Background: Root system architecture (RSA) traits are of interest for breeding selection; however, measurement of these traits is difficult, resource intensive, and results in large variability. The advent of computer vision and machine learning (ML) enabled trait extraction and measurement has renewed interest in utilizing RSA traits for genetic enhancement to develop more robust and resilient crop cultivars. We developed a mobile, low-cost, and high-resolution root phenotyping system composed of an imaging platform with computer vision and ML based segmentation approach to establish a seamless end-to-end pipeline - from obtaining large quantities of root samples through image based trait processing and analysis.Results: This high throughput phenotyping system, which has the capacity to handle hundreds to thousands of plants, integrates time series image capture coupled with automated image processing that uses optical character recognition (OCR) to identify seedlings via barcode, followed by robust segmentation integrating convolutional auto-encoder (CAE) method prior to feature extraction. The pipeline includes an updated and customized version of the Automatic Root Imaging Analysis (ARIA) root phenotyping software. Using this system, we studied diverse soybean accessions from a wide geographical distribution and report genetic variability for RSA traits, including root shape, length, number, mass, and angle.Conclusions: This system provides a high-throughput, cost effective, non-destructive methodology that delivers biologically relevant time-series data on root growth and development for phenomics, genomics, and plant breeding applications. This phenotyping platform is designed to quantify root traits and rank genotypes in a common environment thereby serving as a selection tool for use in plant breeding. Root phenotyping platforms and image based phenotyping are essential to mirror the current focus on shoot phenotyping in breeding efforts.
Nodules form on plant roots through the symbiotic relationship between soybean (Glycine max L. Merr.) roots and bacteria (Bradyrhizobium japonicum) and are an important structure where atmospheric nitrogen (N2) is fixed into bioavailable ammonia (NH3) for plant growth and development. Nodule quantification on soybean roots is a laborious and tedious task; therefore, assessment is frequently done on a numerical scale that allows for rapid phenotyping, but is less informative and suffers from subjectivity. We report the Soybean Nodule Acquisition Pipeline (SNAP) for nodule quantification that combines RetinaNet and UNet deep learning architectures for object (i.e., nodule) detection and segmentation. SNAP was built using data from 691 unique roots from diverse soybean genotypes, vegetative growth stages, and field locations and has a good model fit (). SNAP reduces the human labor and inconsistencies of counting nodules, while acquiring quantifiable traits related to nodule growth, location, and distribution on roots. The ability of SNAP to phenotype nodules on soybean roots at a higher throughput enables researchers to assess the genetic and environmental factors, and their interactions on nodulation from an early development stage. The application of SNAP in research and breeding pipelines may lead to more nitrogen use efficiency for soybean and other legume species cultivars, as well as enhanced insight into the plant-Bradyrhizobium relationship.
Insect pests significantly impact global agricultural productivity and crop quality. Effective integrated pest management strategies require the identification of insects, including beneficial and harmful insects. Automated identification of insects under real-world conditions presents several challenges, including the need to handle intraspecies dissimilarity and interspecies similarity, life-cycle stages, camouflage, diverse imaging conditions, and variability in insect orientation. An end-to-end approach for training deep-learning models, InsectNet, is proposed to address these challenges. Our approach has the following key features: (i) uses a large dataset of insect images collected through citizen science along with label-free self-supervised learning to train a global model, (ii) fine-tuning this global model using smaller, expert-verified regional datasets to create a local insect identification model, (iii) which provides high prediction accuracy even for species with small sample sizes, (iv) is designed to enhance model trustworthiness, and (v) democratizes access through streamlined machine learning operations. This global-to-local model strategy offers a more scalable and economically viable solution for implementing advanced insect identification systems across diverse agricultural ecosystems. We report accurate identification (>96% accuracy) of numerous agriculturally and ecologically relevant insect species, including pollinators, parasitoids, predators, and harmful insects. InsectNet provides fine-grained insect species identification, works effectively in challenging backgrounds, and avoids making predictions when uncertain, increasing its utility and trustworthiness. The model and associated workflows are available through a web-based portal accessible through a computer or mobile device. We envision InsectNet to complement existing approaches, and be part of a growing suite of AI technologies for addressing agricultural challenges.
The accuracy of trait measurements greatly affects the quality of genetic analyses. During automated phenotyping, trait measurement errors, i.e. differences between automatically extracted trait values and ground truth, are often treated as random effects that can be controlled by increasing population sizes and/or replication number. In contrast, there is some evidence that trait measurement errors may be partially under genetic control. Consistent with this hypothesis, we observed substantial nonrandom, genetic contributions to trait measurement errors for five maize (Zea mays) tassel traits collected using an image-based phenotyping platform. The phenotyping accuracy varied according to whether a tassel exhibited “open” versus. “closed” branching architecture, which is itself under genetic control. Trait-associated SNPs (TASs) identified via genome-wide association studies (GWASs) conducted on five tassel traits that had been phenotyped both manually (i.e. ground truth) and via feature extraction from images exhibit little overlap. Furthermore, identification of TASs from GWASs conducted on the differences between the two values indicated that a fraction of measurement error is under genetic control. Similar results were obtained in a sorghum (Sorghum bicolor) plant height dataset, demonstrating that trait measurement error is genetically determined in multiple species and traits. Trait measurement bias cannot be controlled by increasing population size and/or replication number.
Societal Impact Statement: Maize plays a key role in agricultural profitability and food security on six continents. Successful efforts to breed higher‐yielding maize varieties depend on replicated yield trials in many environments. Capturing in‐season data can help improve and accelerate the development of regionally adapted hybrids, but collecting these data can be impractical in many locations. We demonstrate that satellite remote sensing could play a similar role in crop performance assessment as unmanned aerial vehicles (UAVs) but with far lower labor costs and the greatest ease of collection at remote field sites. This dataset and benchmarks have the potential to enable predictive models that could guide farmers and crop breeders in decision‐making.Summary: Accurate early yield estimates at fields and plots offer potential benefits to farmers in optimizing their agronomic practices and breeders in screening thousands of varieties contributing to improving agriculture and food production systems. Effective approaches to track plant growth and predict yield require large datasets of remote sensing and ground truth data collected across multiple environments. Low‐altitude drone flights are increasingly being used to collect data from field evaluations of new crop varieties, while satellite imagery is being explored to track yield and management practices at regional scales. Satellite platforms exhibit logistical and technical advantages in scalability and accessibility and could facilitate plot‐level predictions, especially with steadily improving spatial resolution. However, plot‐level, high‐resolution satellite images capturing differences in genotypes from multiple environments with ground truth measurements are not publicly available. Here, we generated, described, and evaluated over 20,000 plot‐level images of over 80 hybrid maize varieties grown across the US corn belt under various management practices collected from (near simultaneous) satellite and drone (synonym UAVs, UASs) flights integrated with ground truth yield measurement. Of the six baseline models examined, models employing data collected from satellite images often matched the performance of models employing drone images for both within and cross‐environment yield prediction.