Accurate estimation of crop yield and biomass using UAV-based remote sensing is influenced by flight altitude, plant density, canopy structure, vegetation index (VI) selection, and crop growth stage. This study evaluated how the joint optimization of these factors influences biomass and yield prediction in common buckwheat (Fagopyrum esculentum Moench var. 'Yangjeol'). Field experiments were conducted using broadcast seeding and drill seeding at four row spacings (12.5, 20, 30, and 40 cm) following the complete Latin square design. UAV RGB imagery was acquired at the third-leaf and full-flowering stages from 30, 50, and 60 m altitudes, and vegetation indices Excess Green Index (ExG), Green Leaf Index (GLI), and Normalized Green-Red Difference Index (NGRDI)were extracted. ANOVA with Tukey's HSD revealed significant variations in biomass and yield traits among sowing treatments (p < 0.005). The highest fresh weight was recorded under drill seeding at 12.5 cm spacing, while seed weight was consistently higher under all drill seeding treatments compared with broadcast seeding. The number of seeds per plant peaked under 40 cm spacing, indicating a trade-off between planting density and reproductive output. Strong and significant correlations between vegetation indices and ground-measured traits were observed (r = 0.82-0.98), but these relationships were highly dependent on growth stage, sowing configuration, and UAV altitude. The third-leaf stage under broadcast seeding and full flowering stage under drill seeding at 20 cm spacing showed the strongest and most consistent VI-trait associations. Among UAV altitudes, 50 m provided the most stable predictive performance across traits. ExG and GLI exhibited more consistent relationships with biomass and yield parameters than NGRDI. These findings demonstrate that no single UAV altitude, vegetation index, or growth stage is universally optimal. Instead, coordinated optimization of UAV operational parameters and sowing configurationsubstantially improves the reliability of UAV-based yield and biomass estimation in buckwheat.
Buckwheat (Fagopyrum spp.) germplasm represents an underutilized source of morphological diversity for crop improvement. This study presents a high-throughput phenomic survey quantifying five seed morphological traits (area, length, width, circularity, roundness) across 563 RDA genebank accessions (519 common buckwheat (F. esculentum), 44 Tartary buckwheat (F. tataricum) using standardized imaging. Common buckwheat exhibits larger seeds (area: 21.12 ± 4.04 mm²) with lower coefficients of variation (CVs: 17.9%), while Tartary buckwheat shows smaller seeds (14.80 ± 3.23 mm²) with higher CVs (20.1%) and greater shape dispersion (PC2 variance: 3.73 vs. 1.06). Principal component analysis confirms species-level morphological separation and documents exploitable polymorphism, including notched/slender/round/rice morphotypes in F. tataricum. These standardized phenotypic baselines support genebank curation, accession ranking by seed size/shape extremes, and prioritization for multi-environment trials and genetic studies.
Abstract Correlative imaging is a powerful tool for revealing information on cell-type structures and their biochemistry, with the potential to inform healthier food choices and improved dietary recommendations. Determination of plant structures and their structural biochemistry advances our understanding of specific structures designed to store different biomolecules within cells and tissues. Compared to the classical biochemical separation techniques, the key advantage of sequential correlative imaging techniques is in relating spatial plant (micro)structures to their biochemistry in a nondestructive manner. Sequential imaging reported here comprises six methodologies on a single sample, a cross-section of a Tartary buckwheat (Fagopyrum tataricum) grain, namely, bright-field and autofluorescence microscopy, fluorescence microspectroscopy, MeV-secondary ion mass spectrometry, micro-particle-induced X-ray emission, scanning electron microscopy coupled with energy dispersive X-ray spectroscopy, and laser ablation-inductively coupled plasma-mass spectrometry. Results confirm that the stepwise addition of the desired information across several classes of biomolecules and several spatial scales informs the quality and safety of plant-based produce across scales. Therefore, a viable workflow is proposed, enabling sequential spatial analysis of grain and highlighting plant structures' in situ specificity. The advantages and disadvantages of the selected methodologies were critically evaluated.
Reproduction assets foundThe paper explicitly points to a public Zenodo deposit containing the correlative imaging data (SEM, micro-PIXE, MeV-SIMS maps) used in its analyses, with instructions for reproducing image fusion in Wolfram Mathematica or ImageJ.Dataset · publicsed to reveal the allocation of K
to cotyledons (Supplementary Fused Image 1). Similarly, on
the same SEM image, MeV-SIMS distribution maps under the
selected peak were overlaid (Supplementary Fused Image 2).
Custom combinations can be done in the Wolfram
Mathematica program or in ImageJ (Merge Channels) using
data available at https://doi.org/10.5281/zenodo.14628251, fol
lowing the instructions in the Materials and Methods.
Conclusions
The low emission properties of fluorescence biomolecules,
when excited with 405 nm light, inherently limit the informa
tion acquired using fluorescence imaging. At this excitation
wavelength, catechin may be the primary fluorophore in
Tartary buckwheat cotOpen asset ↗zenodo · 10.5281/zenodo.14628251pdf-raw-page:13 lines:1-89Plant phenotyping relevance matchEurope PMC · checked 6 Sept 2026
Introduction The optimal harvest period for buckwheat is challenging to determine due to its short growth cycle. Harvesting too early or too late can negatively affect the quality of the crop. Traditional harvest methods are labor-intensive and fail to account for the spatial variability in buckwheat quality within a field. This study explores the use of near-infrared (NIR) spectral data to classify the maturity stages of buckwheat. Method Four distinct developmental stages were examined: UM (Unripe Maturity), representing buckwheat harvested at 65 days after sowing; HM (Half Maturity), harvested at 75 days; MS (Full Maturity with Shell), harvested at 85 days with husks intact; and MUS (Full Maturity Unhulled Sample), also harvested at 85 days but manually dehulled. Unlike traditional machine learning models, which require diverse and extensive datasets, this study investigates the use of a conditional WGAN-GP to generate synthetic datasets and improve model performance. Four machine learning models were employed in this study: Support Vector Machine (SVM), Random Forest (RF), k-Nearest Neighbors (KNN), and Partial Least Squares Linear Discriminant Analysis (PLS-LDA). Results and discussion The conditional WGAN with the gradient penalty was trained for a range of epochs: 1000, 2000, 8000, 10,000, and 20,000. After training 10,000 epochs, synthetic hyperspectral reflectance data were very similar to real spectra for each maturity category. To assess the impact of conditional WGAN-GP data augmentation, model performance was first evaluated using the original dataset as a baseline, showing PLS-LDA had the best classification performance with accuracy of 95% and kappa coefficient of 0.93. The models were then trained on a combination of original and synthetic data, revealing that synthetic data can improve the classification model performance for RF and KNN. The best classification performance was achieved by RF with an accuracy of 97% and kappa coefficient of 0.94. This study demonstrates the effectiveness of synthetic data in enhancing classification accuracy.
Crop identification at the field level using remote sensing data is a very important task. However, the use of multispectral data for the construction of vegetation indices is sometimes impossible or limited. For such situations, solutions based on the use of time series of synthetic aperture radar (SAR) indices are promising, eliminating the problems associated with cloudiness and providing an assessment of crop development characteristics during the growing season. We evaluated the use of time series of synthetic aperture radar (SAR) indices to characterize crop development during the growing season. The use of SAR imagery for crop identification addresses issues related to cloudiness. Therefore, it is important to choose the SAR index that is the most stable and has the lowest spatial variability throughout the growing season while being comparable to the normalized difference vegetation index (NDVI). The presented work is devoted to the study of these issues. In this study, the spatial variabilities of different SAR indices time series were compared for a single region for the first time to identify the most stable index for use in precision agriculture, including the in-field heterogeneity of crop sites, crop rotation control, mapping, and other tasks in various agricultural areas. Seventeen Sentinel-1B images of the southern part of the Khabarovsk Territory in the Russian Far East at a spatial resolution of 20 m and temporal resolution of 12 days for the period between 14 April 2021 and 1 November 2021 were obtained and processed to generate vertical–horizontal/vertical–vertical polarization (VH/VV), radar vegetation index (RVI), and dual polarimetric radar vegetation index (DpRVI) time series. NDVI time series were constructed from multispectral Sentinel-2 images using a cloud cover mask. The characteristics of time series maximums were calculated for different types of crops: soybean, oat, buckwheat, and timothy grass. The DpRVI index exhibited the highest stability, with coefficients of variation of the time series that were significantly lower than those for RVI and VH/VV. The main characteristics of the SAR and NDVI time series—the maximum values, the dates of the maximum values, and the variability of these indices—were compared. The variabilities of the maximum values and dates of maximum values for DpRVI were lower than for RVI and VH/VV, whereas the variabilities of the maximum values and the dates of maximum values were comparable for DpRVI and NDVI. On the basis of the DpRVI index, classifications were carried out using seven machine learning methods (fine tree, quadratic discriminant, Gaussian naïve Bayes, fine k nearest neighbors or KNN, random under-sampling boosting or RUSBoost, random forest, and support vector machine) for experimental sites covering a total area of 1009.8 ha. The quadratic discriminant method yielded the best results, with a pixel classification accuracy of approximately 82% and a kappa value of 0.67. Overall, 90% of soybean, 74.1% of oat, 68.9% of buckwheat, and 57.6% of timothy grass pixels were correctly classified. At the field level, 94% of the fields included in the test dataset were correctly classified. The paper results show that the DpRVI can be used in cases where the NDVI is limited, allowing for the monitoring of phenological development and crop mapping. The research results can be used in the south of Khabarovsk Territory and in neighboring territories.
Tartary buckwheat (TB) starch is a low-glycaemic-index food source. Analysis of genotype-by-environment effects on starch content is needed to improve high-quality TB production. However, an accurate and high-throughput evaluation method for starch content is a bottleneck for the analysis of genotype-by-environment effects on starch content. In the current study, a rapid and non-destructive method for detecting starch was developed based on near-infrared reflectance (NIR) spectroscopy. Overall, 281 varieties were planted in three environments for 2 years and measured. The coefficient of correlation between the laboratory-determined and NIR model-predicted starch content values was 0.9577. The average starch content of TB varieties had higher variants among the three environments. The genotype-by-environment interaction analysis showed the significant impact of environmental factors on TB starch content. Of them, two varieties (Ft155 and Ft184) with stable and relatively high starch contents (733.43 and 689.16 mg/g) were identified. The amylose content, structure character, thermal properties and pasting character revealed that these physicochemical properties of TB starch were distinct from those of potato and rice. Moreover, Ft155 was more difficult to gelatinise, and Ft184 has desired high-starch-quality cooking properties. These assessments provide robust nutritional quality evaluation approaches and food processing materials.
Buckwheat plant height is an important indicator for producers. Due to the decline in agricultural labor, the automatic and real-time acquisition of crop growth information will become a prominent issue for farms in the future. To address this problem, we focused on stereo vision and a regression convolutional neural network (CNN) in order to estimate buckwheat plant height. MobileNet V3 Small, NasNet Mobile, RegNet Y002, EfficientNet V2 B0, MobileNet V3 Large, NasNet Large, RegNet Y008, and EfficientNet V2 L were modified into regression CNNs. Through a five-fold cross-validation of the modeling data, the modified RegNet Y008 was selected as the optimal estimation model. Based on the depth and contour information of buckwheat depth image, the mean absolute error (MAE), root mean square error (RMSE), mean square error (MSE), and mean relative error (MRE) when estimating plant height were 0.56 cm, 0.73 cm, 0.54 cm, and 1.7%, respectively. The coefficient of determination (R2) value between the estimated and measured results was 0.9994. Combined with the LabVIEW software development platform, this method can estimate buckwheat accurately, quickly, and automatically. This work contributes to the automatic management of farms.
Reproduction assets foundThe paper's buckwheat height estimation model code (modified regression CNNs with training results) is publicly available via an authors' GitHub repository explicitly stated in the text. The phenotype dataset (depth images with height labels) is only available by contacting the authors, so it is not a public asset.Code · publicndows 11 (64 bit), and an
Nvidia GeForce RTX 3090 24 GB graphics card with Nvidia Ampere architecture. All of
the models used the processed grayscale images of 224 × 224 pixels as the input and the
estimated buckwheat height as the output. The codes of the models with training results
are available at the following GitHub link: https://github.com/18801389568/Buckwheat-height-estimation (accessed on 26 July 2023).
Figure 5. Construction method of the buckwheat crop height estimation models.
Training the models was essentially a process of continually updating the trainable
parameters of each model in order to make the crop height estimation results increasingly
accurate. Considering the quantOpen asset ↗18801389568/Buckwheat-height-estimationpdf-raw-page:6 lines:1-60Plant phenotyping relevance matchOpenAlex · Europe PMC · checked 7 Sept 2026
Ju‐Kyung Yu · Sungyul Chang · Gyung Deok Han · Seong‐Hoon Kim · Jinhyun Ahn · Jieun Park · Yoon-Ha Kim · Jaeyoung Kim · Yong Suk Chung
BuckwheatMorphology / geometry measurement
The beauty of conserving germplasm is the securement of genetic resources with numerous important traits, which could be utilized whenever they need to be incorporated into current cultivars. However, it would not be as useful as expected if the proper information was not given to breeders and researchers. In this study, we demonstrated that there is a large variation, both among and within germplasm, using a low-cost image-based phenotyping method; this could be valuable for improving gene banks' screening systems and for crop breeding. Using the image analyses of 507 accessions of buckwheat, we identified a wide range of variations per trait between germplasm accessions and within an accession. Since this implies a similarity with other important agronomic traits, we suggest that the variance of the presented traits should be checked and provided for better germplasm enhancement.
Buckwheat is an important minor grain crop with medicinal and edible functions. The accurate judgment of buckwheat maturity is beneficial to reduce harvest losses and improve yield. With the rapid development of unmanned aerial vehicle (UAV) technology, it has been widely used to predict the maturity of agricultural products. This paper proposed a method using recursive feature elimination cross-validation (RFECV) combined with multiple regression models to predict the maturity of buckwheat in UAV-RGB images. The images were captured in the buckwheat experimental field of Shanxi Agricultural University in Jinzhong, Northern China, from September to October in 2021. The variety was sweet buckwheat of "Jinqiao No. 1". In order to deeply mine the feature vectors that highly correlated with the prediction of buckwheat maturity, 22 dimensional features with 5 vegetation indexes, 9 color features, and 8 texture features of buckwheat were selected initially. The RFECV method was adopted to obtain the optimal feature vector dimensions and combinations with six regression models of decision tree regression, linear regression, random forest regression, AdaBoost regression, gradient lifting regression, and extreme random tree regression. The coefficient of determination (R2) and root mean square error (RMSE) were used to analyze the different combinations of the six regression models with different feature spaces. The experimental results show that the single vegetation index performed poorly in the prediction of buckwheat maturity; the prediction result of feature space "5" combined with the gradient lifting regression model performed the best; and the R2 and RMSE were 0.981 and 1.70 respectively. The research results can provide an important theoretical basis for the prediction of the regional maturity of crops.
Buckwheat is an important cereal crop with high nutritional and health value. Buckwheat disease greatly affects the quality and yield of buckwheat. The real-time monitoring of disease is an essential part of ensuring the development of the buckwheat industry. In this research work, we proposed an automated way to identify buckwheat diseases. It was achieved by integrating a convolutional neural network (CNN) with the image processing technology. Firstly, the proposed approach would detect the buckwheat disease area accurately. Then, to improve the accuracy of classification, a two-level inception structure was added to the traditional convolutional neural network for accurate feature extraction. It also helps to handle low-quality image problems, which includes complex imaging environment and leaf crossing in sampling buckwheat image, etc. At the same time, instead of the traditional convolution, the convolution based on cosine similarity was adopted to reduce the influence of uneven illumination during the imaging. The experiment proved that the revised convolution enabled better feature extraction within samples with uneven illumination. Finally, the experiment results showed that the accuracy, recall, and F1-measure of the disease detection reached 97.54, 96.38, and 97.82%, respectively. For identifying disease categories, the mean values of precision, recall, and F1-measure were 84.86, 85.78, and 85.4%. Our method has provided important technical support for realizing the automatic recognition of buckwheat diseases.
Abstract The beauty of conserving germplasm is the securement of genetic resources with numerous important traits, which could be utilized whenever they need to be incorporated into current cultivars. However, it would not be as useful as expected if the proper information was not given to breeders and researchers. In this study, we demonstrated that there is a large variation, both among and within germplasm, using a low-cost image-based phenotyping method; this could be valuable for improving gene banks’ screening systems and for crop breeding. Using the image analyses of 507 accessions of buckwheat, we identified a wide range of variations per trait between germplasm accessions and within an accession. Since this implies a similarity with other important agronomic traits, we suggest that the variance of the presented traits should be checked and provided for better germplasm enhancement.
Koyama T, Murakami S, Karasawa T, Ejiri M, Shiono K.
BuckwheatSoybeanRootMorphology / geometry measurementRoot system architecture
Background Detailed datasets containing root system and its architecture in soil are required to improve understanding of resource capture by roots. However, most of the root study methods have paid little attention to make and preserve whole root specimens. This study introduces root system sampling equipment that makes the entire root specimen with minimum impairment and without displacement of the spatial arrangement of the root system in root boxes. The objectives are to assess: whether the equipment can rapidly sample the entire root system; whether root surface area is measurable from a scanned digital image of the root specimen; and whether staining of the entire root specimens would provide multidimensional visual information on the interaction between soil and physiological function of root system architecture (RSA). For validation, we examined the root response of two soybean cultivars to arbuscular mycorrhizal (AM) inoculation and the effect of waterlogging stress on the physiological activity of buckwheat RSA. Results The root boxes allowed soybean and buckwheat plants to grow uniformly across the replications. Both species showed significant differences between cultivars and/or among treatments in shoot and root traits. The equipment enabled to sample the whole-root specimens of soybean and buckwheat, where the tips of the fine roots were alive (diameter Conclusions The present method realized: fast and accurate production of the whole root specimen and precise calculation of the specimens' root surface area. Moreover, staining of the root specimens enabled analyzing the interaction between soil and physiological function of RSA. The evaluation of root traits, using our methods, will contribute to developing agronomic management and breeding program for sustainable food production.
Cosegmentation is a newly emerging computer vision technique used to segment an object from the background by processing multiple images at the same time. Traditional plant phenotyping analysis uses thresholding segmentation methods which result in high segmentation accuracy. Although there are proposed machine learning and deep learning algorithms for plant segmentation, predictions rely on the specific features being present in the training set. The need for a multi-featured dataset and analytics for cosegmentation becomes critical to better understand and predict plants' responses to the environment. High-throughput phenotyping produces an abundance of data that can be leveraged to improve segmentation accuracy and plant phenotyping. This paper introduces four datasets consisting of two plant species, Buckwheat and Sunflower, each split into control and drought conditions. Each dataset has three modalities (Fluorescence, Infrared, and Visible) with 7 to 14 temporal images that are collected in a high-throughput facility at the University of Nebraska-Lincoln. The four datasets (which will be collected under the CosegPP data repository in this paper) are evaluated using three cosegmentation algorithms: Markov random fields-based, Clustering-based, and Deep learning-based cosegmentation, and one commonly used segmentation approach in plant phenotyping. The integration of CosegPP with advanced cosegmentation methods will be the latest benchmark in comparing segmentation accuracy and finding areas of improvement for cosegmentation methodology.
Reproduction assets foundThe paper's CosegPP plant image dataset (Buckwheat/Sunflower, multi-modal, with ground-truth masks) is publicly deposited on Zenodo per the Data Availability statement. The GitHub repos mentioned (MIG, Subdiscover, DeepCO3) are cited third-party prior-work code, not authors' paper-specific analysis code.Dataset · publicData Availability: All relevant data underlying this study are available at https://doi.org/10.5281/zenodo.5117176 .Open asset ↗zenodo · 10.5281/zenodo.5117176lines:138-150