The overarching aim of this research was to develop a method for deriving crop maps from a time series of Sentinel-2 images between 2017 and 2018 to address global challenges in agriculture and food security. This study is the first step towards improving crop mapping based on phenological features retrieved from an object-based time series on a national scale. Five main crops in Israel were classified: wheat, barley, cotton, carrot, and chickpea. To optimize the object-based classification process, different characteristics and inputs of the mean shift segmentation algorithm were tested, including vegetation indices, three-band combinations, and high/low emphasis on the spatial and spectral characteristics. Four known vegetation indices (VIs)-based time series were tested. Additionally, we compared two widely used machine learning methods for crop classification, support vector machine (SVM) and random forest (RF), in addition to a newer classifier, extreme gradient boosting (XGBoost). Lastly, we examined two accuracy measures—overall accuracy (OA) and area under the curve (AUC)—in order to optimally estimate the accuracy in the case of imbalanced class representation. Mean shift best performed when emphasizing both the spectral and spatial characteristics while using the green, red, and near-infrared (NIR) bands as input. Both accuracy measures showed that RF and XGBoost classified different types of crops with significantly greater success than achieved by SVM. Nevertheless, AUC was better able to represent the significant differences between the classification algorithms than OA was. None of the VIs showed a significantly higher contribution to the classification. However, normalized difference infrared index (NDII) with XGBoost classifier showed the highest AUC results (88%). This study demonstrates that the short-wave infrared (SWIR) band with XGBoost improves crop type classification results. Furthermore, the study emphasizes the importance of addressing imbalanced classification datasets by using a proper accuracy measure. Since object-based classification and phenological features derived from a VI-based time series are widely used to produce crop maps, the current study is also relevant for operational agricultural management and informatics at large scales.

Close range spectra imaging of agricultural plants is widely performed to support digital plant phenotyping, a task where physicochemical changes in plants are monitored in a non-destructive way. A major step before analyzing the spectral images of plants is to distinguish the plant from the background. Usually, this is an easy task and can be performed using mathematical operations on the combinations of selected spectral bands, such as estimating the normalized difference vegetative index (NDVI). However, when the background of plants contains objects with similar spectral properties as plant then the segmentation based on the threshold of NDVI images can suffer. Another common approach is to train pixel classifiers on spectra extracted from selected locations in the spectral image, but such an approach does not take the spatial information about the plant structure into account. From a technical perspective, plant spectral imaging for digital phenotyping applications usually involves imaging several plants together for a comparative purpose, hence, the imaging scene is relatively big in terms of memory. To solve the challenge of plant segmentation and handling the memory challenge, this study proposes a novel approach, which combines chemometrics with advanced deep learning (DL) based semantic segmentation. The approach has four key steps. As a first step, the spectral image is pre-processed to reduce illumination effects present in the close-range spectral images of plants resulting from the interaction of light with complex plant geometry. Different chemometric pre-processing methods were explored to find possible improvements in the segmentation performance of the DL model. The second step was to perform a principal components analysis (PCA) to reduce the dimensionality of the images, thus drastically reducing their size so that they can be handled more easily using the available computer memory during the training of the DL model. As the third step, small random images (128 × 128) were subsampled from the tall and wide image matrices to generate the training and validation sets for training the DL models. In the last step, a U-net based deep semantic segmentation model was trained and validated on the sub-sampled spectral images. The results showed that the proposed approach allowed efficient handling and training of the DL segmentation model. The intersection over union (IoU) scores for the segmentation was 0.96 for the independent test set image. The segmentation based on variable sorting for normalization and standard normal variate pre-processed data achieved the highest IoU scores. A combination of chemometrics and DL led to an efficient segmentation of tall and wide spectral images which otherwise would have given out-of-memory errors. The developed method can facilitate digital phenotyping tasks where close-range spectral imaging is used to estimate the physicochemical properties of plants.

In analytical chemistry, spectral imaging of complex analytical systems is commonly performed. A major task in spectral imaging analysis is to extract signals related to important analytes present in the imaged scene. Hence, the first task of spectral image analysis is to perform an image segmentation to extract the relevant signals to analyze. However, in the chemometric domain, the traditional image segmentation methods are limited either to threshold-based or pixel-wise classification, therefore, no approache uses the contextual information present in the imaging scene. This study presents for the first time a pixel2pixel (p2p) image translation using conditional generative adversarial networks (cGAN) for the segmentation of spectral images. The p2p cGAN trains two neural models simultaneously where one model (generator) learns to segment and the other model learns to detect if the segmentation performed by the generator model is correct. During the process of generation and detection, the model automatically learns to segment the spectral images accurately. As an application of the p2p cGAN, a case of segmenting visible and near-infrared spectral images of plants was presented. Furthermore, as a comparison, threshold-based and pixel-wise image classification based on partial least-square discriminant analysis were also presented. The results showed that the p2p cGAN based image translation performed the best segmentation task with an intersection over union score of 0.95 ​± ​0.04. The advanced new DL based image processing approaches can complement spectral image processing.

Close-range spectral imaging (SI) of agricultural plants is widely performed for digital plant phenotyping. A key task in digital plant phenotyping is the non-destructive and rapid identification of drought stress in plants so as to allow plant breeders to select potential genotypes for breeding drought-resistant plant varieties. Visible and near-infrared SI is a key sensing technique that allows the capture of physicochemical changes occurring in the plant under drought stress. The main challenges are in processing the massive spectral images to extract information relevant for plant breeders to support genotype selection. Hence, this study presents a generic data processing workflow for analysing SI data generated in real-world digital phenotyping experiments to extract meaningful information for decision making by plant breeders. The workflow is a combination of chemometric approaches and deep learning. The usefulness of the proposed workflow is demonstrated on a real-life experiment related to drought stress detection and quantification in Arabidopsis thaliana plants grown in a semi-controlled environment. The results show that the proposed approach is able to detect the presence of drought just 3 days after its induction compared to the well-watered plants. Furthermore, the unsupervised clustering approach provides detailed time-series images where the drought-related changes in plants can be followed visually along the time course. The developed approach facilitates digital phenotyping and can thus accelerate breeding of drought-tolerant plant varieties.

Since its discovery by F.A.L Clowes, extensive research has been dedicated to identifying the functions of the quiescent center (QC). One of the earliest hypotheses was that it serves a key role in regeneration of the root meristem. Recent works provide support for this hypothesis and began to elucidate the molecular mechanisms underlying this phenomenon. There are two scenarios to consider when assessing the role of the QC in regeneration. One, when the damage leaves the QC intact, and the other, when the QC itself is destroyed. In the first scenario, multiple factors are recruited to activate QC cell division in order to replace damaged cells, but whether the QC has a role in the second scenario is less clear. Using both gene expression studies and following cell division pattern has shown that the QC is assembled gradually, only to appear as a coherent identity late in regeneration. Similar late emergence of the QC was observed during the de novo formation of the lateral root meristem. These observations can lead to the conclusion that the QC has no role in regeneration. However, activities normally occurring in QC cells, such as local auxin biosynthesis, are still found during regeneration but occur in different cells in the regenerating meristem. Thus, we explore an alternative hypothesis, that following destruction of the QC, QC-related gene activity is temporarily distributed to other cells in the regenerating meristem, only coalesce into a distinct cell identity when regeneration is complete.

Stilbenes and flavonoids are two major health-promoting phenylpropanoid groups in grapes. Attempts to promote the accumulation of one group usually resulted in a decrease in the other. This study presents a unique strategy for simultaneously increasing metabolites in both groups in V. vinifera cv. Gamay Red grape cell culture, by overexpression of flavonol synthase (FLS) and increasing Phe availability. Increased Phe availability was achieved by transforming the cell culture with a second gene, the feedback-insensitive E. coli DAHP synthase (AroG*), and feeding them with Phe. A combined metabolomic and transcriptomic analysis reveals that the increase in both phenylpropanoid groups is accompanied by an induction of many of the flavonoid biosynthetic genes and no change in the expression levels of stilbene synthase. Furthermore, FLS overexpression with increased Phe availability resulted in higher anthocyanin levels, mainly those derived from delphinidin, due to the induction of F3′5′H. These insights may contribute to the development of grape berries with increased health benefits.Stilbenes and flavonoids are two major health-promoting phenylpropanoid groups in grapes. Attempts to promote the accumulation of one group usually resulted in a decrease in the other. This study presents a unique strategy for simultaneously increasing metabolites in both groups in V. vinifera cv. Gamay Red grape cell culture, by overexpression of flavonol synthase (FLS) and increasing Phe availability. Increased Phe availability was achieved by transforming the cell culture with a second gene, the feedback-insensitive E. coli DAHP synthase (AroG*), and feeding them with Phe. A combined metabolomic and transcriptomic analysis reveals that the increase in both phenylpropanoid groups is accompanied by an induction of many of the flavonoid biosynthetic genes and no change in the expression levels of stilbene synthase. Furthermore, FLS overexpression with increased Phe availability resulted in higher anthocyanin levels, mainly those derived from delphinidin, due to the induction of F3′5′H. These insights may contribute to the development of grape berries with increased health benefits.

Conventional methods of plant nutrient estimation for nutrient management need a huge number of leaf or tissue samples and extensive chemical analysis, which is time-consuming and expensive. Remote sensing is a viable tool to estimate the plant’s nutritional status to determine the appropriate amounts of fertilizer inputs. The aim of the study was to use remote sensing to characterize the foliar nutrient status of mango through the development of spectral indices, multivariate analysis, chemometrics, and machine learning modeling of the spectral data. A spectral database within the 350–1050 nm wavelength range of the leaf samples and leaf nutrients were analyzed for the development of spectral indices and multivariate model development. The normalized difference and ratio spectral indices and multivariate models–partial least square regression (PLSR), principal component regression, and support vector regression (SVR) were ineffective in predicting any of the leaf nutrients. An approach of using PLSR-combined machine learning models was found to be the best to predict most of the nutrients. Based on the independent validation performance and summed ranks, the best performing models were cubist (R2 ≥ 0.91, the ratio of performance to deviation (RPD) ≥ 3.3, and the ratio of performance to interquartile distance (RPIQ) ≥ 3.71) for nitrogen, phosphorus, potassium, and zinc, SVR (R2 ≥ 0.88, RPD ≥ 2.73, RPIQ ≥ 3.31) for calcium, iron, copper, boron, and elastic net (R2 ≥ 0.95, RPD ≥ 4.47, RPIQ ≥ 6.11) for magnesium and sulfur. The results of the study revealed the potential of using hyperspectral remote sensing data for non-destructive estimation of mango leaf macro- and micro-nutrients. The developed approach is suggested to be employed within operational retrieval workflows for precision management of mango orchard nutrients.

The inference of functional vegetation traits from remotely sensed signals is key to providing efficient information for multiple plant-based applications and to solve related problems [...]

Wet chemistry analysis of agricultural plant materials such as leaves is widely performed to quantify key chemical components to understand plant physiological status. Visible and near-infrared (Vis-NIR) spectroscopy is an interesting tool to replace the wet chemistry analysis, often labour intensive and time-consuming. Hence, this study accesses the potential of Vis-NIR spectroscopy to predict nitrogen (N) and potassium (K) concentration in bell pepper leaves. In the chemometrics perspective, the study aims to identify key Vis-NIR wavelengths that are most correlated to the N and K, and hence, improves the predictive performance for N and K in bell pepper leaves. For wavelengths selection, six different wavelength selection techniques were used. The performances of several wavelength selection techniques were compared to identify the best technique. As a baseline comparison, the partial least-square (PLS) regression analysis was used. The results showed that the Vis-NIR spectroscopy has the potential to predict N and K in pepper leaves with root mean squared error of prediction (RMSEP) of 0.28 and 0.44%, respectively. The wavelength selection in general improved the predictive performance of models for both K and N compared to the PLS regression. With wavelength selection, the RMSEP's were decreased by 19% and 15% for N and K, respectively, compared to the PLS regression. The results from the study can support the development of protocols for non-destructive prediction of key plant chemical components such as K and N without wet chemistry analysis.

Fruit taste is determined by sugars, acids and in some species, bitter chemicals. Attraction of seed-dispersing organisms in nature and breeding for consumer preferences requires reduced fruit bitterness. A key metabolic shift during ripening prevents tomato fruit bitterness by eliminating α-tomatine, a renowned defence-associated Solanum alkaloid. Here, we combined fine mapping with information from 150 resequenced genomes and genotyping a 650-tomato core collection to identify nine bitter-tasting accessions including the ‘high tomatine’ Peruvian landraces reported in the literature. These ‘bitter’ accessions contain a deletion in GORKY, a nitrate/peptide family transporter mediating α-tomatine subcellular localization during fruit ripening. GORKY exports α-tomatine and its derivatives from the vacuole to the cytosol and this facilitates the conversion of the entire α-tomatine pool to non-bitter forms, rendering the fruit palatable. Hence, GORKY activity was a notable innovation in the process of tomato fruit domestication and breeding.

The papain-like cysteine proteases (PLCPs) are the most abundant family of cysteine proteases in plants, with essential roles in biotic/abiotic stress responses, growth and senescence. Papain, bromelain and ficin are widely used in food, medicine and other industries. In this study, 31 PLCP genes (FcPCLPs) were identified in the fig (Ficus carica L.) genome by HMM search and manual screening, and assigned to one of nine subfamilies based on gene structure and conserved motifs. SAG12 and RD21 were the largest subfamilies with 10 and 7 members, respectively. The FcPCLPs ranged from 1,128 to 5,075 bp in length, containing 1–10 introns, and the coding sequence ranged from 624 to 1,518 bp, encoding 207–505 amino acids. Subcellular localization analysis indicated that 24, 2, and 5 PLCP proteins were targeted to the lysosome/vacuole, cytoplasm and extracellular matrix, respectively. Promoter (2,000 bp upstream) analysis of FcPLCPs revealed a high number of plant hormone and low temperature response elements. RNA-seq revealed differential expression of 17 FcPLCPs in the inflorescence and receptacle, and RD21 subfamily members were the major PLCPs expressed in the fruit; 16 and 5 FcPLCPs responded significantly to ethylene and light, respectively. Proteome analyses revealed 18 and 5 PLCPs in the fruit cell soluble proteome and fruit latex, respectively. Ficins were the major PLCP in fig fruit, with decreased abundance in inflorescences, but increased abundance in receptacles of commercial-ripe fruit. FcRD21B/C and FcALP1 were aligned as the genes encoding the main ficin isoforms. Our study provides valuable multi-omics information on the FcPLCP family and lays the foundation for further functional studies.

A protracted domestication time-frame for cereals in the Near East is widely endorsed by the plant domestication research community. This occurs in tandem with the pre-domestication cultivation concept, which rests on the assumption that human husbandry operations (namely cultivation) exerted selection pressures in favor of domesticated phenotypes (e.g., non-shattering spikes) at the expense of the wild type (WT) shattering phenotype. The protracted domestication model rests on a long series of assumptions of which we address only two: (1) that the archeobotanical assemblages found in Neolithic occupation sites are representative of the managed plant populations from the cultivated fields; (2) that WT (shattering, brittle spikes) and domesticated (non-shattering, non-brittle spikes) stocks were grown for millennia as admixed populations across the Near East before the domesticated (non-shattering) morphotype slowly came to dominate the managed cereal populations. Scrutinizing these assumptions, and their derivatives, we suggest that the proportion of wild vs. domesticated cereal remains in archeobotanical assemblages cannot possibly represent the presumed cultivated plant populations. Moreover, agronomic considerations expose severe methodological and theoretical drawbacks in the protracted domestication reconstruction vis-à-vis the proportions of shattering vs. non-shattering spikelets in archeobotanical assemblages.

Plant breeders and conservationist depend on knowledge about the genetic variation of their species of interest. Pisum fulvum, a wild relative of domesticated pea, has attracted attention as a genetic resource for crop improvement, yet little information about its diversity in the wild has been published hitherto. We sampled 15 populations of P. fulvum from Israeli natural habitats and conducted genotyping by sequencing to analyse their genetic diversity and adaptive state. We also attempted to evaluate the species past demography and the prospects of its future reaction to environmental changes. The results suggest that genetic diversity of P. fulvum is low to medium and is distributed between well diverged populations. Surprisingly, with 56 % in the total population the selfing rate was found to be significantly lower than expected from a species that is commonly assumed to be a predominant selfer. We found a strong genetic bottleneck during the last glacial period and only limited patterns of isolation by distance and environment, which explained 13 %–18 % of the genetic variation. Despite the weak signatures of genome-wide IBE, 1,354 markers were significantly correlated with environmental factors, 1,233 of which were located within known genes with a nonsynonymous to synonymous ratio of 0.382. Species distribution modelling depicted an ongoing fragmentation and decreased habitable area over the next 80 years under two different socio-economic pathways. Our results suggest that complex interactions of substantial drift and selection shaped the genome of P. fulvum. Climate changeis likely to cause further erosion of genetic diversity in P. fulvum. Systematic ex-situ conservation may be advisable to safeguard genetic variability for future utilization of this species.

A “cultivation prior to domestication”, or a “pre-domestication cultivation” phase features in many reconstructions of Near Eastern plant domestication. Archaeobotanists who accept this notion search for evidence to support the assumption regarding a wild plant’s cultivation phase, which in their view, preceded and eventually led to plant domestication. The presence of non-crop plant remains in the archaeobotanical record interpreted as arable weeds, i.e., weeds of cultivation, is viewed as a strong argument in support of the pre-domestication cultivation phase. Herein, we show that the simple practice of harvest by hand-pulling (uprooting) has the potential to secure an almost weed-free harvest. Indeed, rather clean (weed-free) Neolithic seed caches from a range of relevant sites were documented in archaeobotanical reports. These reports, alongside ethnographic observations suggest that (in certain cases) ancient harvest may have been carried out by selective hand-pulling. Hence, one has no reason to view archaeobotanical assemblages from occupation sites as fully representative of cultivated fields. Therefore, the concept of “arable—pre-domestication weeds”, its logic, and its potential contribution to the prevailing reconstructions of Near Eastern plant domestication need be reconsidered.

Abstract BACKGROUND Thaumatin II, a supersweet protein from the African plant katemfe (Thaumatococcus daniellii Benth.), shows promise as a zero-calorie sweetener for use in the food and pharmaceutical industries and for improving the taste of fruit. RESULTS We report on the stability of thaumatin in salted and pickled tomatoes, as well as on the effect of thaumatin on the taste quality of processed tomatoes. Fruit of tomato cv. Yalf, transformed with the thaumatin II gene were salted and pickled and then stored for 6 months. Western blot analysis showed relative thaumatin II stability at salting; its content in processed fruits was 62?83% of the initial level depending in the studied line. In pickled tomatoes, thaumatin II content was decreased by up to 25% of the initial amount. Both salted and pickled tomatoes had a sweet taste with a typical thaumatin aftertaste. Salted tomatoes were characterized as being sweeter than pickled tomatoes. The overall taste of pickled tomatoes was rated by panellists as significantly better compared to that of salted or non-processed ones. CONCLUSION In the present study, we have shown that tomatoes expressing supersweet protein thaumatin II can be used for processing under mild conditions, including salting and pickling. ? 2021 Society of Chemical Industry.

Divergence of gene function is a hallmark of evolution, but assessing functional divergence over deep time is not trivial. The few alleles available for cross-species studies often fail to expose the entire functional spectrum of genes, potentially obscuring deeply conserved pleiotropic roles. Here, we explore the functional divergence of WUSCHEL HOMEOBOX9 (WOX9), suggested to have species-specific roles in embryo and inflorescence development. Using a cis-regulatory editing drive system, we generate a comprehensive allelic series in tomato, which revealed hidden pleiotropic roles for WOX9. Analysis of accessible chromatin and conserved cis-regulatory sequences identifies the regions responsible for this pleiotropic activity, the functions of which are conserved in groundcherry, a tomato relative. Mimicking these alleles in Arabidopsis, distantly related to tomato and groundcherry, reveals new inflorescence phenotypes, exposing a deeply conserved pleiotropy. We suggest that targeted cis-regulatory mutations can uncover conserved gene functions and reduce undesirable effects in crop improvement.

{Potassium is a macro element in plants that is typically supplied to crops in excess throughout the season to avoid a deficit leading to reduced crop yield. Transpiration rate is a momentary physiological attribute that is indicative of soil water content, the plant’s water requirements, and abiotic stress factors. In this study, two systems were combined to create a hyperspectral–physiological plant database for classification of potassium treatments (low, medium, and high) and estimation of momentary transpiration rate from hyperspectral images. PlantArray 3.0 was used to control fertigation, log ambient conditions, and calculate transpiration rates. In addition, a semi-automated platform carrying a hyperspectral camera was triggered every hour to capture images of a large array of pepper plants. The combined attributes and spectral information on an hourly basis were used to classify plants into their given potassium treatments (average accuracy = 80%) and to estimate transpiration rate (RMSE = 0.025 g/min

Chemical weed-control is the most effective practice for wheat, however, rapid evolution of herbicide-resistant weeds threat food-security and calls for integration of non-chemical practices. We hypothesis that integration of alternative GA-responsive dwarfing genes into elite wheat cultivars can promote early vigor and weed-competitiveness under Mediterranean climate. We develop near-isogenic lines of bread wheat cultivars with GAR dwarfing genes and evaluate them for early vigor and weed-competitiveness under various environmental and management conditions to identify promising NIL for weed-competitiveness and grain yield. While all seven NILs responded to external gibberellic acid application, they exhibited differences in early vigor. Greenhouse and field evaluations highlighted NIL OC1 (Rht8andRht12) as a promising line, with significant advantage in canopy early vigor over its parental. To facilitate accurate and continuous early vigor data collection, we applied non-destructive image-based phenotyping approaches which offers non-expensive and end-user friendly solution for selection. NIL OC1 was tested under different weed density level, infestation waves, and temperatures and highlight the complex genotypic × environmental × management interactions. Our findings demonstrate the potential of genetic modification of dwarfing genes as promising approach to improve weed-competitiveness, and serve as basis for future breeding efforts to support sustainable wheat production under semi-arid Mediterranean climate.