Biology subjects

Ruhter, J.

Publications and source records attributed to Ruhter, J..

3 recordsLinked to original sources

bioRxiv2026

ROOTQUANT: AUTOMATED ROOT TRAIT QUANTIFICATION FROMMINIRHIZOTRON IMAGES USING DEEP LEARNING

AO_SCPLOWBSTRACTC_SCPLOWQuantifying root traits such as root length (RL) and root surface area (RSA) from minirhizotron imagery is a valuable approach for overcoming the phenotyping bottleneck that limits understanding and improvement of crop productivity, resource use efficiency and resilience in field experiments. However, current approaches remain labor-intensive, and deep learning (DL) methods suffer from limited generalization ability. We present RootQuant, an end-to-end DL model that simultaneously predicts RL and RSA directly from minirhizotron images using only whole-image trait values as supervision, thereby eliminating the need for pixel-level annotations. The models generalization ability was evaluated across species and fine-tuning configurations. The practical applicability of the model was further assessed under field conditions by converting image-derived RL estimates into volumetric root length density (vRLD). Using 118,191 maize and soybean images collected between 2009 and 2020, RootQuant trained on both species achieved an R2 of 0.90 and an RMSE of 2.9 mm for RL, and an R2 of 0.88 and an RMSE of 4.2 mm2 for RSA. The same mixed-species model generalized strongly across species, yielding an 8% relative improvement in R2 and a 30% lower RMSE on maize compared with the same architecture trained on a single species and applied zero-shot. Image-derived RL predictions converted to vRLD showed the expected depth-dependent decline in vRLD, as was also found by coincident destructive quantification of roots washed out of soil cores. By providing a generalist backbone model trained on a large dataset from two major crop species, RootQuant enables high-throughput simultaneous estimation of two relevant root traits directly from raw imagery without task-specific fine-tuning, thereby accelerating in situ root system analysis and phenotyping applications.

plant biology↗

bioRxiv2025

Breaking the barrier of human-annotated training data for machine-learning-aided plant research using aerial imagery

Machine learning (ML) can accelerate biological research. However, the adoption of such tools to facilitate phenotyping based on sensor data has been limited by: (1) the need for a large amount of human-annotated training data for each context in which the tool is used; and (2) phenotypes varying across contexts defined in terms of genetics and environment. This is a major bottleneck because acquiring training data is generally costly and time-consuming. This study demonstrates how a ML approach can address these challenges by minimizing the amount of human supervision needed for tool building. A case study comparing ML approaches that examine images collected by an uncrewed aerial vehicle was performed to determine the presence of panicles (i.e., "heading") across thousands of field plots containing genetically diverse breeding populations of two Miscanthus species. Automated analysis of aerial imagery enabled the identification of heading approximately nine times faster than in-field visual inspection by humans. Leveraging an Efficiently Supervised Generative and Adversarial Network (ESGAN) learning strategy reduced the requirement for human-annotated data by one to two orders of magnitude compared to traditional, fully supervised learning approaches. The ESGAN model learned the salient features of the dataset by using thousands of unlabeled images to inform the discriminative ability of a classifier so that it required minimal human-labeled training data. This method can accelerate the phenotyping of heading date as a measure of flowering time in Miscanthus across diverse contexts (e.g., in multi-state trials) and opens avenues to promote the broad adoption of ML tools. One-sentence summaryMachine learning approach accelerates plant phenotyping by reducing the need for large amounts of human-annotated data, enabling faster and more efficient detection of a plant trait using aerial imagery The author responsible for distribution of materials integral to the findings presented in this article in accordance with the policy described in the Instructions for Authors (https://academic.oup.com/plphys/pages/General-Instructions) is Sebastian Varela.

bioinformatics↗

bioRxiv2021

Installation and imaging of thousands of minirhizotrons to phenotype root systems of field-grown plants

BackgroundRoots are vital to plant performance because they acquire resources from the soil and provide anchorage. However, it remains difficult to assess root system size and distribution because roots are inaccessible in the soil. Existing methods to phenotype entire root systems range from slow, often destructive, methods applied to relatively small numbers of plants in the field to rapid methods that can be applied to large numbers of plants in controlled environment conditions. Much has been learned recently by extensive sampling of the root crown portion of field-grown plants. But, information on large-scale genetic and environmental variation in the size and distribution of root systems in the field remains a key knowledge gap. Minirhizotrons are the only established, non-destructive technology that can address this need in a standard field trial. Prior experiments have used only modest numbers of minirhizotrons, which has limited testing to small numbers of genotypes or environmental conditions. This study addressed the need for methods to install and collect images from thousands of minirhizotrons and thereby help break the phenotyping bottleneck in the field. ResultsOver three growing seasons, methods were developed and refined to install and collect images from up to3038 minirhizotrons per experiment. Modifications were made to four tractors and hydraulic soil corers mounted to them. High quality installation was achieved at an average rate of up to 84.4 minirhizotron tubes per tractor per day. A set of four commercially available minirhizotron camera systems were each transported by wheelbarrow to allow collection of images of mature maize root systems at an average rate of up to 65.3 tubes per day per camera. This resulted in over 300,000 images being collected in as little as 11 days for a single experiment. ConclusionThe scale of minirhizotron installation was increased by two orders of magnitude by simultaneously using four tractor-mounted, hydraulic soil corers with modifications to ensure high quality, rapid operation. Image collection can be achieved at the corresponding scale using commercially available minirhizotron camera systems. Along with recent advances in image analysis, these advances will allow use of minirhizotrons at unprecedented scale to address key knowledge gaps regarding genetic and environmental effects on root system size and distribution in the field.

plant biology↗