Our results indicate that CLT can lead to a comprehensive deep root study aiming at measuring both deep root growth and root activity from the same plants. Once produced and installed, the access-tubes and ingrowth-cores can be used for a long-term period, which reduces the workload and cost for the research. Therefore, CLT has a wide range of potential applications to the research involving roots in deep soil layers, which requires further confirmation by future experiments.

Structural changes of plant residues during decomposition in a compost environment

The degradation of plant material during composting was investigated qualitatively by scanning electron microscopy (SEM) and quantitatively by chemical methods. Decomposition of Miscanthus (Miscanthus oogiformis L.), hemp (Cannabis sativa L.) and wheat (Triticum aestivum L.) straw was observed by placing litterbags containing these materials in compost piles. Hemp and Miscanthus straw were more stable than wheat straw, but the two materials differed in the way they were degraded despite similar chemical compositions. Hemp straw was broken down in more flexible structures compared to the rigid breakdown of Miscanthus straw. It was concluded that the anatomical arrangement of the tissue is just as important as the content of recalcitrant compounds in determining decomposition rate. Thus, when using composted plant materials as growing medium, the choice of material must depend not only on nutritional quality but also on structural quality. This study indicated that hemp material might be a good structural component in a compost to be used as a growing medium.

Delayed nutrient application affects mineralisation rate during composting of plant residues

The hypothesis that delayed addition of nutrient rich material to compost would influence the mineralisation pattern was investigated by studying N turnover in compost based on wheat straw and clover-grass hay. After 712 weeks of composting almost twice as much N was mineralised when the addition of some of the N-rich clover-grass hay was postponed, suggesting that this influenced the microbial succession. The delayed addition resulted in a second temperature peak and a decline in the pH. Despite the altered conditions no significant effect was observed on the weight loss or loss of C and N. In conclusion, compost processes can in a simple way be affected by delayed substrate application leading to a higher nutrient availability without altering other parameters significantly.