Plant Phenomics最新文献

Unmanned aerial vehicle (UAV)-based multispectral imaging is one of the most widely used technologies for rapid crop monitoring, essential for crop-growth management. However, the technology's complex optical structure and difficulty in interpreting real-time crop-growth information seriously restrict its application. This paper presents a newly designed UAV-based snapshot multispectral imaging crop-growth sensor (SMICGS) aimed at simplifying the optical structure and realizing the online interpretation of crop spectral information. Mosaic filters based on the special spectral characteristics of crops were designed to achieve multiband co-optical imaging. A spectral crosstalk correction method based on the pixel response characteristics of SMICGS was proposed, and a processing system based on the coupling of sensor information and crop-growth monitoring models was developed to realize real-time online processing of crop spectral information. Field experiments showed that the vegetation indices obtained by SMICGS combined with the machine learning algorithm random forest (RF) achieved better results in predicting leaf area index (LAI) and above-ground biomass (AGB) for wheat and rice. For wheat, the R² and root mean square error (RMSE) values for the LAI and AGB prediction models were 0.81 and 0.85, and 0.682 and 1.127 ​t/ha, respectively. For rice, the R² and RMSE values for the LAI and AGB prediction models were 0.89 and 0.93, and 0.818 and 0.866 ​t/ha, respectively. Overall, SMICGS provides a reliable foundational tool for real-time, non-destructive monitoring of field crop growth information, offering significant potential for the precise management of agricultural production.

Sorghum canopy architecture in field trials is determined by various phenotypic traits, such plant and panicle count, leaf density and angle and panicle morphology, and canopy height. These traits together affect light capture and biomass production as well as conversion of photosynthates to grain yield. Panicle morphology exhibits considerable variation as influenced by genetics, environmental conditions and management practices. This study presents a framework for the 3D reconstruction of sorghum canopies and phenotyping panicle morphology. First, we developed a scalable, low-altitude Unmanned Aerial Vehicle (UAV)-based protocol that leverages videos for efficient data acquisition, combined with Neural Radiance Fields (NeRF)s to generate high-quality 3D point cloud reconstructions of sorghum canopies. Next, a 3D model was built to simulate 3D sorghum canopies to create annotated datasets for training deep learning-based semantic segmentation and panicle detection algorithms. Finally, we propose SegVoteNet, a novel multi-task deep learning model that integrates VoteNet and PointNet++ within a shared backbone architecture. Designed for semantic segmentation and 3D detection on pure point cloud data, SegVoteNet incorporates a voting and sampling module that leverages segmentation results to optimize object proposal generation. SegVoteNet is robust, achieving 0.986 Mean Average Precision (mAP) @ 0.5 Intersection Over Union (IOU) on synthetic datasets, and 0.850 mAP @ 0.5 IOU on real point cloud datasets for sorghum panicle detection, without fine-tuning. This set of pipelines provides a robust scalable method for phenotyping sorghum panicles in field trials in breeding and commercial applications. Further work is developing a capability to estimate grain number per panicle, which would provide breeders with additional phenotypes to select.

Noninvasive analysis of pod phenotypic traits under field conditions is crucial for soybean breeding research. However, previous pod phenotyping studies focused on postharvest materials or were limited to indoor scenarios, failing to generalize to real-field environments. To address these issues, this paper employs an instance segmentation approach for the precise extraction of the pod area from multiplant RGB images in preharvest soybean fields. We first introduce a cost-effective workflow for constructing datasets of densely planted crop images with a uniform backdrop. Starting with video recording, high-quality static frames are collected by automatic selection. Then, a large vision model is explored to facilitate dense annotation and build a large-scale soybean dataset comprising 20k pod masks. Second, the pod instance segmentation model PodNet is developed based on the YOLOv8 architecture. We propose a novel hierarchical prototype aggregation strategy to fuse multiscale semantic features and a U-EMA prototype generation network to improve the model's perception performance for small objects. Comprehensive experiments suggest that lightweight PodNet achieves a superior mean average accuracy of 0.786 in the custom pod segmentation dataset. PodNet also performs competitively on in-field images without a backdrop and enables real-time inference on the edge computing platform. To the best of our knowledge, PodNet is the first pod instance segmentation model for preharvest fields. The low-cost and high-precision extraction of pods is not only a prerequisite for phenotypic analysis of the pod organs but also constitutes an important foundation in conducting cross-scale phenotyping from whole-plant to seed levels.

Identification of the phenotypes of fruits is critical for understanding complex genetic traits. Computed tomography (CT) imaging technology enables the noninvasive acquisition of three-dimensional images of fruit interiors, thus providing a robust data foundation for phenotypic analysis. Accurate segmentation of internal fruit tissues is essential, as it directly influences the accuracy and reliability of the results. Current methods are not optimized for the unique features of plant fruit images. This study introduces XFruitSeg, which is a general deep learning model for segmenting plant fruit CT images. The model uses a U-shaped encoder-decoder architecture and integrates multitask learning. A large convolutional kernel network, RepLKNet, expands the receptive field for feature extraction. Multiscale skip connections and a deep supervision mechanism improve the model's capacity to learn features of various sizes, and a contour feature learning branch specifically targets the interorganizational boundaries. An optimized composite loss function enhances the model's robustness when applied to imbalanced categories. Additionally, a dataset named XrayFruitData was established, which contains high-resolution images of twelve plant fruit varieties, with accurate annotations for orange, mangosteen, and durian fruits for model evaluation. Compared with four mainstream advanced models, XFruitSeg achieved superior segmentation performance on the orange, mangosteen, and durian datasets, with mean Dice coefficients of 95.21 ​%, 93.24 ​%, and 94.70 ​% and mean intersection over union (mIoU) scores of 91.09 ​%, 87.91 ​%, and 90.35 ​%, respectively. The results of extensive ablation experiments demonstrate the effectiveness of each component. Therefore, the proposed XFruitSeg model has been proven to be beneficial for high-precision analysis of internal fruit phenotyping traits.

The disease syndrome "basses richesses" (SBR) leads to a significant reduction in sugar beet biomass and sugar content, negatively affecting the sugar economy. The mechanistic understanding regarding growth and photoassimilates distribution within the sugar beet taproot diseased with SBR is currently incomplete. We combined two tomographic methods, magnetic resonance imaging (MRI) and positron emission tomography (PET) using ¹¹C as tracer, to non-invasively determine SBR effects on structural growth and photoassimilates distribution within the developing taproot over six weeks. MRI analysis revealed a deformed cross-sectional anatomical structure from an early stage, as well as a reduction in taproot volume and width of inner cambium ring structures of up to 26 and 24 ​%, respectively. These SBR disease effects were also confirmed by post-harvest analysis of the taproot. PET analysis revealed a heterogeneous distribution of labeled photoassimilates for diseased plants: sectors of the taproot with characteristic SBR symptoms showed little to very low ¹¹C tracer signal. The heterogeneity of SBR disease effects is most likely due to a partial inoculation of leaves leading to an uneven distribution of the SBR pathogen in the taproot through the strong vascular interconnection between shoot and root. Also, the pathogen needs to spread non-uniformly within the taproot to explain the observed marked increase of the SBR disease effects over time. Our results indicate that SBR affects photoassimilates sink capacity at an early stage of taproot development. Co-registration of MRI and PET may support an early judging of susceptibility and selection of promising genotype candidates for future breeding programs.

Leaf spectroscopy, combined with partial least squares regression (PLSR), is recognized as an efficient and precise tool for measuring plant leaf traits. However, the feasibility of developing a generalizable model remains unclear, primarily due to limited understanding of PLSR model transferability. Here, we collected six key leaf traits along with paired leaf reflectance spectra from 1967 samples of 349 tree species in eight forest sites across China. Using this dataset, we explored the transferability of PLSR models, factors affecting model transferability, and the feasibility of developing generalizable PLSR models for leaf trait prediction. Overall, PLSR models trained at a specific study site demonstrate limited transferability to other study sites. Dissimilarities in plant evolutionary history and environmental conditions between study sites are the primary factors influencing the transferability of PLSR models. Incorporating training data from diverse evolutionary histories and environmental conditions can improve the transferability of PLSR models, achieving accuracy equivalent to that of site-specific models. Our findings provide guidelines for the use of spectroscopy in leaf trait prediction and underscore the urgent need for collaborative efforts to build an open database of leaf traits and reflectance spectra, thereby promoting the development of universal PLSR models for plant leaf trait prediction.

The spike number (SN) is an important trait that significantly impacts grain yield in wheat. Manual counting of SN is time-consuming, hindering large-scale breeding efforts. Hence, there is an urgent need to develop efficient and accurate methodologies for SN counting. A YOLOX algorithm was used to determine the optimal growth stage for developing wheat spike detection models among recombinant inbred lines (RILs) across Zhongmai 175 ​× ​Lunxuan 987 and a diverse panel of 166 cultivars. We subsequently increased the precision of spike identification by developing a new YOLOX-P algorithm that incorporates the convolutional block attention module and increasing the resolution of the input images. We also used these SN data to identify underlying loci in the Zhongmai 578 ​× ​Jimai 22 RIL population. The results revealed that the late grain-filling stage presented the highest precision among the SN detection models, with accuracies ranging from 91.8 to 95.02 ​%. The improved YOLOX-P algorithm demonstrated higher mean average precision scores (5.30-5.99 ​%) and F1 scores (0.06) than did the YOLOX algorithm when it was applied to the same subsets. Three new SN loci, namely, QSN.caas-4A2, QSN.caas-4D and QSN.caas-5B2, were identified using the 50k SNP arrays. Two kompetitive allele-specific PCR markers linked with QSN.caas-4A2 and QSN.caas-5B2 were developed, and their genetic effects were validated in a diverse panel of 166 cultivars. These findings provide useful tools for high-throughput identification of SNs and novel loci in wheat.

Capturing crop physiological information by phenotyping is a key trend in smart agriculture. However, current studies underutilize spatial structural information in phenotypic imaging. To evaluate the feasibility of crop cold stress monitoring based on phenotypic spatial variability, we conducted controlled experiments on 'Toyonoka' strawberry plants under four dynamic cooling gradients and three stress durations and analyzed the dependence of their photosynthetic physiology and phenotypic traits on temperature-time interactions. The results revealed that NPQ/1D-Parallel/TENT, Y(NO)/2D-Region/INEM, and qP/1D-Parallel/TENT presented the highest mutual information, with the maximum net photosynthetic rate (P_max), relative electrolyte conductivity (REC), and total chlorophyll content (Chl_{a ​+ ​b}), respectively. The difference between the Photosynthetic Physiological Potential Index (PPPI) and relative negative accumulated temperature (RNAT)/650 effectively was used to calculate the cold damage risk (CDRI). An XGBoost-based model integrating the PPPI and RNAT outperformed AdaBoost and RandomForest, achieving an R² of 0.98, an RMSE of 0.337, a classification accuracy of 92.13 ​%, and a Kappa coefficient of 0.904. qP/1D-Parallel/TENT contributed the most to the model. This study provides a scientific basis for phenotypic information mining and agro-meteorological disaster monitoring.

Canopy temperature (CT) estimates from drone-based uncooled thermal cameras are prone to confounding effects, which affects the interpretability of CT estimates. Experimental sources of variance, such as genotypes and experimental treatments blend with confounding sources of variance such as thermal drift, spatial field trends, and effects related to viewing geometry. Nevertheless, CT is gaining popularity to characterize crop performance and crop water use, and as a proxy measurement of stomatal conductance and transpiration. Drone-based thermography was therefore proposed to measure CT in agricultural experiments. For a meaningful interpretation of CT, confounding sources of variance must be considered. In this study, the multi-view approach was applied to examine the variance components of CT on 99 flights with a drone-based thermal camera. Flights were conducted on two variety testing field trials of winter wheat over two years with contrasting meteorological conditions in the temperate climate of Switzerland. It was demonstrated how experimental sources of variance can be disentangled from confounding sources of variance and on average more than 96.5 ​% of the initial variance could be explained with experimental and confounding sources combined. Not considering confounding sources led to erroneous conclusions about phenotypic correlations of CT with traits such as yield, plant height, fractional canopy cover, and multispectral indices. Based on extensive and diverse data, this study provides comprehensive insights into the manifold sources of variance in CT measurements, which supports the planning and interpretation of drone-based CT screenings in variety testing, breeding, and research.

High throughput phenotyping for crop monitoring at both leaf and canopy scales is essential for understanding plant responses to various stresses. PhenoGazer, a high-throughput phenotyping system, enhances crop monitoring in controlled environments by integrating a portable hyperspectral spectrometer with eight fiber optics, four Raspberry Pi cameras, and blue LED lights. This system allows for comprehensive assessment of plant health and development. PhenoGazer features automated moveable upper and lower racks for continuous measurements. The lower rack, equipped with four blue LED lights and spectrometer fiber optics, captures blue light-induced chlorophyll fluorescence at night. The upper rack, carrying four spectrometer fiber optics and cameras, captures hyperspectral reflectance and RGB images during the day. This dual capability enables detailed evaluation of plant phenology, stress responses, and growth dynamics throughout the entire crop growth cycle. Fully automated and managed by a Raspberry Pi running Python scripts, PhenoGazer ensures precise control and data acquisition with minimal human intervention. Additionally, it includes continuous measurements through a datalogger to acquire photosynthetically active radiation (PAR), soil moisture and temperature, and features expansion capability for additional analog or digital sensors as desired by end users. To test the system, soybean plants representing three conditions, healthy well watered, healthy droughted, and diseased, were monitored to evaluate growth and stress responses. PhenoGazer successfully phenotyped plants under different conditions in a walk-in growth chamber. By combining nighttime blue light induced chlorophyll fluorescence, hyperspectral reflectance-based vegetation indices, and RGB imagery, PhenoGazer represented a significant advancement in plant phenotyping technology, enhancing our understanding of crop responses to environmental conditions and supporting optimized crop performance in research and agricultural applications.