基于数字化植物表型平台(D3P)的田间小麦冠层光截获算法开发

冠层光截获能力是反映作物品种间差异的重要功能性状,高通量表型冠层光截获对提高作物改良效率具有重要意义。本研究以小麦为研究目标,利用数字化植物表型平台(D3P)模拟生成了100种冠层结构不同的小麦品种在5个生育期的三维冠层场景,记录了从原始冠层结构中提取的绿色叶面积指数(GAI)、平均倾角(AIA)和散射光截获率(FIPAR_(dif))信息作为真实值,进一步利用上述三维小麦场景开展了虚拟的激光雷达(LiDAR)模拟实验,生成了对应的三维点云数据。基于模拟的点云数据提取了其高度分位数特征(H)和绿色分数特征(GF)。最后,利用人工神经网络(ANN)算法分别构建了从不同LiDAR点云特征(H、GF和H+GF)输入到FIPAR_(dif)、GAI和AIA的反演模型。结果表明,对于GAI、AIA和FIPAR_(dif),预测精度从高到低对应的点云特征输入为GF+H> H> GF。由此可见,H特征对提高目标表型特性的估算精度起到了重要作用。输入GF+H特征,在中等测量噪音(10%)情况下,FIPAR_(dif)和GAI的估算均获得了满意精度,R^2分别为0.95和0.98,而AIA的估算精度(R^2=0.20)还有待进一步提升。本研究基于D3P模拟数据开展,算法的实际表现还有待通过田间数据进一步验证。尽管如此,本研究验证了D3P协助表型算法开发的能力,展示了高通量LiDAR数据在估算田间冠层光截获和冠层结构方面的较高潜力。

Global Wheat Head Detection 2021:An Improved Dataset for Benchmarking Wheat Head Detection Methods

The Global Wheat Head Detection(GWHD)dataset was created in 2020 and has assembled 193,634 labelled wheat heads from 4700 RGB images acquired from various acquisition platforms and 7 countries/institutions.With an associated competition hosted in Kaggle,GWHD_2020 has successfully attracted attention from both the computer vision and agricultural science communities.From this first experience,a few avenues for improvements have been identified regarding data size,head diversity,and label reliability.To address these issues,the 2020 dataset has been reexamined,relabeled,and complemented by adding 1722 images from 5 additional countries,allowing for 81,553 additional wheat heads.We now release in 2021 a new version of the Global Wheat Head Detection dataset,which is bigger,more diverse,and less noisy than the GWHD_2020 version.

Global Wheat Head Detection(GWHD)Dataset:A Large and Diverse Dataset of High-Resolution RGB-Labelled Images to Develop and Benchmark Wheat Head Detection Methods

The detection of wheat heads in plant images is an important task for estimating pertinent wheat traits including head population density and head characteristics such as health,size,maturity stage,and the presence of awns.Several studies have developed methods for wheat head detection from high-resolution RGB imagery based on machine learning algorithms.However,these methods have generally been calibrated and validated on limited datasets.High variability in observational conditions,genotypic differences,development stages,and head orientation makes wheat head detection a challenge for computer vision.Further,possible blurring due to motion or wind and overlap between heads for dense populations make this task even more complex.Through a joint international collaborative effort,we have built a large,diverse,and well-labelled dataset of wheat images,called the Global Wheat Head Detection(GWHD)dataset.It contains 4700 high-resolution RGB images and 190000 labelled wheat heads collected from several countries around the world at different growth stages with a wide range of genotypes.Guidelines for image acquisition,associating minimum metadata to respect FAIR principles,and consistent head labelling methods are proposed when developing new head detection datasets.The GWHD dataset is publicly available at http://www.global-wheat.com/and aimed at developing and benchmarking methods for wheat head detection.

Self-Supervised Plant Phenotyping by Combining Domain Adaptation with 3D Plant Model Simulations: Application to Wheat Leaf Counting at Seedling Stage

The number of leaves at a given time is important to characterize plant growth and development.In this work,we developed a high-throughput method to count the number of leaves by detecting leaf tips in RGB images.The digital plant phenotyping platform was used to simulate a large and diverse dataset of RGB images and corresponding leaf tip labels of wheat plants at seedling stages(150,000 images with over 2 million labels).The realism of the images was then improved using domain adaptation methods before training deep learning models.The results demonstrate the efficiency of the proposed method evaluated on a diverse test dataset,collecting measurements from 5 countries obtained under different environments,growth stages,and lighting conditions with different cameras(450 images with over 2,162 labels).Among the 6 combinations of deep learning models and domain adaptation techniques,the Faster-RCNN model with cycle-consistent generative adversarial network adaptation technique provided the best performance(R^(2)=0.94,root mean square error=8.7).Complementary studies show that it is essential to simulate images with sufficient realism(background,leaf texture,and lighting conditions)before applying domain adaptation techniques.Furthermore,the spatial resolution should be better than 0.6 mm per pixel to identify leaf tips.The method is claimed to be self-supervised since no manual labeling is required for model training.The self-supervised phenotyping approach developed here offers great potential for addressing a wide range of plant phenotyping problems.The trained networks are available at https://github.com/YinglunLi/Wheat-leaf-tip-detection.

Identification of sap flow driving factors of jujube plantation in semi-arid areas in Northwest China

Jujube is widely cultivated in the semi-arid region of the Loess Plateau in Northwest China due to its high water deficit tolerance.In such an ecologically vulnerable area,it is critical to explore the water consumption processes of key tree species and their responses to driving factors.Sap flow data gathered during a two-year field study in a jujube plantation were analyzed as a surrogate for transpiration measurements.The measured sap flows were related to changes in the soil water content,meteorological factors(the vapor pressure deficit and the level of photosynthetically active radiation),and plant physiological factors(the sap wood area,leaf area and leaf area index).The factors that govern sap flow were found to vary depending on the growing season,and on hourly and daily timescales.The plants’drought tolerance could be predicted based on their peak sap flows and the variation in their sap flow rates at different soil water levels.The sap flow was most strongly affected by the water content of the topmost(0-20 cm)soil layer.Of the studied meteorological factors,the photosynthetically active radiation had a greater effect on sap flow than the vapor pressure deficit.The correlation we found could be applied to predict jujube tree water consumption and assist the design of irrigation scheme.

A Novel Feature Selection Strategy Based on Salp Swarm Algorithm for Plant Disease Detection

Deep learning has been widely used for plant disease recognition in smart agriculture and has proven to be a powerful tool for image classification and pattern recognition.However,it has limited interpretability for deep features.With the transfer of expert knowledge,handcrafted features provide a new way for personalized diagnosis of plant diseases.However,irrelevant and redundant features lead to high dimensionality.In this study,we proposed a swarm intelligence algorithm for feature selection[salp swarm algorithm for feature selection(SSAFS)]in image-based plant disease detection.SSAFS is employed to determine the ideal combination of handcrafted features to maximize classification success while minimizing the number of features.To verify the effectiveness of the developed SSAFS algorithm,we conducted experimental studies using SSAFS and 5 metaheuristic algorithms.Several evaluation metrics were used to evaluate and analyze the performance of these methods on 4 datasets from the UCI machine learning repository and 6 plant phenomics datasets from PlantVillage.Experimental results and statistical analyses validated the outstanding performance of SSAFS compared to existing state-of-the-art algorithms,confirming the superiority of SSAFS in exploring the feature space and identifying the most valuable features for diseased plant image classification.This computational tool will allow us to explore an optimal combination of handcrafted features to improve plant disease recognition accuracy and processing time.

Bio-Master:Design and Validation of a High-Throughput Biochemical Profiling Platform for Crop Canopies

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.