A Deep Learning-Based Phenotypic Analysis of Rice Root Distribution from Field Images

Review of applications of artificial intelligence (AI) methods in crop research

Sophisticated and modern crop improvement techniques can bridge the gap for feeding the ever-increasing population. Artificial intelligence (AI) refers to the simulation of human intelligence in machines, which refers to the application of computational algorithms, machine learning (ML) and deep learning (DL) techniques. This is aimed to generalise patterns and relationships from historical data, employing various mathematical optimisation techniques thus making prediction models for facilitating selection of superior genotypes. These techniques are less resource intensive and can solve the problem based on the analysis of large-scale phenotypic datasets. ML for genomic selection (GS) uses high-throughput genotyping technologies to gather genetic information on a large number of markers across the genome. The prediction of GS models is based on the mathematical relation between genotypic and phenotypic data from the training population. ML techniques have emerged as powerful tools for genome editing through analysing large-scale genomic data and facilitating the development of accurate prediction models. Precise phenotyping is a prerequisite to advance crop breeding for solving agricultural production-related issues. ML algorithms can solve this problem through generating predictive models, based on the analysis of large-scale phenotypic datasets. DL models also have the potential reliability of precise phenotyping. This review provides a comprehensive overview on various ML and DL models, their applications, potential to enhance the efficiency, specificity and safety towards advanced crop improvement protocols such as genomic selection, genome editing, along with phenotypic prediction to promote accelerated breeding.

Deep learning-based association analysis of root image data and cucumber yield

The root system is important for the absorption of water and nutrients by plants. Cultivating and selecting a root system architecture (RSA) with good adaptability and ultrahigh productivity have become the primary goals of agricultural improvement. Exploring the correlation between the RSA and crop yield is important for cultivating crop varieties with high-stress resistance and productivity. In this study, 277 cucumber varieties were collected for root system image analysis and yield using germination plates and greenhouse cultivation. Deep learning tools were used to train ResNet50 and U-Net models for image classification and segmentation of seedlings and to perform quality inspection and productivity prediction of cucumber seedling root system images. The results showed that U-Net can automatically extract cucumber root systems with high quality (F1_score ≥ 0.95), and the trained ResNet50 can predict cucumber yield grade through seedling root system image, with the highest F1_score reaching 0.86 using 10-day-old seedlings. The root angle had the strongest correlation with yield, and the shallow- and steep-angle frequencies had significant positive and negative correlations with yield, respectively. RSA and nutrient absorption jointly affected the production capacity of cucumber plants. The germination plate planting method and automated root system segmentation model used in this study are convenient for high-throughput phenotypic (HTP) research on root systems. Moreover, using seedling root system images to predict yield grade provides a new method for rapidly breeding high-yield RSA in crops such as cucumbers.

Non-destructive real-time monitoring of underground root development with distributed fiber optic sensing

Crop genetic engineering for better root systems can offer practical solutions for food security and carbon sequestration; however, soil layers prevent the direct visualization of plant roots, thus posing a challenge to effective phenotyping. Here, we demonstrate an original device with a distributed fiber-optic sensor for fully automated, real-time monitoring of underground root development. We show that spatially encoding an optical fiber with a flexible and durable polymer film in a spiral pattern can significantly enhance sensor detection. After signal processing, the resulting device can detect the penetration of a submillimeter-diameter object in the soil, indicating more than a magnitude higher spatiotemporal resolution than previously reported with underground monitoring techniques. Additionally, we also developed computational models to visualize the roots of tuber crops and monocotyledons and then applied them to radish and rice to compare the results with those of X-ray computed tomography. The device's groundbreaking sensitivity and spatiotemporal resolution enable seamless and laborless phenotyping of root systems that are otherwise invisible underground.

TrichomeYOLO: A Neural Network for Automatic Maize Trichome Counting

Plant trichomes are epidermal structures with a wide variety of functions in plant development and stress responses. Although the functional importance of trichomes has been realized, the tedious and time-consuming manual phenotyping process greatly limits the research progress of trichome gene cloning. Currently, there are no fully automated methods for identifying maize trichomes. We introduce TrichomeYOLO, an automated trichome counting and measuring method that uses a deep convolutional neural network, to identify the density and length of maize trichomes from scanning electron microscopy images. Our network achieved 92.1% identification accuracy on scanning electron microscopy micrographs of maize leaves, which is much better performed than the other 5 currently mainstream object detection models, Faster R-CNN, YOLOv3, YOLOv5, DETR, and Cascade R-CNN. We applied TrichomeYOLO to investigate trichome variations in a natural population of maize and achieved robust trichome identification. Our method and the pretrained model are open access in Github (https://github.com/yaober/trichomecounter). We believe TrichomeYOLO will help make efficient trichome identification and help facilitate researches on maize trichomes.

Soybean Seedling Root Segmentation Using Improved U-Net Network

Soybean seedling root morphology is important to genetic breeding. Root segmentation is a key technique for identifying root morphological characteristics. This paper proposed a semantic segmentation model of soybean seedling root images based on an improved U-Net network to address the problems of the over-segmentation phenomenon, unsmooth root edges and root disconnection, which are easily caused by background interference such as water stains and noise, as well as inconspicuous contrast in soybean seedling images. Soybean seedling root images in the hydroponic environment were collected for annotation and augmentation. A double attention mechanism was introduced in the downsampling process, and an Attention Gate mechanism was added in the skip connection part to enhance the weight of the root region and suppress the interference of background and noise. Then, the model prediction process was visually interpreted using feature maps and class activation mapping maps. The remaining background noise was removed by connected component analysis. The experimental results showed that the Accuracy, Precision, Recall, F1-Score and Intersection over Union of the model were 0.9962, 0.9883, 0.9794, 0.9837 and 0.9683, respectively. The processing time of an individual image was 0.153 s. A segmentation experiment on soybean root images was performed in the soil-culturing environment. The results showed that this proposed model could extract more complete detail information and had strong generalization ability. It can achieve accurate root segmentation in soybean seedlings and provide a theoretical basis and technical support for the quantitative evaluation of the root morphological characteristics in soybean seedlings.

Phenotyping for waterlogging tolerance in crops: current trends and future prospects

Yield losses to waterlogging are expected to become an increasingly costly and frequent issue in some regions of the world. Despite the extensive work that has been carried out examining the molecular and physiological responses to waterlogging, phenotyping for waterlogging tolerance has proven difficult. This difficulty is largely due to the high variability of waterlogging conditions such as duration, temperature, soil type, and growth stage of the crop. In this review, we highlight use of phenotyping to assess and improve waterlogging tolerance in temperate crop species. We start by outlining the experimental methods that have been utilized to impose waterlogging stress, ranging from highly controlled conditions of hydroponic systems to large-scale screenings in the field. We also describe the phenotyping traits used to assess tolerance ranging from survival rates and visual scoring to precise photosynthetic measurements. Finally, we present an overview of the challenges faced in attempting to improve waterlogging tolerance, the trade-offs associated with phenotyping in controlled conditions, limitations of classic phenotyping methods, and future trends using plant-imaging methods. If effectively utilized to increase crop resilience to changing climates, crop phenotyping has a major role to play in global food security.

Objective Phenotyping of Root System Architecture Using Image Augmentation and Machine Learning in Alfalfa (Medicago sativa L.)

Active breeding programs specifically for root system architecture (RSA) phenotypes remain rare; however, breeding for branch and taproot types in the perennial crop alfalfa is ongoing. Phenotyping in this and other crops for active RSA breeding has mostly used visual scoring of specific traits or subjective classification into different root types. While image-based methods have been developed, translation to applied breeding is limited. This research is aimed at developing and comparing image-based RSA phenotyping methods using machine and deep learning algorithms for objective classification of 617 root images from mature alfalfa plants collected from the field to support the ongoing breeding efforts. Our results show that unsupervised machine learning tends to incorrectly classify roots into a normal distribution with most lines predicted as the intermediate root type. Encouragingly, random forest and TensorFlow-based neural networks can classify the root types into branch-type, taproot-type, and an intermediate taproot-branch type with 86% accuracy. With image augmentation, the prediction accuracy was improved to 97%. Coupling the predicted root type with its prediction probability will give breeders a confidence level for better decisions to advance the best and exclude the worst lines from their breeding program. This machine and deep learning approach enables accurate classification of the RSA phenotypes for genomic breeding of climate-resilient alfalfa.

Root system architecture in cereals: progress, challenges and perspective

Roots are essential multifunctional plant organs involved in water and nutrient uptake, metabolite storage, anchorage, mechanical support, and interaction with the soil environment. Understanding of this 'hidden half' provides potential for manipulation of root system architecture (RSA) traits to optimize resource use efficiency and grain yield in cereal crops. Unfortunately, root traits are highly neglected in breeding due to the challenges of phenotyping, but could have large rewards if the variability in RSA traits can be fully exploited. Until now, a plethora of genes have been characterized in detail for their potential role in improving RSA. The use of forward genetics approaches to find sequence variations in genes underpinning desirable RSA would be highly beneficial. Advances in computer vision applications have allowed image-based approaches for high-throughput phenotyping of RSA traits that can be used by any laboratory worldwide to make progress in understanding root function and dissection of the genetics. At the same time, the frontiers of root measurement include non-invasive methods like X-ray computer tomography and magnetic resonance imaging that facilitate new types of temporal studies. Root physiology and ecology are further supported by spatiotemporal root simulation modeling. The discovery of component traits providing improved resilience and yield advantage in target environments is a key necessity for mainstreaming root-based cereal breeding. The integrated use of pan-genome resources, now available in most cereals, coupled with new in-field phenotyping platforms has the potential for precise selection of superior genotypes with improved RSA.

Improving the efficiency of plant root system phenotyping through digitization and automation

Root system architecture (RSA) determines unevenly distributed water and nutrient availability in soil. Genetic improvement of RSA, therefore, is related to crop production. However, RSA phenotyping has been carried out less frequently than above-ground phenotyping because measuring roots in the soil is difficult and labor intensive. Recent advancements have led to the digitalization of plant measurements; this digital phenotyping has been widely used for measurements of both above-ground and RSA traits. Digital phenotyping for RSA is slower and more difficult than for above-ground traits because the roots are hidden underground. In this review, we summarized recent trends in digital phenotyping for RSA traits. We classified the sample types into three categories: soil block containing roots, section of soil block, and root sample. Examples of the use of digital phenotyping are presented for each category. We also discussed room for improvement in digital phenotyping in each category.

Digging roots is easier with AI

The scale of root quantification in research is often limited by the time required for sampling, measurement, and processing samples. Recent developments in convolutional neural networks (CNNs) have made faster and more accurate plant image analysis possible, which may significantly reduce the time required for root measurement, but challenges remain in making these methods accessible to researchers without an in-depth knowledge of machine learning. We analyzed root images acquired from three destructive root samplings using the RootPainter CNN software that features an interface for corrective annotation for easier use. Root scans with and without non-root debris were used to test if training a model (i.e. learning from labeled examples) can effectively exclude the debris by comparing the end results with measurements from clean images. Root images acquired from soil profile walls and the cross-section of soil cores were also used for training, and the derived measurements were compared with manual measurements. After 200 min of training on each dataset, significant relationships between manual measurements and RootPainter-derived data were noted for monolith (R2=0.99), profile wall (R2=0.76), and core-break (R2=0.57). The rooting density derived from images with debris was not significantly different from that derived from clean images after processing with RootPainter. Rooting density was also successfully calculated from both profile wall and soil core images, and in each case the gradient of root density with depth was not significantly different from manual counts. Differences in root-length density (RLD) between crops with contrasting root systems were captured using automatic segmentation at soil profiles with high RLD (1-5 cm cm-3) as well with low RLD (0.1-0.3 cm cm-3). Our results demonstrate that the proposed approach using CNN can lead to substantial reductions in root sample processing workloads, increasing the potential scale of future root investigations.

Root phenotyping: important and minimum information required for root modeling in crop plants

As plants cannot relocate, they require effective root systems for water and nutrient uptake. Root development plasticity enables plants to adapt to different environmental conditions. Research on improvements in crop root systems is limited in comparison with that in shoots as the former are difficult to image. Breeding more effective root systems is proposed as the "second green revolution". There are several recent publications on root system architecture (RSA), but the methods used to analyze the RSA have not been standardized. Here, we introduce traditional and current root-imaging methods and discuss root structure phenotyping. Some important root structures have not been standardized as roots are easily affected by rhizosphere conditions and exhibit greater plasticity than shoots; moreover, root morphology significantly varies even in the same genotype. For these reasons, it is difficult to define the ideal root systems for breeding. In this review, we introduce several types of software to analyze roots and identify important root parameters by modeling to simplify the root system characterization. These parameters can be extracted from photographs captured in the field. This modeling approach is applicable to various legacy root data stored in old or unpublished formats. Standardization of RSA data could help estimate root ideotypes.

Root phenotyping: important and minimum information required for root modeling in crop plants

As plants cannot relocate, they require effective root systems for water and nutrient uptake. Root development plasticity enables plants to adapt to different environmental conditions. Research on improvements in crop root systems is limited in comparison with that in shoots as the former are difficult to image. Breeding more effective root systems is proposed as the "second green revolution". There are several recent publications on root system architecture (RSA), but the methods used to analyze the RSA have not been standardized. Here, we introduce traditional and current root-imaging methods and discuss root structure phenotyping. Some important root structures have not been standardized as roots are easily affected by rhizosphere conditions and exhibit greater plasticity than shoots; moreover, root morphology significantly varies even in the same genotype. For these reasons, it is difficult to define the ideal root systems for breeding. In this review, we introduce several types of software to analyze roots and identify important root parameters by modeling to simplify the root system characterization. These parameters can be extracted from photographs captured in the field. This modeling approach is applicable to various legacy root data stored in old or unpublished formats. Standardization of RSA data could help estimate root ideotypes.