Plant Phenomics studies the phenotypic dynamics that form plant phenotypes by systematically measuring traits using phenotyping methods from the quantum to the ecosystem levels. It has emerged as an interdisciplinary field advancing sensing, computation, and plant biology. However, Plant Phenomics has lacked a unifying framework that integrates its community’s core concepts from the formal and life sciences. Central to this framework is the definition of the phenome as a set of phenes that govern phenotypic dynamics across all spatial and temporal scales of biological and ecological organization and in interaction with the environment. This paradigm moves beyond gene-centric views and recognizes the equal importance of all spatial and temporal scales in forming plant phenotypes, advancing Plant Phenomics as a data-driven discipline and its emerging profession, the plant phenomicist.

Chocolate spot (CS), caused by Botrytis fabae, is one of the most destructive fungal diseases affecting faba bean (Vicia faba L.) globally. This study evaluated 33 faba bean cultivars across two locations and over 2 years to assess genetic resistance and the effect of fungicide application on CS progression. The utility of unmanned aerial vehicle-mounted multispectral camera for disease monitoring was examined. Significant variability was observed in cultivar susceptibility, with Bolivia exhibiting the highest level of resistance and Louhi, Sampo, Vire, Merlin, Mistral, and GL Sunrise proving highly susceptible. Fungicide application significantly reduced CS severity and improved yield. Analysis of canopy spectral signatures revealed the near-infrared and red edge bands, along with enhanced vegetation index (EVI) and soil adjusted vegetation index, as most sensitive to CS infection, and they had a strong negative correlation with CS severity ranging from -0.51 to -0.71. In addition, EVI enabled early disease detection in the field. Support vector machine accurately classified CS severity into four classes (resistant, moderately resistant, moderately susceptible, and susceptible) based on spectral data with higher accuracy after the onset of disease compared to later in the season (accuracy 0.75-0.90). This research underscores the value of integrating resistant germplasm, sound agronomic practices, and spectral monitoring for effectively identification and managing CS disease in faba bean.

Unmanned aerial vehicles (UAVs) equipped with high-resolution imaging sensors have shown great potential for plant phenotyping in agricultural research. This study aimed to explore the potential of UAV-derived red–green–blue (RGB) and multispectral imaging data for estimating classical phenotyping measures such as plant height and predicting yield and chlorophyll content (indicated by SPAD values) in a field trial of 38 faba bean ( Vicia faba L.) cultivars grown at four replicates in south-eastern Norway. To predict yield and SPAD values, Support Vector Regression (SVR) and Random Forest (RF) models were utilized. Two feature selection methods, namely the Pearson correlation coefficient (PCC) and sequential forward feature selection (SFS), were applied to identify the most relevant features for prediction. The models incorporated various combinations of multispectral bands, indices, and UAV-based plant height values at four different faba bean development stages. The correlation between manual and UAV-based plant height measurements revealed a strong agreement with a correlation coefficient (R 2 ) of 0.97. The best prediction of SPAD value was achieved at BBCH 50 (flower bud present) with an R 2 of 0.38 and RMSE of 1.14. For yield prediction, BBCH 60 (first flower open) was identified as the optimal stage, using spectral indices yielding an R 2 of 0.83 and RMSE of 0.53 tons/ha. This development stage presents an opportunity to implement targeted management practices to enhance yield. The integration of UAVs equipped with RGB and multispectral cameras, along with machine learning algorithms, proved to be an accurate approach for estimating agronomically important traits in faba bean. This methodology offers a practical solution for rapid and efficient high-throughput phenotyping in faba bean breeding programs.

ABSTRACTThis study evaluated 22 spring‐type faba bean cultivars in the main areas for cultivation of faba bean in Norway to assess the variation of 14 faba bean traits due to cultivar (G), environment (E), and their interaction (G × E), and to assess their stability across environments by using the additive main effects and multiplicative interaction (AMMI) analysis and coefficient of variation (CV). Significant G, E, and G × E effects were found for most traits, with environment accounting for much of the variance in yield and the growing degree days (GDD) to different developmental stages. Yield was highly correlated with thousand kernel weight (TKW) and GDD to BBCH 89 (maturation). The stability of the cultivars was studied for yield, TKW, and GDD to BBCH 89. Stability analysis using the AMMI stability value, yield stability index, CV, and the average sum of ranks identified Birgit, Stella, Bobas, and Macho as the most stable high‐yielding cultivars across environments, achieving a mean yield of 6–6.4 tons ha−1. Bobas, Macho, Stella, and Yukon had the most stable TKW (612–699 g) and Bobas, Capri, Trumpet, and Vertigo were the most stable regarding GDD to BBCH 89 (1257°C days, with a base temperature of 5°C). These stable cultivars can be utilized in breeding programs to achieve high and stable faba bean yield in the main growing areas of Norway and other Nordic‐Baltic countries.

With abundant available genomic data, genomic selection has become routine in many plant breeding programs. Multispectral data captured by UAVs showed potential for grain yield (GY) prediction in many plant species using machine learning; however, the possibilities of utilizing this data to augment genomic prediction models still need to be explored. We collected high-throughput phenotyping (HTP) multispectral data in a genotyped multi-environment large-scale field trial using two cost-effective cameras to fill this gap. We tested back to back the prediction ability of GY prediction models, including genomic (G matrix), multispectral-derived (M matrix), and environmental (E matrix) relationships using best linear unbiased predictor (BLUP) methodology in single and multi-environment scenarios. We discovered that M allows for GY prediction comparable to the G matrix and that models using both G and M matrices show superior accuracies and errors compared with G or M alone, both in single and multi-environment scenarios. We showed that the M matrix is not entirely environment-specific, and the genotypic relationships become more robust with more data capture sessions over the season. We discovered that the optimal time for data capture occurs during grain filling and that camera bands with the highest heritability are important for GY prediction using the M matrix. We showcased that GY prediction can be performed using only an RGB camera, and even a single data capture session can yield valuable data for GY prediction. This study contributes to a better understanding of multispectral data and its relationships. It provides a flexible framework for improving GS protocols without significant investments or software customization.

Abstract This study assesses strategies for utilizing multispectral imaging data (from flowering to maturity) to predict late‐season traits in the Norwegian wheat breeding program, comparing them with genomic prediction (GP). In the phenomic prediction (PP) approach, spectral bands, their multispectral relationship matrix (M‐matrix), and vegetation indices (VIs) were considered. GP involved the genomic relationship matrix (G), extended to multi‐kernel predictors by incorporating environmental and genotype–environment interaction effects, complemented with multispectral reflectance data. Two different models including PLSR (partial least square regression) and Bayesian genomic best linear unbiased prediction regressor were applied. The phenological stage of spectral data collection impacted the trait prediction accuracy correlating with the relationship between multispectral data and measured traits. Higher correlations resulted in higher PP prediction accuracy. The results revealed that spectral bands and M‐matrix outperformed VIs by 10%–40% across different timepoints and all timepoints together for grain yield (GY) prediction. The single‐kernel GP model (G) outperformed PP by 28% (using Bayesian) and 29% (using PLSR). The integration of multi‐kernel GP models with spectral data improved GY prediction by up to 4%. In terms of days to maturity (DM) prediction, phenomic methods excelled, surpassing the single‐kernel GP (G: r = 0.63) model by 11% (Bayesian). In conclusion, this study underscores the effectiveness of phenomics prediction for traits like DM and its potential to enhance predictions for complex traits such as GY while highlighting the importance of correlation between measured traits and spectral data, kernel combinations, and model selection for prediction accuracy.

Wheat ( Triticum aestivum L.) has become the most widely grown cereal crop in the Nordic-Baltic region, however, due to climate change its yields are under increasing risk. Here we present results of international effort harnessing available wheat germplasm in the region for identification of tools and genotypes for breeding wheat varieties with improved yield stability. We formed a panel comprising 300 spring wheat genotypes from Nordic-Baltic region and studied their phenotypic diversity across different environments to identify genotypes with high potential for adaptation to changing climate. Field experiments were carried out in 2021 and 2022 in Estonia, Latvia, Lithuania and Norway. The performance and stability of yield (GY), protein content (PC), thousand kernel weight (TKW), test weight (TW), length of growing period (GP), and nine other traits – were studied. Drought and excessive rainfall occurred in the Baltic countries in 2021–2022, whereas weather was more stable in Norway. High variability for most, and significant GxE effect for all the studied traits was identified. We found out genotypes combining yield and quality with stability using the AMMI model-based Weighted Average of Absolute Scores index (WAASB). Finally, we selected nineteen superior genotypes that combined high yield with high values of important quality traits. Thus, combining broad Nordic-Baltic wheat germplasm with extensive field phenotyping, we identified promising breeding material to develop climate ready spring wheat varieties for the region.

Accurate and robust methods are needed to monitor crop growth and predict grain yield and quality in breeding programs, particularly under variable agrometeorological conditions. Field experiments were conducted during two successive cropping seasons (2021, 2022) at four trial locations (Estonia, Latvia, Lithuania, Norway). The focus was on assessment of the grain yield (GY), grain protein content (GPC), and UAV-derived NDVI measured at different plant growth stages. The performance and stability of 16 selected spring wheat genotypes were assessed under two N application rates (75, 150 kg N ha−1) and across different agrometeorological conditions. Quantitative relationships between agronomic traits and UAV-derived variables were determined. None of the traits exhibited a significant (p < 0.05) genotype-by-nitrogen interaction. High-yielding and high-protein genotypes were detected with a high WAASB stability, specifically under high and low N rates. This study highlights the significant effect of an NDVI analysis at GS55 and GS75 as key linear predictors, especially concerning spring wheat GYs. However, the effectiveness of these indices depends on the specific growing conditions in different, geospatially distant locations, limiting their universal utility.

Quantitative trait prediction using multispectral UAV imagery is gaining popularity in field trials. However, the reliability of models is influenced by the type of camera and its consistency under different light conditions. In this study, we investigate the comparability of two popular multispectral cameras, the Phantom 4 Multispectral (P4M) and the Micasense RedEdge-M (RedEdge-M), for wheat yield and biomass prediction under varying sun angles and phenological changes. Our results indicate that the P4M camera produces more stable values for wavelength bands and derived vegetation indices (VIs) than the RedEdge-M camera under different sun angles. However, the Green Normalized Difference Vegetation Index (GNDVI) showed minimal anisotropic reflectance effect and was consistently correlated with yield, regardless of the camera type. Both cameras were found suitable for yield and biomass prediction, with P4M being more robust against sun angle and providing more stable results. The maximum R2 values for yield were 0.71 and 0.68 in season 2020, and 0.66 and 0.64 in season 2021 for RedEdge-M and P4M, respectively. For biomass prediction, the maximum R2 values were 0.73 and 0.71 for dry biomass and 0.62 and 0.57 for fresh biomass for RedEdge-M and P4M, respectively. These findings have implications for researchers and practitioners using multispectral UAV imagery for quantitative trait prediction in field trials.

Dried figs are a garden produce that must be graded after harvesting. Moisture levels and contaminated blank are two of the most critical effective elements on the marketability of dried figs, and they are highly related to fig quality. In the present research, an intelligent system was employed to classify dried figs based on moisture content levels and infected blank fruits. Capacitance characteristics, average diameter, and fruit area were all taken into account in this study. The dried fig dielectric constant was measured at six different frequency levels: 12, 22, 32, 42, 52, and 62 MHz. The best frequency was then chosen using the improved distance evaluation feature selection approach. Image processing was also used to determine the average diameter and area of the figures. Following that, the dielectric constant of the most effective frequency, the average diameter, and the area of the fruit were used as input parameters in the artificial neural network classification model to classify and describe the moisture and porosity level of the dried fig. The most essential dielectric constant information relating to moisture and porosity level was at frequencies of 22 and 52 MHz, respectively. Finally, classification accuracy of 95.7% for moisture and 91.3% for porosity level was attained. The results demonstrated the excellent performance and capabilities of the proposed approach for rating the internal quality of dried figs.

Traditional plant breeding based on selection for grain yield is time-consuming and costly; therefore, new innovative methods are in high demand to reduce costs and accelerate genetic gains. Remote sensing-based platforms such as unmanned aerial vehicles (UAV) show promise to predict different traits including grain yield. Attention is currently being devoted to machine learning methods in order to extract the most meaningful information from the massive amounts of data generated by UAV images. These methods have shown a promising capability to come up with nonlinearity and explore patterns beyond the human ability. This study investigates the application of two different machine learning based regressor methods to predict wheat grain yield using extracted vegetation indices from UAV images. The goal of the study was to investigate the strength of Support Vector Regression (SVR) in combination with Sequential Forward Selection (SFS) for grain yield prediction and compare the results with LASSO regressor with an internal feature selector. Models were tested on grain yield data from 600 plots of spring wheat planted in South-Eastern Norway in 2018. Five spectral bands along with three different vegetation indices; the Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), and MERIS Terrestrial Chlorophyll Index (MTCI) were extracted from multispectral images at three dates between heading and maturity of the plants. These features for each field trial plot at each date were used as input data for the SVR model. The best model hyperparameters were estimated using grid search. Based on feature selection results from both methods, NDVI showed the highest prediction ability for grain yield at all dates and its explanatory power increased toward maturity, while adding MTCI and EVI at earlier stages of grain filling improved model performance. Combined models based on all indices and dates explained up to 90% of the variation in grain yield on the test set. Inclusion of individual bands added collinearity to the models and did not improve the predictions. Although both regression methods showed a good capability for grain yield prediction, LASSO regressor proved to be more affordable and economical in terms of time.

The Global Wheat Head Detection (GWHD) dataset was created in 2020 and has assembled 193,634 labelled wheat heads from 4,700 RGB images acquired from various acquisition platforms and 7 countries/institutions. With an associated competition hosted in Kaggle, GWHD has successfully attracted attention from both the computer vision and agricultural science communities. From this first experience in 2020, a few avenues for improvements have been identified, especially from the perspective of data size, head diversity and label reliability. To address these issues, the 2020 dataset has been reexamined, relabeled, and augmented by adding 1,722 images from 5 additional countries, allowing for 81,553 additional wheat heads to be added. We would hence like to release a new version of the Global Wheat Head Detection (GWHD) dataset in 2021, which is bigger, more diverse, and less noisy than the 2020 version. The GWHD 2021 is now publicly available at http://www.global-wheat.com/ and a new data challenge has been organized on AIcrowd to make use of this updated dataset.

The Global Wheat Head Detection (GWHD) dataset was created in 2020 and has assembled 193,634 labelled wheat heads from 4,700 RGB images acquired from various acquisition platforms and 7 countries/institutions. With an associated competition hosted in Kaggle, GWHD has successfully attracted attention from both the computer vision and agricultural science communities. From this first experience in 2020, a few avenues for improvements have been identified, especially from the perspective of data size, head diversity and label reliability. To address these issues, the 2020 dataset has been reexamined, relabeled, and augmented by adding 1,722 images from 5 additional countries, allowing for 81,553 additional wheat heads to be added. We now release a new version of the Global Wheat Head Detection (GWHD) dataset in 2021, which is bigger, more diverse, and less noisy than the 2020 version. The GWHD 2021 is now publicly available at http://www.global-wheat.com/ and a new data challenge has been organized on AIcrowd to make use of this updated dataset.

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.

This paper reports the data mining study on the NIR spectrum of lime juice samples to determine their purity (natural or synthetic). NIR spectra for 72 pure and synthetic lime juice samples were recorded in reflectance mode. Sample outliers were removed using PCA analysis. Different data mining techniques for feature selection (Genetic Algorithm (GA)) and classification (including the radial basis function (RBF) network, Support Vector Machine (SVM), and Random Forest (RF) tree) were employed. Based on the results, SVM proved to be the most accurate classifier as it achieved the highest accuracy (97%) using the raw spectrum information. The classifier accuracy dropped to 93% when selected feature vector by GA search method was applied as classifier input. It can be concluded that some relevant features which produce good performance with the SVM classifier are removed by feature selection. Also, reduced spectra using PCA do not show acceptable performance (total accuracy of 66% by RBFNN), which indicates that dimensional reduction methods such as PCA do not always lead to more accurate results. These findings demonstrate the potential of data mining combination with near-infrared spectroscopy for monitoring lime juice quality in terms of natural or synthetic nature. (C) 2018 Published by Elsevier B.V.

Nondestructive methods are of utmost importance for honey characterization. This study investigates the potential application of VIS-NIR hyperspectral imaging for detection of honey flower origin using machine learning techniques. Hyperspectral images of 52 honey samples were taken in transmittance mode in the visible/near infrared (VIS-NIR) range (400–1000 nm). Three different machine learning algorithms were implemented to predict honey floral origin using honey spectral images. These methods, included radial basis function (RBF) network, support vector machine (SVM), and random forest (RF). Principal component analysis (PCA) was also exploited for dimensionality reduction. According to the obtained results, the best classifier (RBF) achieved a precision of 94% in a fivefold cross validation experiment using only the first two PCs. Mapping of the classifier results to the test set images showed 90% accuracy for honey images. Three types of honey including buckwheat, rapeseed and heather were classified with 100% accuracy. The proposed approach has great potential for honey floral origin detection. As some other honey properties can also be predicted using image features, in addition to floral origin detection, this method may be applied to predict other honey characteristics.

This study investigates the application of hyperspectral imaging system and data mining based classifiers for honey adulteration detection. Hyperspectral images from pure and adulterated samples were captured in using a VIS-NIR hyperspectral camera (400 – 1000 nm). After preprocessing the images, five different data mining based techniques, including artificial neural network (ANN), support vector machine (SVM), Linear discriminant analysis (LDA), Fisher and Parzen classifiers were applied for supervised image classification. Classifier test results show the highest classification accuracy of 95% for ANN classifier. Other classifiers including SVM with radial basis kernel function (92%), LDA (90%), Fisher (89 %), and Parzen with 84% correct classification rate also showed acceptable results. This research shows the capability of hyperspectral imaging for honey authentication.

This study was aimed to evaluate the freshness and quality of cultured shrimp (litopenaeus vannamei) during 9 days of storage on ice (i.e., at a temperature of 0 degrees C) using image processing technique. A lighting chamber was used to provide uniform conditions for illumination. The shrimp freshness was evaluated using computer vision technique through color changes of head, legs and tail of the harvested shrimps. Thirty-six color parameters of the images such as mean and variance of red (r), green (g), blue (b), lightness hue (h), saturation (s), value (v), luma information (i and y), the luma component (y), chroma component (cr), lightness (L*), redness (a*), yellowness (b*), chroma (c), and hue (h) were analyzed. Some parameters, such as b*, from side pictures and r mean, b variance, v mean, y mean, b* mean and (L*) mean from top pictures changed with a rather similar trend during the storage period. Different computational expert approaches such as linear discriminant analysis, quadratic discriminant analysis, K nearest neighbors, and discriminant partial least squares regression were examined for shrimp freshness classification. For this, all the variables and the subsets of variables were selected by means of stepwise linear discriminant analysis, stepwise orthogonalization, classification and regression trees. The shrimp freshness was characterized with a high classification accuracy of 90%. Freshness evaluation using image processing is proposed as a potential technique to the food industry.

This paper reports the development of a computer vision system (CVS) for non-destructive characterization of honey based on colour and its correlated chemical attributes including ash content (AC), antioxidant activity (AA), and total phenolic content (TPC). Artificial neural network (ANN) models were applied to transform RGB values of images to CIE L∗a∗b∗ colourimetric measurements and to predict AC, TPC and AA from colour features of images. The developed ANN models were able to convert RGB values to CIE L∗a∗b∗ colourimetric parameters with low generalization error of 1.01 ± 0.99. In addition, the developed models for prediction of AC, TPC and AA showed high performance based on colour parameters of honey images, as the R2 values for prediction were 0.99, 0.98, and 0.87, for AC, AA and TPC, respectively. The experimental results show the effectiveness and possibility of applying CVS for non-destructive honey characterization by the industry.