Plant Phenomics最新文献

Inefficient nitrogen (N) utilization in agricultural production has led to many negative impacts such as excessive use of N fertilizers, redundant plant growth, greenhouse gases, long-lasting toxicity in ecosystem, and even effect on human health, indicating the importance to optimize N applications in cropping systems. Here, we present a multiseasonal study that focused on measuring phenotypic changes in wheat plants when they were responding to different N treatments under field conditions. Powered by drone-based aerial phenotyping and the AirMeasurer platform, we first quantified 6 N response-related traits as targets using plot-based morphological, spectral, and textural signals collected from 54 winter wheat varieties. Then, we developed dynamic phenotypic analysis using curve fitting to establish profile curves of the traits during the season, which enabled us to compute static phenotypes at key growth stages and dynamic phenotypes (i.e., phenotypic changes) during N response. After that, we combine 12 yield production and N-utilization indices manually measured to produce N efficiency comprehensive scores (NECS), based on which we classified the varieties into 4 N responsiveness (i.e., N-dependent yield increase) groups. The NECS ranking facilitated us to establish a tailored machine learning model for N responsiveness-related varietal classification just using N-response phenotypes with high accuracies. Finally, we employed the Wheat55K SNP Array to map single-nucleotide polymorphisms using N response-related static and dynamic phenotypes, helping us explore genetic components underlying N responsiveness in wheat. In summary, we believe that our work demonstrates valuable advances in N response-related plant research, which could have major implications for improving N sustainability in wheat breeding and production.

Root system architecture (RSA) is an important measure of how plants navigate and interact with the soil environment. However, current methods in studying RSA must make tradeoffs between precision of data and proximity to natural conditions, with root growth in germination papers providing accessibility and high data resolution. Functional-structural plant models (FSPMs) can overcome this tradeoff, though parameterization and evaluation of FSPMs are traditionally based in manual measurements and visual comparison. Here, we applied a germination paper system to study the adventitious RSA and root phenology of Populus trichocarpa stem cuttings using time-series image-based phenotyping augmented by FSPM. We found a significant correlation between timing of root initiation and thermal time at cutting collection (P value = 0.0061, R² = 0.875), but little correlation with RSA. We also present a use of RhizoVision [1] for automatically extracting FSPM parameters from time series images and evaluating FSPM simulations. A high accuracy of the parameterization was achieved in predicting 2D growth with a sensitivity rate of 83.5%. This accuracy was lost when predicting 3D growth with sensitivity rates of 38.5% to 48.7%, while overall accuracy varied with phenotyping methods. Despite this loss in accuracy, the new method is amenable to high throughput FSPM parameterization and bridges the gap between advances in time-series phenotyping and FSPMs.

Pine wilt disease (PWD) is a significantly destructive forest disease. To control the spread of PWD, an urgent need exists for a real-time and efficient method to detect infected trees. However, existing object detection models have often faced challenges in balancing lightweight design and accuracy, particularly in complex mixed forests. To address this, an improvement was made to the YOLOv5s (You Only Look Once version 5s) algorithm, resulting in a real-time and efficient model named PWD-YOLO. First, a lightweight backbone was constructed, composed of multiple connected RepVGG Blocks, significantly enhancing the model's inference speed. Second, a C2fCA module was designed to incorporate rich gradient information flow and concentrate on key features, thereby preserving more detailed characteristics of PWD-infected trees. In addition, the GSConv network was utilized instead of conventional convolutions to reduce network complexity. Last, the Bidirectional Feature Pyramid Network strategy was used to enhance the propagation and sharing of multiscale features. The results demonstrate that on a self-built dataset, PWD-YOLO surpasses existing object detection models with respective measurements of model size (2.7 MB), computational complexity (3.5 GFLOPs), parameter volume (1.09 MB), and speed (98.0 frames/s). The Precision, Recall, and F1-score on the test set are 92.5%, 95.3%, and 93.9%, respectively, which confirms the effectiveness of the proposed method. It provides reliable technical support for daily monitoring and clearing of infected trees by forestry management departments.

Salt stress is considered one of the primary threats to cotton production. Although cotton is found to have reasonable salt tolerance, it is sensitive to salt stress during the seedling stage. This research aimed to propose an effective method for rapidly detecting salt stress of cotton seedlings using multicolor fluorescence-multispectral reflectance imaging coupled with deep learning. A prototyping platform that can obtain multicolor fluorescence and multispectral reflectance images synchronously was developed to get different characteristics of each cotton seedling. The experiments revealed that salt stress harmed cotton seedlings with an increase in malondialdehyde and a decrease in chlorophyll content, superoxide dismutase, and catalase after 17 days of salt stress. The Relief algorithm and principal component analysis were introduced to reduce data dimension with the first 9 principal component images (PC1 to PC9) accounting for 95.2% of the original variations. An optimized EfficientNet-B2 (EfficientNet-OB2), purposely used for a fixed resource budget, was established to detect salt stress by optimizing a proportional number of convolution kernels assigned to the first convolution according to the corresponding contributions of PC1 to PC9 images. EfficientNet-OB2 achieved an accuracy of 84.80%, 91.18%, and 95.10% for 5, 10, and 17 days of salt stress, respectively, which outperformed EfficientNet-B2 and EfficientNet-OB4 with higher training speed and fewer parameters. The results demonstrate the potential of combining multicolor fluorescence-multispectral reflectance imaging with the deep learning model EfficientNet-OB2 for salt stress detection of cotton at the seedling stage, which can be further deployed in mobile platforms for high-throughput screening in the field.

Accurate assessment of crop biochemical profiles plays a crucial role in diagnosing their physiological status. The conventional destructive methods, although reliable, demand extensive laboratory work for measuring various traits. On the other hand, nondestructive techniques, while efficient and adaptable, often suffer from reduced precision due to the intricate interplay of the field environment and canopy structure. Striking a delicate balance between efficiency and accuracy, we have developed the Bio-Master phenotyping system. This system is capable of simultaneously measuring four vital biochemical components of the canopy profile: dry matter, water, chlorophyll, and nitrogen content. Bio-Master initiates the process by addressing structural influences, through segmenting the fresh plant and then further chopping the segment into uniform small pieces. Subsequently, the system quantifies hyperspectral reflectance and fresh weight over the sample within a controlled dark chamber, utilizing an independent light source. The final step involves employing an embedded estimation model to provide synchronous estimates for the four biochemical components of the measured sample. In this study, we established a comprehensive training dataset encompassing a wide range of rice varieties, nitrogen levels, and growth stages. Gaussian process regression model was used to estimate biochemical contents utilizing reflectance data obtained by Bio-Master. Leave-one-out validation revealed the model's capacity to accurately estimate these contents at both leaf and plant scales. With Bio-Master, measuring a single rice plant takes approximately only 5 min, yielding around 10 values for each of the four biochemical components across the vertical profile. Furthermore, the Bio-Master system allows for immediate measurements near the field, mitigating potential alterations in plant status during transportation and processing. As a result, our measurements are more likely to faithfully represent in situ values. To summarize, the Bio-Master phenotyping system offers an efficient tool for comprehensive crop biochemical profiling. It harnesses the benefits of remote sensing techniques, providing significantly greater efficiency than conventional destructive methods while maintaining superior accuracy when compared to nondestructive approaches.

Accurate segmentation and detection of rice seedlings is essential for precision agriculture and high-yield cultivation. However, current methods suffer from high computational complexity and poor robustness to different rice varieties and densities. This article proposes 2 lightweight neural network architectures, LW-Segnet and LW-Unet, for high-precision rice seedling segmentation. The networks adopt an encoder-decoder structure with hybrid lightweight convolutions and spatial pyramid dilated convolutions, achieving accurate segmentation while reducing model parameters. Multispectral imagery acquired by unmanned aerial vehicle (UAV) was used to train and test the models covering 3 rice varieties and different planting densities. Experimental results demonstrate that the proposed LW-Segnet and LW-Unet models achieve higher F1-scores and intersection over union values for seedling detection and row segmentation across varieties, indicating improved segmentation accuracy. Furthermore, the models exhibit stable performance when handling different varieties and densities, showing strong robustness. In terms of efficiency, the networks have lower graphics processing unit memory usage, complexity, and parameters but faster inference speeds, reflecting higher computational efficiency. In particular, the fast speed of LW-Unet indicates potential for real-time applications. The study presents lightweight yet effective neural network architectures for agricultural tasks. By handling multiple rice varieties and densities with high accuracy, efficiency, and robustness, the models show promise for use in edge devices and UAVs to assist precision farming and crop management. The findings provide valuable insights into designing lightweight deep learning models to tackle complex agricultural problems.