Showing papers in "Plant Methods in 2020"

Early recognition of tomato gray leaf spot disease based on MobileNetv2-YOLOv3 model

Abstract: Tomato gray leaf spot is a worldwide disease, especially in warm and humid areas. The continuous expansion of greenhouse tomato cultivation area and the frequent introduction of foreign varieties in recent years have increased the severity of the epidemic hazards of this disease in some tomato planting bases annually. This disease is a newly developed one. Thus, farmers generally lack prevention and control experience and measures in production; the disease is often misdiagnosed or not prevented and controlled timely; this condition results in tomato production reduction or crop failure, which causes severe economic losses to farmers. Therefore, tomato gray leaf spot disease should be identified in the early stage, which will be important in avoiding or reducing the economic loss caused by the disease. The advent of the era of big data has facilitated the use of machine learning method in disease identification. Therefore, deep learning method is proposed to realise the early recognition of tomato gray leaf spot. Tomato growers need to develop the app of image detection mobile terminal of tomato gray leaf spot disease to realise real-time detection of this disease. This study proposes an early recognition method of tomato leaf spot based on MobileNetv2-YOLOv3 model to achieve a good balance between the accuracy and real-time detection of tomato gray leaf spot. This method improves the accuracy of the regression box of tomato gray leaf spot recognition by introducing the GIoU bounding box regression loss function. A MobileNetv2-YOLOv3 lightweight network model, which uses MobileNetv2 as the backbone network of the model, is proposed to facilitate the migration to the mobile terminal. The pre-training method combining mixup training and transfer learning is used to improve the generalisation ability of the model. The images captured under four different conditions are statistically analysed. The recognition effect of the models is evaluated by the F1 score and the AP value, and the experiment is compared with Faster-RCNN and SSD models. Experimental results show that the recognition effect of the proposed model is significantly improved. In the test dataset of images captured under the background of sufficient light without leaf shelter, the F1 score and AP value are 94.13% and 92.53%, and the average IOU value is 89.92%. In all the test sets, the F1 score and AP value are 93.24% and 91.32%, and the average IOU value is 86.98%. The object detection speed can reach 246 frames/s on GPU, the extrapolation speed for a single 416 × 416 picture is 16.9 ms, the detection speed on CPU can reach 22 frames/s, the extrapolation speed is 80.9 ms and the memory occupied by the model is 28 MB. The proposed recognition method has the advantages of low memory consumption, high recognition accuracy and fast recognition speed. This method is a new solution for the early prediction of tomato leaf spot and a new idea for the intelligent diagnosis of tomato leaf spot.

Deep convolutional neural networks for image-based Convolvulus sepium detection in sugar beet fields

Abstract: Convolvulus sepium (hedge bindweed) detection in sugar beet fields remains a challenging problem due to variation in appearance of plants, illumination changes, foliage occlusions, and different growth stages under field conditions. Current approaches for weed and crop recognition, segmentation and detection rely predominantly on conventional machine-learning techniques that require a large set of hand-crafted features for modelling. These might fail to generalize over different fields and environments. Here, we present an approach that develops a deep convolutional neural network (CNN) based on the tiny YOLOv3 architecture for C. sepium and sugar beet detection. We generated 2271 synthetic images, before combining these images with 452 field images to train the developed model. YOLO anchor box sizes were calculated from the training dataset using a k-means clustering approach. The resulting model was tested on 100 field images, showing that the combination of synthetic and original field images to train the developed model could improve the mean average precision (mAP) metric from 0.751 to 0.829 compared to using collected field images alone. We also compared the performance of the developed model with the YOLOv3 and Tiny YOLO models. The developed model achieved a better trade-off between accuracy and speed. Specifically, the average precisions (APs@IoU0.5) of C. sepium and sugar beet were 0.761 and 0.897 respectively with 6.48 ms inference time per image (800 × 1200) on a NVIDIA Titan X GPU environment. The developed model has the potential to be deployed on an embedded mobile platform like the Jetson TX for online weed detection and management due to its high-speed inference. It is recommendable to use synthetic images and empirical field images together in training stage to improve the performance of models.

Segmentation of roots in soil with U-Net.

Abstract: Plant root research can provide a way to attain stress-tolerant crops that produce greater yield in a diverse array of conditions. Phenotyping roots in soil is often challenging due to the roots being difficult to access and the use of time consuming manual methods. Rhizotrons allow visual inspection of root growth through transparent surfaces. Agronomists currently manually label photographs of roots obtained from rhizotrons using a line-intersect method to obtain root length density and rooting depth measurements which are essential for their experiments. We investigate the effectiveness of an automated image segmentation method based on the U-Net Convolutional Neural Network (CNN) architecture to enable such measurements. We design a data-set of 50 annotated chicory (Cichorium intybus L.) root images which we use to train, validate and test the system and compare against a baseline built using the Frangi vesselness filter. We obtain metrics using manual annotations and line-intersect counts. Our results on the held out data show our proposed automated segmentation system to be a viable solution for detecting and quantifying roots. We evaluate our system using 867 images for which we have obtained line-intersect counts, attaining a Spearman rank correlation of 0.9748 and an $$r^2$$ of 0.9217. We also achieve an $$F_1$$ of 0.7 when comparing the automated segmentation to the manual annotations, with our automated segmentation system producing segmentations with higher quality than the manual annotations for large portions of the image. We have demonstrated the feasibility of a U-Net based CNN system for segmenting images of roots in soil and for replacing the manual line-intersect method. The success of our approach is also a demonstration of the feasibility of deep learning in practice for small research groups needing to create their own custom labelled dataset from scratch.

Large scale genome skimming from herbarium material for accurate plant identification and phylogenomics.

Abstract: Herbaria are valuable sources of extensive curated plant material that are now accessible to genetic studies because of advances in high-throughput, next-generation sequencing methods. As an applied assessment of large-scale recovery of plastid and ribosomal genome sequences from herbarium material for plant identification and phylogenomics, we sequenced 672 samples covering 21 families, 142 genera and 530 named and proposed named species. We explored the impact of parameters such as sample age, DNA concentration and quality, read depth and fragment length on plastid assembly error. We also tested the efficacy of DNA sequence information for identifying plant samples using 45 specimens recently collected in the Pilbara. Genome skimming was effective at producing genomic information at large scale. Substantial sequence information on the chloroplast genome was obtained from 96.1% of samples, and complete or near-complete sequences of the nuclear ribosomal RNA gene repeat were obtained from 93.3% of samples. We were able to extract sequences for the core DNA barcode regions rbcL and matK from 96 to 93.3% of samples, respectively. Read quality and DNA fragment length had significant effects on sequencing outcomes and error correction of reads proved essential. Assembly problems were specific to certain taxa with low GC and high repeat content (Goodenia, Scaevola, Cyperus, Bulbostylis, Fimbristylis) suggesting biological rather than technical explanations. The structure of related genomes was needed to guide the assembly of repeats that exceeded the read length. DNA-based matching proved highly effective and showed that the efficacy for species identification declined in the order cpDNA >> rDNA > matK >> rbcL. We showed that a large-scale approach to genome sequencing using herbarium specimens produces high-quality complete cpDNA and rDNA sequences as a source of data for DNA barcoding and phylogenomics.

Computer vision and machine learning enabled soybean root phenotyping pipeline

Abstract: 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. 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. 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.

SpikeSegNet-a deep learning approach utilizing encoder-decoder network with hourglass for spike segmentation and counting in wheat plant from visual imaging

Abstract: High throughput non-destructive phenotyping is emerging as a significant approach for phenotyping germplasm and breeding populations for the identification of superior donors, elite lines, and QTLs. Detection and counting of spikes, the grain bearing organs of wheat, is critical for phenomics of a large set of germplasm and breeding lines in controlled and field conditions. It is also required for precision agriculture where the application of nitrogen, water, and other inputs at this critical stage is necessary. Further, counting of spikes is an important measure to determine yield. Digital image analysis and machine learning techniques play an essential role in non-destructive plant phenotyping analysis. In this study, an approach based on computer vision, particularly object detection, to recognize and count the number of spikes of the wheat plant from the digital images is proposed. For spike identification, a novel deep-learning network, SpikeSegNet, has been developed by combining two proposed feature networks: Local Patch extraction Network (LPNet) and Global Mask refinement Network (GMRNet). In LPNet, the contextual and spatial features are learned at the local patch level. The output of LPNet is a segmented mask image, which is further refined at the global level using GMRNet. Visual (RGB) images of 200 wheat plants were captured using LemnaTec imaging system installed at Nanaji Deshmukh Plant Phenomics Centre, ICAR-IARI, New Delhi. The precision, accuracy, and robustness (F1 score) of the proposed approach for spike segmentation are found to be 99.93%, 99.91%, and 99.91%, respectively. For counting the number of spikes, “analyse particles”—function of imageJ was applied on the output image of the proposed SpikeSegNet model. For spike counting, the average precision, accuracy, and robustness are 99%, 95%, and 97%, respectively. SpikeSegNet approach is tested for robustness with illuminated image dataset, and no significant difference is observed in the segmentation performance. In this study, a new approach called as SpikeSegNet has been proposed based on combined digital image analysis and deep learning techniques. A dedicated deep learning approach has been developed to identify and count spikes in the wheat plants. The performance of the approach demonstrates that SpikeSegNet is an effective and robust approach for spike detection and counting. As detection and counting of wheat spikes are closely related to the crop yield, and the proposed approach is also non-destructive, it is a significant step forward in the area of non-destructive and high-throughput phenotyping of wheat.

Analysis and comprehensive comparison of PacBio and nanopore-based RNA sequencing of the Arabidopsis transcriptome

Abstract: The number of studies using third-generation sequencing utilising Pacific Biosciences (PacBio) and Oxford Nanopore Technologies (ONT) is rapidly increasing in many different research areas. Among them, plant full-length single-molecule transcriptome studies have mostly used PacBio sequencing, whereas ONT is rarely used. Therefore, in this study, we examined ONT RNA sequencing methods in plants. We performed a detailed evaluation of reads from PacBio, Nanopore direct cDNA (ONT Dc), and Nanopore PCR cDNA (ONT Pc) sequencing including characteristics of raw data and identification of transcripts. In addition, matched Illumina data were generated for comparison. ONT Pc showed overall better raw data quality, whereas PacBio generated longer read lengths. In the transcriptome analysis, PacBio and ONT Pc performed similarly in transcript identification, simple sequence repeat analysis, and long non-coding RNA prediction. PacBio was superior in identifying alternative splicing events, whereas ONT Pc could estimate transcript expression levels. This paper made a comprehensive comparison of PacBio and nanopore-based RNA sequencing of the Arabidopsis transcriptome, the results indicate that ONT Pc is more cost-effective for generating extremely long reads and can characterise the transcriptome as well as quantify transcript expression. Therefore, ONT Pc is a new cost-effective and worthwhile method for full-length single-molecule transcriptome analysis in plants.

High-throughput three-dimensional visualization of root system architecture of rice using X-ray computed tomography

Abstract: X-ray computed tomography (CT) allows us to visualize root system architecture (RSA) beneath the soil, non-destructively and in a three-dimensional (3-D) form. However, CT scanning, reconstruction processes, and root isolation from X-ray CT volumes, take considerable time. For genetic analyses, such as quantitative trait locus mapping, which require a large population size, a high-throughput RSA visualization method is required. We have developed a high-throughput process flow for the 3-D visualization of rice (Oryza sativa) RSA (consisting of radicle and crown roots), using X-ray CT. The process flow includes use of a uniform particle size, calcined clay to reduce the possibility of visualizing non-root segments, use of a higher tube voltage and current in the X-ray CT scanning to increase root-to-soil contrast, and use of a 3-D median filter and edge detection algorithm to isolate root segments. Using high-performance computing technology, this analysis flow requires only 10 min (33 s, if a rough image is acceptable) for CT scanning and reconstruction, and 2 min for image processing, to visualize rice RSA. This reduced time allowed us to conduct the genetic analysis associated with 3-D RSA phenotyping. In 2-week-old seedlings, 85% and 100% of radicle and crown roots were detected, when 16 cm and 20 cm diameter pots were used, respectively. The X-ray dose per scan was estimated at < 0.09 Gy, which did not impede rice growth. Using the developed process flow, we were able to follow daily RSA development, i.e., 4-D RSA development, of an upland rice variety, over 3 weeks. We developed a high-throughput process flow for 3-D rice RSA visualization by X-ray CT. The X-ray dose assay on plant growth has shown that this methodology could be applicable for 4-D RSA phenotyping. We named the RSA visualization method ‘RSAvis3D’ and are confident that it represents a potentially efficient application for 3-D RSA phenotyping of various plant species.

Development of support vector machine-based model and comparative analysis with artificial neural network for modeling the plant tissue culture procedures: effect of plant growth regulators on somatic embryogenesis of chrysanthemum, as a case study

Abstract: Optimizing the somatic embryogenesis protocol can be considered as the first and foremost step in successful gene transformation studies. However, it is usually difficult to achieve an optimized embryogenesis protocol due to the cost and time-consuming as well as the complexity of this process. Therefore, it is necessary to use a novel computational approach, such as machine learning algorithms for this aim. In the present study, two machine learning algorithms, including Multilayer Perceptron (MLP) as an artificial neural network (ANN) and support vector regression (SVR), were employed to model somatic embryogenesis of chrysanthemum, as a case study, and compare their prediction accuracy. The results showed that SVR (R2 > 0.92) had better performance accuracy than MLP (R2 > 0.82). Moreover, the Non-dominated Sorting Genetic Algorithm-II (NSGA-II) was also applied for the optimization of the somatic embryogenesis and the results showed that the highest embryogenesis rate (99.09%) and the maximum number of somatic embryos per explant (56.24) can be obtained from a medium containing 9.10 μM 2,4-dichlorophenoxyacetic acid (2,4-D), 4.70 μM kinetin (KIN), and 18.73 μM sodium nitroprusside (SNP). According to our results, SVR-NSGA-II was able to optimize the chrysanthemum’s somatic embryogenesis accurately. SVR-NSGA-II can be employed as a reliable and applicable computational methodology in future plant tissue culture studies.

Drought and heat stress tolerance screening in wheat using computed tomography

Abstract: Improving abiotic stress tolerance in wheat requires large scale screening of yield components such as seed weight, seed number and single seed weight, all of which is very laborious, and a detailed analysis of seed morphology is time-consuming and visually often impossible. Computed tomography offers the opportunity for much faster and more accurate assessment of yield components. An X-ray computed tomographic analysis was carried out on 203 very diverse wheat accessions which have been exposed to either drought or combined drought and heat stress. Results demonstrated that our computed tomography pipeline was capable of evaluating grain set with an accuracy of 95–99%. Most accessions exposed to combined drought and heat stress developed smaller, shrivelled seeds with an increased seed surface. As expected, seed weight and seed number per ear as well as single seed size were significantly reduced under combined drought and heat compared to drought alone. Seed weight along the ear was significantly reduced at the top and bottom of the wheat spike. We were able to establish a pipeline with a higher throughput with scanning times of 7 min per ear and accuracy than previous pipelines predicting a set of agronomical important seed traits and to visualize even more complex traits such as seed deformations. The pipeline presented here could be scaled up to use for high throughput, high resolution phenotyping of tens of thousands of heads, greatly accelerating breeding efforts to improve abiotic stress tolerance.

Yield prediction by machine learning from UAS-based mulit-sensor data fusion in soybean

Abstract: Nowadays, automated phenotyping of plants is essential for precise and cost-effective improvement in the efficiency of crop genetics. In recent years, machine learning (ML) techniques have shown great success in the classification and modelling of crop parameters. In this research, we consider the capability of ML to perform grain yield prediction in soybeans by combining data from different optical sensors via RF (Random Forest) and XGBoost (eXtreme Gradient Boosting). During the 2018 growing season, a panel of 382 soybean recombinant inbred lines were evaluated in a yield trial at the Agronomy Center for Research and Education (ACRE) in West Lafayette (Indiana, USA). Images were acquired by the Parrot Sequoia Multispectral Sensor and the S.O.D.A. compact digital camera on board a senseFly eBee UAS (Unnamed Aircraft System) solution at R4 and early R5 growth stages. Next, a standard photogrammetric pipeline was carried out by SfM (Structure from Motion). Multispectral imagery serves to analyse the spectral response of the soybean end-member in 2D. In addition, RGB images were used to reconstruct the study area in 3D, evaluating the physiological growth dynamics per plot via height variations and crop volume estimations. As ground truth, destructive grain yield measurements were taken at the end of the growing season. Algorithms and feature extraction techniques were combined to develop a regression model to predict final yield from imagery, achieving an accuracy of over 90.72% by RF and 91.36% by XGBoost. Results provide practical information for the selection of phenotypes for breeding coming from UAS data as a decision support tool, affording constant operational improvement and proactive management for high spatial precision.

Non-destructive estimation of field maize biomass using terrestrial lidar: an evaluation from plot level to individual leaf level

Abstract: Precision agriculture is an emerging research field that relies on monitoring and managing field variability in phenotypic traits. An important phenotypic trait is biomass, a comprehensive indicator that can reflect crop yields. However, non-destructive biomass estimation at fine levels is unknown and challenging due to the lack of accurate and high-throughput phenotypic data and algorithms. In this study, we evaluated the capability of terrestrial light detection and ranging (lidar) data in estimating field maize biomass at the plot, individual plant, leaf group, and individual organ (i.e., individual leaf or stem) levels. The terrestrial lidar data of 59 maize plots with more than 1000 maize plants were collected and used to calculate phenotypes through a deep learning-based pipeline, which were then used to predict maize biomass through simple regression (SR), stepwise multiple regression (SMR), artificial neural network (ANN), and random forest (RF). The results showed that terrestrial lidar data were useful for estimating maize biomass at all levels (at each level, R2 was greater than 0.80), and biomass estimation at leaf group level was the most precise (R2 = 0.97, RMSE = 2.22 g) among all four levels. All four regression techniques performed similarly at all levels. However, considering the transferability and interpretability of the model itself, SR is the suggested method for estimating maize biomass from terrestrial lidar-derived phenotypes. Moreover, height-related variables showed to be the most important and robust variables for predicting maize biomass from terrestrial lidar at all levels, and some two-dimensional variables (e.g., leaf area) and three-dimensional variables (e.g., volume) showed great potential as well. We believe that this study is a unique effort on evaluating the capability of terrestrial lidar on estimating maize biomass at difference levels, and can provide a useful resource for the selection of the phenotypes and models required to estimate maize biomass in precision agriculture practices.

Simple semi-high throughput determination of activity signatures of key antioxidant enzymes for physiological phenotyping

Abstract: Reactive oxygen species (ROS) such as hydrogen peroxide and superoxide anions significantly accumulate during biotic and abiotic stress and cause oxidative damage and eventually cell death. There is accumulating evidence that ROS are also involved in regulating beneficial plant–microbe interactions, signal transduction and plant growth and development. Due to the relevance of ROS throughout the life cycle and for interaction with the multifactorial environment, the physiological phenotyping of the mechanisms controlling ROS homeostasis is of general importance. In this study, we have developed a robust and resource-efficient experimental platform that allows the determination of the activities of the nine key ROS scavenging enzymes from a single extraction that integrates posttranscriptional and posttranslational regulations. The assays were optimized and adapted for a semi-high throughput 96-well assay format. In a case study, we have analyzed tobacco leaves challenged by pathogen infection, drought and salt stress. The three stress factors resulted in distinct activity signatures with differential temporal dynamics. This experimental platform proved to be suitable to determine the antioxidant enzyme activity signature in different tissues of monocotyledonous and dicotyledonous model and crop plants. The universal enzymatic extraction procedure combined with the 96-well assay format demonstrated to be a simple, fast and semi-high throughput experimental platform for the precise and robust fingerprinting of nine key antioxidant enzymatic activities in plants.

A multiplex guide RNA expression system and its efficacy for plant genome engineering

Abstract: The Streptococcus pyogenes CRISPR system is composed of a Cas9 endonuclease (SpCas9) and a single-stranded guide RNA (gRNA) harboring a target-specific sequence. Theoretically, SpCas9 proteins could cleave as many targeted loci as gRNAs bind in a genome. We introduce a PCR-free multiple gRNA cloning system for editing plant genomes. This method consists of two steps: (1) cloning the annealed products of two single-stranded oligonucleotide fragments harboring a complimentary target-binding sequence on each strand between tRNA and gRNA scaffold sequences in a pGRNA vector; and (2) assembling tRNA-gRNA units from several pGRNA vectors with a plant binary vector containing a SpCas9 expression cassette using the Golden Gate assembly method. We validated the editing efficiency and patterns of the multiplex gRNA expression system in wild tobacco (Nicotiana attenuata) protoplasts and in transformed plants by performing targeted deep sequencing. Two proximal cleavages by SpCas9-gRNA largely increased the editing efficiency and induced large deletions between two cleavage sites. This multiplex gRNA expression system enables high-throughput production of a single binary vector and increases the efficiency of plant genome editing.

Wheat ear counting using K-means clustering segmentation and convolutional neural network

Abstract: Wheat yield is influenced by the number of ears per unit area, and manual counting has traditionally been used to estimate wheat yield. To realize rapid and accurate wheat ear counting, K-means clustering was used for the automatic segmentation of wheat ear images captured by hand-held devices. The segmented data set was constructed by creating four categories of image labels: non-wheat ear, one wheat ear, two wheat ears, and three wheat ears, which was then was sent into the convolution neural network (CNN) model for training and testing to reduce the complexity of the model. The recognition accuracy of non-wheat, one wheat, two wheat ears, and three wheat ears were 99.8, 97.5, 98.07, and 98.5%, respectively. The model R2 reached 0.96, the root mean square error (RMSE) was 10.84 ears, the macro F1-score and micro F1-score both achieved 98.47%, and the best performance was observed during late grain-filling stage (R2 = 0.99, RMSE = 3.24 ears). The model could also be applied to the UAV platform (R2 = 0.97, RMSE = 9.47 ears). The classification of segmented images as opposed to target recognition not only reduces the workload of manual annotation but also improves significantly the efficiency and accuracy of wheat ear counting, thus meeting the requirements of wheat yield estimation in the field environment.

Leaf to panicle ratio (LPR): a new physiological trait indicative of source and sink relation in japonica rice based on deep learning

Abstract: Identification and characterization of new traits with sound physiological foundation is essential for crop breeding and production management. Deep learning has been widely used in image data analysis to explore spatial and temporal information on crop growth and development, thus strengthening the power of identification of physiological traits. Taking the advantage of deep learning, this study aims to develop a novel trait of canopy structure that integrate source and sink in japonica rice. We applied a deep learning approach to accurately segment leaf and panicle, and subsequently developed the procedure of GvCrop to calculate the leaf to panicle ratio (LPR) of rice canopy during grain filling stage. Images of training dataset were captured in the field experiments, with large variations in camera shooting angle, the elevation and the azimuth angles of the sun, rice genotype, and plant phenological stages. Accurately labeled by manually annotating the panicle and leaf regions, the resulting dataset were used to train FPN-Mask (Feature Pyramid Network Mask) models, consisting of a backbone network and a task-specific sub-network. The model with the highest accuracy was then selected to check the variations in LPR among 192 rice germplasms and among agronomical practices. Despite the challenging field conditions, FPN-Mask models achieved a high detection accuracy, with Pixel Accuracy being 0.99 for panicles and 0.98 for leaves. The calculated LPR displayed large spatial and temporal variations as well as genotypic differences. In addition, it was responsive to agronomical practices such as nitrogen fertilization and spraying of plant growth regulators. Deep learning technique can achieve high accuracy in simultaneous detection of panicle and leaf data from complex rice field images. The proposed FPN-Mask model is applicable to detect and quantify crop performance under field conditions. The newly identified trait of LPR should provide a high throughput protocol for breeders to select superior rice cultivars as well as for agronomists to precisely manage field crops that have a good balance of source and sink.

Machine learning for high-throughput field phenotyping and image processing provides insight into the association of above and below-ground traits in cassava ( Manihot esculenta Crantz)

Abstract: Rapid non-destructive measurements to predict cassava root yield over the full growing season through large numbers of germplasm and multiple environments is a huge challenge in Cassava breeding programs. As opposed to waiting until the harvest season, multispectral imagery using unmanned aerial vehicles (UAV) are capable of measuring the canopy metrics and vegetation indices (VIs) traits at different time points of the growth cycle. This resourceful time series aerial image processing with appropriate analytical framework is very important for the automatic extraction of phenotypic features from the image data. Many studies have demonstrated the usefulness of advanced remote sensing technologies coupled with machine learning (ML) approaches for accurate prediction of valuable crop traits. Until now, Cassava has received little to no attention in aerial image-based phenotyping and ML model testing. To accelerate image processing, an automated image-analysis framework called CIAT Pheno-i was developed to extract plot level vegetation indices/canopy metrics. Multiple linear regression models were constructed at different key growth stages of cassava, using ground-truth data and vegetation indices obtained from a multispectral sensor. Henceforth, the spectral indices/features were combined to develop models and predict cassava root yield using different Machine learning techniques. Our results showed that (1) Developed CIAT pheno-i image analysis framework was found to be easier and more rapid than manual methods. (2) The correlation analysis of four phenological stages of cassava revealed that elongation (EL) and late bulking (LBK) were the most useful stages to estimate above-ground biomass (AGB), below-ground biomass (BGB) and canopy height (CH). (3) The multi-temporal analysis revealed that cumulative image feature information of EL + early bulky (EBK) stages showed a higher significant correlation (r = 0.77) for Green Normalized Difference Vegetation indices (GNDVI) with BGB than individual time points. Canopy height measured on the ground correlated well with UAV (CHuav)-based measurements (r = 0.92) at late bulking (LBK) stage. Among different image features, normalized difference red edge index (NDRE) data were found to be consistently highly correlated (r = 0.65 to 0.84) with AGB at LBK stage. (4) Among the four ML algorithms used in this study, k-Nearest Neighbours (kNN), Random Forest (RF) and Support Vector Machine (SVM) showed the best performance for root yield prediction with the highest accuracy of R2 = 0.67, 0.66 and 0.64, respectively. UAV platforms, time series image acquisition, automated image analytical framework (CIAT Pheno-i), and key vegetation indices (VIs) to estimate phenotyping traits and root yield described in this work have great potential for use as a selection tool in the modern cassava breeding programs around the world to accelerate germplasm and varietal selection. The image analysis software (CIAT Pheno-i) developed from this study can be widely applicable to any other crop to extract phenotypic information rapidly.

Deep learning-based detection of seedling development.

Abstract: Monitoring the timing of seedling emergence and early development via high-throughput phenotyping with computer vision is a challenging topic of high interest in plant science. While most studies focus on the measurements of leaf area index or detection of specific events such as emergence, little attention has been put on the identification of kinetics of events of early seedling development on a seed to seed basis. Imaging systems screened the whole seedling growth process from the top view. Precise annotation of emergence out of the soil, cotyledon opening, and appearance of first leaf was conducted. This annotated data set served to train deep neural networks. Various strategies to incorporate in neural networks, the prior knowledge of the order of the developmental stages were investigated. Best results were obtained with a deep neural network followed with a long short term memory cell, which achieves more than 90% accuracy of correct detection. This work provides a full pipeline of image processing and machine learning to classify three stages of plant growth plus soil on the different accessions of two species of red clover and alfalfa but which could easily be extended to other crops and other stages of development.

ROSE-X: an annotated data set for evaluation of 3D plant organ segmentation methods

Abstract: The production and availability of annotated data sets are indispensable for training and evaluation of automatic phenotyping methods. The need for complete 3D models of real plants with organ-level labeling is even more pronounced due to the advances in 3D vision-based phenotyping techniques and the difficulty of full annotation of the intricate 3D plant structure. We introduce the ROSE-X data set of 11 annotated 3D models of real rosebush plants acquired through X-ray tomography and presented both in volumetric form and as point clouds. The annotation is performed manually to provide ground truth data in the form of organ labels for the voxels corresponding to the plant shoot. This data set is constructed to serve both as training data for supervised learning methods performing organ-level segmentation and as a benchmark to evaluate their performance. The rosebush models in the data set are of high quality and complex architecture with organs frequently touching each other posing a challenge for the current plant organ segmentation methods. We report leaf/stem segmentation results obtained using four baseline methods. The best performance is achieved by the volumetric approach where local features are trained with a random forest classifier, giving Intersection of Union (IoU) values of 97.93% and 86.23% for leaf and stem classes, respectively. We provided an annotated 3D data set of 11 rosebush plants for training and evaluation of organ segmentation methods. We also reported leaf/stem segmentation results of baseline methods, which are open to improvement. The data set, together with the baseline results, has the potential of becoming a significant resource for future studies on automatic plant phenotyping.

Evaluation of novel precision viticulture tool for canopy biomass estimation and missing plant detection based on 2.5D and 3D approaches using RGB images acquired by UAV platform.

Abstract: The knowledge of vine vegetative status within a vineyard plays a key role in canopy management in order to achieve a correct vine balance and reach the final desired yield/quality. Detailed information about canopy architecture and missing plants distribution provides useful support for farmers/winegrowers to optimize canopy management practices and the replanting process, respectively. In the last decade, there has been a progressive diffusion of UAV (Unmanned Aerial Vehicles) technologies for Precision Viticulture purposes, as fast and accurate methodologies for spatial variability of geometric plant parameters. The aim of this study was to implement an unsupervised and integrated procedure of biomass estimation and missing plants detection, using both the 2.5D-surface and 3D-alphashape methods. Both methods showed good overall accuracy respect to ground truth biomass measurements with high values of R2 (0.71 and 0.80 for 2.5D and 3D, respectively). The 2.5D method led to an overestimation since it is derived by considering the vine as rectangular cuboid form. On the contrary, the 3D method provided more accurate results as a consequence of the alphashape algorithm, which is capable to detect each single shoot and holes within the canopy. Regarding the missing plants detection, the 3D approach confirmed better performance in cases of hidden conditions by shoots of adjacent plants or sparse canopy with some empty spaces along the row, where the 2.5D method based on the length of section of the row with lower thickness than the threshold used (0.10 m), tended to return false negatives and false positives, respectively. This paper describes a rapid and objective tool for the farmer to promptly identify canopy management strategies and drive replanting decisions. The 3D approach provided results closer to real canopy volume and higher performance in missing plant detection. However, the dense cloud based analysis required more processing time. In a future perspective, given the continuous technological evolution in terms of computing performance, the overcoming of the current limit represented by the pre- and post-processing phases of the large image dataset should mainstream this methodology.

A cucumber green mottle mosaic virus vector for virus-induced gene silencing in cucurbit plants

Abstract: Cucurbits produce fruits or vegetables that have great dietary importance and economic significance worldwide. The published genomes of at least 11 cucurbit species are boosting gene mining and novel breeding strategies, however genetic transformation in cucurbits is impractical as a tool for gene function validation due to low transformation efficiency. Virus-induced gene silencing (VIGS) is a potential alternative tool. So far, very few ideal VIGS vectors are available for cucurbits. Here, we describe a new VIGS vector derived from cucumber green mottle mosaic virus (CGMMV), a monopartite virus that infects cucurbits naturally. We show that the CGMMV vector is competent to induce efficient silencing of the phytoene desaturase (PDS) gene in the model plant Nicotiana benthamiana and in cucurbits, including watermelon, melon, cucumber and bottle gourd. Infection with the CGMMV vector harboring PDS sequences of 69–300 bp in length in the form of sense-oriented or hairpin cDNAs resulted in photobleaching phenotypes in N. benthamiana and cucurbits by PDS silencing. Additional results reflect that silencing of the PDS gene could persist for over two months and the silencing effect of CGMMV-based vectors could be passaged. These results demonstrate that CGMMV vector could serve as a powerful and easy-to-use tool for characterizing gene function, controlling viral pathogens or even performing resistance breeding in cucurbits. Moreover, this study will possess considerable important reference value for developing different viral vectors.

Recent developments and emerging trends of mass spectrometric methods in plant hormone analysis: a review

Abstract: Plant hormones are naturally occurring small molecule compounds which are present at trace amounts in plant. They play a pivotal role in the regulation of plant growth. The biological activity of plant hormones depends on their concentrations in the plant, thus, accurate determination of plant hormone is paramount. However, the complex plant matrix, wide polarity range and low concentration of plant hormones are the main hindrances to effective analyses of plant hormone even when state-of-the-art analytical techniques are employed. These factors substantially influence the accuracy of analytical results. So far, significant progress has been realized in the analysis of plant hormones, particularly in sample pretreatment techniques and mass spectrometric methods. This review describes the classic extraction and modern microextraction techniques used to analyze plant hormone. Advancements in solid phase microextraction (SPME) methods have been driven by the ever-increasing requirement for dynamic and in vivo identification of the spatial distribution of plant hormones in real-life plant samples, which would contribute greatly to the burgeoning field of plant hormone investigation. In this review, we describe advances in various aspects of mass spectrometry methods. Many fragmentation patterns are analyzed to provide the theoretical basis for the establishment of a mass spectral database for the analysis of plant hormones. We hope to provide a technical guide for further discovery of new plant hormones. More than 140 research studies on plant hormone published in the past decade are reviewed, with a particular emphasis on the recent advances in mass spectrometry and sample pretreatment techniques in the analysis of plant hormone. The potential progress for further research in plant hormones analysis is also highlighted.

Pharmacodynamic material basis of traditional Chinese medicine based on biomacromolecules: a review.

Abstract: Biomacromolecules, the first components of bioactive substances in traditional Chinese medicines (TCM) have wide bioactivity-related efficacy but have not yet been fully appreciated compared to small molecule components. The present review brings a novel and systemic point of view to deepen the understanding of the pharmacodynamic material basis of TCM based on biomacromolecules (polysaccharides, proteins and nucleic acids). Biomacromolecules have been, are and will have considerable roles in the efficacy of Chinese medicine, as evidenced by the number of biological activities related to traditional clinical efficacy. The direct and indirect mechanisms of biomacromolecules are further accounted for in a variety of neurotransmitters, hormones, and immune substances to maintain immune function in both sensitive and stable equilibrium. The biological functions of biomacromolecules have been elaborated on in regard to their roles in the process of plant growth and development to the relationship between primary metabolism and secondary metabolism and to the indispensable role of polysaccharides, proteins, and nucleic acids in the quality formation of TCM. Understanding the functional properties and mechanisms of biological macromolecules will help to demystify the drug properties and health benefits of TCM.

A robust spectral angle index for remotely assessing soybean canopy chlorophyll content in different growing stages

Abstract: Timely and accurate estimates of canopy chlorophyll (Chl) a and b content are crucial for crop growth monitoring and agricultural management. Crop canopy reflectance depends on many factors, which can be divided into the following categories: (i) leaf effects (e.g., leaf pigments), (ii) canopy effects (e.g., Leaf Area Index [LAI]), and (iii) soil background reflectance (e.g., soil reflectance). The estimation of leaf variables, such as Chl contents, from reflectance at the canopy scale is usually less accurate than that at the leaf scale. In this study, we propose a Visible and Near-infrared (NIR) Angle Index (VNAI) to estimate the Chl content of soybean canopy, and soybean canopy Chl maps are produced using visible and NIR unmanned aerial vehicle (UAV) remote sensing images. The VNAI is insensitive to LAI and can be used for the multi-stage estimation of crop canopy Chl content. Eleven previously used vegetation indices (VIs) (e.g., Pigment-specific Normalized Difference Index) were selected for performance comparison. The results showed that (i) most previously used Chl VIs were significantly correlated with LAI, and the proposed VNAI was more sensitive to Chl content than LAI; (ii) the VNAI-based estimates of Chl content were more accurate than those based on the other investigated VIs using (1) simulated, (2) real (field), and (3) real (UAV) datasets. Most previously used Chl VIs were significantly correlated with LAI whereas the proposed VNAI was more sensitive to Chl content than to LAI, indicating that the VNAI may be more strongly correlated with Chl content than these previously used VIs. Multi-stage estimations of the Chl content of cropland obtained using the VNAI and broadband remote sensing images may help to obtain Chl maps with high temporal and spatial resolution.

SILEX: a fast and inexpensive high-quality DNA extraction method suitable for multiple sequencing platforms and recalcitrant plant species

Abstract: The use of sequencing and genotyping platforms has undergone dramatic improvements, enabling the generation of a wealth of genomic information. Despite this progress, the availability of high-quality genomic DNA (gDNA) in sufficient concentrations is often a main limitation, especially for third-generation sequencing platforms. A variety of DNA extraction methods and commercial kits are available. However, many of these are costly and frequently give either low yield or low-quality DNA, inappropriate for next generation sequencing (NGS) platforms. Here, we describe a fast and inexpensive DNA extraction method (SILEX) applicable to a wide range of plant species and tissues. SILEX is a high-throughput DNA extraction protocol, based on the standard CTAB method with a DNA silica matrix recovery, which allows obtaining NGS-quality high molecular weight genomic plant DNA free of inhibitory compounds. SILEX was compared with a standard CTAB extraction protocol and a common commercial extraction kit in a variety of species, including recalcitrant ones, from different families. In comparison with the other methods, SILEX yielded DNA in higher concentrations and of higher quality. Manual extraction of 48 samples can be done in 96 min by one person at a cost of 0.12 €/sample of reagents and consumables. Hundreds of tomato gDNA samples obtained with either SILEX or the commercial kit were successfully genotyped with Single Primer Enrichment Technology (SPET) with the Illumina HiSeq 2500 platform. Furthermore, DNA extracted from Solanum elaeagnifolium using this protocol was assessed by Pulsed-field gel electrophoresis (PFGE), obtaining a suitable size ranges for most sequencing platforms that required high-molecular-weight DNA such as Nanopore or PacBio. A high-throughput, fast and inexpensive DNA extraction protocol was developed and validated for a wide variety of plants and tissues. SILEX offers an easy, scalable, efficient and inexpensive way to extract DNA for various next-generation sequencing applications including SPET and Nanopore among others.

DeepFlower: a deep learning-based approach to characterize flowering patterns of cotton plants in the field

Abstract: Flowering is one of the most important processes for flowering plants such as cotton, reflecting the transition from vegetative to reproductive growth and is of central importance to crop yield and adaptability. Conventionally, categorical scoring systems have been widely used to study flowering patterns, which are laborious and subjective to apply. The goal of this study was to develop a deep learning-based approach to characterize flowering patterns for cotton plants that flower progressively over several weeks, with flowers distributed across much of the plant. A ground mobile system (GPhenoVision) was modified with a multi-view color imaging module, to acquire images of a plant from four viewing angles at a time. A total of 116 plants from 23 genotypes were imaged during an approximately 2-month period with an average scanning interval of 2–3 days, yielding a dataset containing 8666 images. A subset (475) of the images were randomly selected and manually annotated to form datasets for training and selecting the best object detection model. With the best model, a deep learning-based approach (DeepFlower) was developed to detect and count individual emerging blooms for a plant on a given date. The DeepFlower was used to process all images to obtain bloom counts for individual plants over the flowering period, using the resulting counts to derive flowering curves (and thus flowering characteristics). Regression analyses showed that the DeepFlower method could accurately (R2 = 0.88 and RMSE = 0.79) detect and count emerging blooms on cotton plants, and statistical analyses showed that imaging-derived flowering characteristics had similar effectiveness as manual assessment for identifying differences among genetic categories or genotypes. The developed approach could thus be an effective and efficient tool to characterize flowering patterns for flowering plants (such as cotton) with complex canopy architecture.

Analysis of trace metal distribution in plants with lab-based microscopic X-ray fluorescence imaging.

Abstract: Many metals are essential for plants and humans. Knowledge of metal distribution in plant tissues in vivo contributes to the understanding of physiological mechanisms of metal uptake, accumulation and sequestration. For those studies, X-rays are a non-destructive tool, especially suited to study metals in plants. We present microfluorescence imaging of trace elements in living plants using a customized benchtop X-ray fluorescence machine. The system was optimized by additional detector shielding to minimize stray counts, and by a custom-made measuring chamber to ensure sample integrity. Protocols of data recording and analysis were optimised to minimise artefacts. We show that Zn distribution maps of whole leaves in high resolution are easily attainable in the hyperaccumulator Noccaea caerulescens. The sensitivity of the method was further shown by analysis of micro- (Cu, Ni, Fe, Zn) and macronutrients (Ca, K) in non-hyperaccumulating crop plants (soybean roots and pepper leaves), which could be obtained in high resolution for scan areas of several millimetres. This allows to study trace metal distribution in shoots and roots with a wide overview of the object, and thus avoids making conclusions based on singular features of tiny spots. The custom-made measuring chamber with continuous humidity and air supply coupled to devices for imaging chlorophyll fluorescence kinetic measurements enabled direct correlation of element distribution with photosynthesis. Leaf samples remained vital even after 20 h of X-ray measurements. Subtle changes in some of photosynthetic parameters in response to the X-ray radiation are discussed. We show that using an optimized benchtop machine, with protocols for measurement and quantification tailored for plant analyses, trace metal distribution can be investigated in a reliable manner in intact, living plant leaves and roots. Zinc distribution maps showed higher accumulation in the tips and the veins of young leaves compared to the mesophyll tissue, while in the older leaves the distribution was more homogeneous.

Efficient chromatin profiling of H3K4me3 modification in cotton using CUT&Tag

Abstract: In 2019, Kaya-Okur et al. reported on the cleavage under targets and tagmentation (CUT&Tag) technology for efficient profiling of epigenetically modified DNA fragments. It was used mainly for cultured cell lines and was especially effective for small samples and single cells. This strategy generated high-resolution and low-background-noise chromatin profiling data for epigenomic analysis. CUT&Tag is well suited to be used in plant cells, especially in tissues from which small samples are taken, such as ovules, anthers, and fibers. Here, we present a CUT&Tag protocol step by step using plant nuclei. In this protocol, we quantified the nuclei that can be used in each CUT&Tag reaction, and compared the efficiency of CUT&Tag with chromatin immunoprecipitation with sequencing (ChIP-seq) in the leaves of cotton. A general workflow for the bioinformatic analysis of CUT&Tag is also provided. Results indicated that, compared with ChIP-seq, the CUT&Tag procedure was faster and showed a higher-resolution, lower-background signal than did ChIP. A CUT&Tag protocol has been refined for plant cells using intact nuclei that have been isolated.

An improved strategy to analyse strigolactones in complex sample matrices using UHPLC–MS/MS

Abstract: Strigolactones represent the most recently described group of plant hormones involved in many aspects of plant growth regulation. Simultaneously, root exuded strigolactones mediate rhizosphere signaling towards beneficial arbuscular mycorrhizal fungi, but also attract parasitic plants. The seed germination of parasitic plants induced by host strigolactones leads to serious agricultural problems worldwide. More insight in these signaling molecules is hampered by their extremely low concentrations in complex soil and plant tissue matrices, as well as their instability. So far, the combination of tailored isolation—that would replace current unspecific, time-consuming and labour-intensive processing of large samples—and a highly sensitive method for the simultaneous profiling of a broad spectrum of strigolactones has not been reported. Depending on the sample matrix, two different strategies for the rapid extraction of the seven structurally similar strigolactones and highly efficient single-step pre-concentration on polymeric RP SPE sorbent were developed and validated. Compared to conventional methods, controlled temperature during the extraction and the addition of an organic modifier (acetonitrile, acetone) to the extraction solvent helped to tailor strigolactone isolation from low initial amounts of root tissue (150 mg fresh weight, FW) and root exudate (20 ml), which improved both strigolactone stability and sample purity. We have designed an efficient UHPLC separation with sensitive MS/MS detection for simultaneous analysis of seven natural strigolactones including their biosynthetic precursors—carlactone and carlactonoic acid. In combination with the optimized UHPLC–MS/MS method, attomolar detection limits were achieved. The new method allowed successful profiling of seven strigolactones in small exudate and root tissue samples of four different agriculturally important plant species—sorghum, rice, pea and tomato. The established method provides efficient strigolactone extraction with aqueous mixtures of less nucleophilic organic solvents from small root tissue and root exudate samples, in combination with rapid single-step pre-concentration. This method improves strigolactone stability and eliminates the co-extraction and signal of matrix-associated contaminants during the final UHPLC–MS/MS analysis with an electrospray interface, which dramatically increases the overall sensitivity of the analysis. We show that the method can be applied to a variety of plant species.

Phenotypic techniques and applications in fruit trees: a review.

Abstract: Phenotypic information is of great significance for irrigation management, disease prevention and yield improvement. Interest in the evaluation of phenotypes has grown with the goal of enhancing the quality of fruit trees. Traditional techniques for monitoring fruit tree phenotypes are destructive and time-consuming. The development of advanced technology is the key to rapid and non-destructive detection. This review describes several techniques applied to fruit tree phenotypic research in the field, including visible and near-infrared (VIS–NIR) spectroscopy, digital photography, multispectral and hyperspectral imaging, thermal imaging, and light detection and ranging (LiDAR). The applications of these technologies are summarized in terms of architecture parameters, pigment and nutrient contents, water stress, biochemical parameters of fruits and disease detection. These techniques have been shown to play important roles in fruit tree phenotypic research.