Sesame (Sesamum indicum) is an important oilseed crop with rising demand owing to its nutritional and health benefits. There is an urgent need to develop and integrate new genomic-based breeding strategies to meet these future demands. While genomic resources have advanced genetic research in sesame, the implementation of high-throughput phenotyping and genetic analysis of longitudinal traits remains limited. Here, we combined high-throughput phenotyping and random regression models to investigate the dynamics of plant height, leaf area index, and five spectral vegetation indices throughout the sesame growing seasons in a diversity panel. Modeling the temporal phenotypic and additive genetic trajectories revealed distinct patterns corresponding to the sesame growth cycle. We also conducted longitudinal genomic prediction and association mapping of plant height using various models and cross-validation schemes. Moderate prediction accuracy was obtained when predicting new genotypes at each time point, and moderate to high values were obtained when forecasting future phenotypes. Association mapping revealed three genomic regions in linkage groups 6, 8, and 11, conferring trait variation over time and growth rate. Furthermore, we leveraged correlations between the temporal trait and seed-yield and applied multi-trait genomic prediction. We obtained an improvement over single-trait analysis, especially when phenotypes from earlier time points were used, highlighting the potential of using a high-throughput phenotyping platform as a selection tool. Our results shed light on the genetic control of longitudinal traits in sesame and underscore the potential of high-throughput phenotyping to detect a wide range of traits and genotypes that can inform sesame breeding efforts to enhance yield.

In light of the changing climate that jeopardizes future food security, genomic selection is emerging as a valuable tool for breeders to enhance genetic gains and introduce high-yielding varieties. However, predicting grain yield is challenging due to the genetic and physiological complexities involved and the effect of genetic-by-environment interactions on prediction accuracy. We utilized a chained model approach to address these challenges, breaking down the complex prediction task into simpler steps. A diversity panel with a narrow phenological range was phenotyped across three Mediterranean environments for various morpho-physiological and yield-related traits. The results indicated that a multi-environment model outperformed a single-environment model in prediction accuracy for most traits. However, prediction accuracy for grain yield was not improved. Thus, in an attempt to ameliorate the grain yield prediction accuracy, we integrated a spectral estimation of spike number, being a major wheat yield component, with genomic data. A machine learning approach was used for spike number estimation from canopy hyperspectral reflectance captured by an unmanned aerial vehicle. The spectral-based estimated spike number was utilized as a secondary trait in a multi-trait genomic selection, significantly improving grain yield prediction accuracy. Moreover, the ability to predict the spike number based on data from previous seasons implies that it could be applied to new trials at various scales, even in small plot sizes. Overall, we demonstrate here that incorporating a novel spectral-genomic chain-model workflow, which utilizes spectral-based phenotypes as a secondary trait, improves the predictive accuracy of wheat grain yield.

Vegetation productivity is a critical indicator of global ecosystem health and is impacted by human activities and climate change. A wide range of optical sensing platforms, from ground-based to airborne and satellite, provide spatially continuous information on terrestrial vegetation status and functioning. As optical Earth observation (EO) data are usually routinely acquired, vegetation can be monitored repeatedly over time, reflecting seasonal vegetation patterns and trends in vegetation productivity metrics. Such metrics include gross primary productivity, net primary productivity, biomass, or yield. To summarize current knowledge, in this paper we systematically reviewed time series (TS) literature for assessing state-of-the-art vegetation productivity monitoring approaches for different ecosystems based on optical remote sensing (RS) data. As the integration of solar-induced fluorescence (SIF) data in vegetation productivity processing chains has emerged as a promising source, we also include this relatively recent sensor modality. We define three methodological categories to derive productivity metrics from remotely sensed TS of vegetation indices or quantitative traits: (i) trend analysis and anomaly detection, (ii) land surface phenology, and (iii) integration and assimilation of TS-derived metrics into statistical and process-based dynamic vegetation models (DVMs). Although the majority of used TS data streams originate from data acquired from satellite platforms, TS data from aircraft and unoccupied aerial vehicles have found their way into productivity monitoring studies. To facilitate processing, we provide a list of common toolboxes for inferring productivity metrics and information from TS data. We further discuss validation strategies of the RS data derived productivity metrics: (1) using in situ measured data, such as yield; (2) sensor networks of distinct sensors, including spectroradiometers, flux towers, or phenological cameras; and (3) inter-comparison of different productivity metrics. Finally, we address current challenges and propose a conceptual framework for productivity metrics derivation, including fully integrated DVMs and radiative transfer models here labelled as “Digital Twin”. This novel framework meets the requirements of multiple ecosystems and enables both an improved understanding of vegetation temporal dynamics in response to climate and environmental drivers and enhances the accuracy of vegetation productivity monitoring.

Water scarcity is the primary environmental constraint affecting wheat growth and production and is increasingly exacerbated due to climatic fluctuation, which jeopardizes future food security. Most breeding efforts to improve wheat yields under drought have focused on above-ground traits. Root traits are closely associated with various drought adaptability mechanisms, but the genetic variation underlying these traits remains untapped, even though it holds tremendous potential for improving crop resilience. Here, we examined this potential by re-introducing ancestral alleles from wild emmer wheat (Triticum turgidum ssp. dicoccoides) and studied their impact on root architecture diversity under terminal drought stress. We applied an active sensing electrical resistivity tomography approach to compare a wild emmer introgression line (IL20) and its drought-sensitive recurrent parent (Svevo) under field conditions. IL20 exhibited greater root elongation under drought, which resulted in higher root water uptake from deeper soil layers. This advantage initiated at the pseudo-stem stage and increased during the transition to the reproductive stage. The increased water uptake promoted higher gas exchange rates and enhanced grain yield under drought. Overall, we show that this presumably ‘lost’ drought-induced mechanism of deeper rooting profile can serve as a breeding target to improve wheat productiveness under changing climate.

In the mass production systems of microalgal species, it is important to ensure the safety and quality of the biomass and product. This requires effective monitoring tools that are sensitive, rapid and simple to use. In this study, hyperspectral transmittance spectroscopy (HTS) was applied for the detection, cell density quantification and classification of algal and cyanobacterial species. A database of HTS data was assembled from samples of seven algal and cyanobacterial species at different cell densities and used for quantifying and classifying the species, using chemometric and machine learning algorithms. The results obtained showed the ability to quantify the species with a detection limit of 104 cells/mL for the support vector machine models applied, and classify the species at concentrations >105 cells/mL. The current study suggests that HTS is applicable for cell density quantification. HTS was used to distinguish between cell cultures of cyanobacteria and algae and was further able to distinguish between cyanobacteria species as well as algal species. In addition, reducing the dimensions (number of spectral bands) of HTS data using feature selection and aggregation improved the classification accuracy. Thus, HTS is recommended as an effective tool for monitoring and management of microalgal bioreactors.

Chickpea (Cicer arietinum L.) is a key legume crop grown in many semi-arid areas. Traditionally, chickpea is a rainfed spring crop, but in certain countries it has become an irrigated crop. The main objective of this study was to evaluate the ability of Unmanned Aerial Systems (UAS) imaging platform with an integrated RGB camera to provide estimations of leaf area index (LAI), biomass, and yield for chickpea during the irrigation period. Two field trials were conducted in 2019 and 2020, in which chickpea plants were subjected to five and six irrigation regimes, respectively. Eight vegetation indexes (VIs) and three morphological parameters were estimated from the RGB images. In parallel, biomass was determined, LAI was measured manually, and yield was determined at full maturity. In total, 294 plant samples were acquired and analyzed over the two years. Firstly, each of the VIs and morphological parameters were correlated separately against the two biophysical parameters and yield. Then, all the VIs and morphological parameters were analyzed together, and two statistical models, partial least squares regression (PLS-R) and support vector machine (SVM); were used to predict biomass and LAI. The yield was predicted using multi-linear regression (MLR). When each index or morphological parameter was analyzed separately, plant height and some of the VIs provided adequate predictions of the biophysical parameters in 2019 (R2 values ≥ 0.50) but failed (R2 values ≤ 0.25) in 2020. The integration of the VIs with the morphological parameters and the use of PLS-R and SVM models increased the accuracy level for both biophysical parameters (R2 ranged from 0.31 to 0.96) and mitigated the lack of consistency between the years. The SVM model was superior to the PLS-R model in both biophysical parameters. The R2 values for the combined 2019 and 2020 biomass model increased, at the model-testing stage, from 0.62 to 0.96 and the RMSE values dropped from 1778 to 490 kg ha−1. The ability of the SVM model to estimate chickpea biomass and LAI can provide convenient support for different management decisions, including timing and amount of irrigation and harvest date.

Remote detection and monitoring of the vegetation responses to stress became relevant for sustainable agriculture. Ongoing developments in optical remote sensing technologies have provided tools to increase our understanding of stress-related physiological processes. Therefore, this study aimed to provide an overview of the main spectral technologies and retrieval approaches for detecting crop stress in agriculture. Firstly, we present integrated views on: i) biotic and abiotic stress factors, the phases of stress, and respective plant responses, and ii) the affected traits, appropriate spectral domains and corresponding methods for measuring traits remotely. Secondly, representative results of a systematic literature analysis are highlighted, identifying the current status and possible future trends in stress detection and monitoring. Distinct plant responses occurring under short-term, medium-term or severe chronic stress exposure can be captured with remote sensing due to specific light interaction processes, such as absorption and scattering manifested in the reflected radiance, i.e. visible (VIS), near infrared (NIR), shortwave infrared, and emitted radiance, i.e. solar-induced fluorescence and thermal infrared (TIR). From the analysis of 96 research papers, the following trends can be observed: increasing usage of satellite and unmanned aerial vehicle data in parallel with a shift in methods from simpler parametric approaches towards more advanced physically-based and hybrid models. Most study designs were largely driven by sensor availability and practical economic reasons, leading to the common usage of VIS-NIR-TIR sensor combinations. The majority of reviewed studies compared stress proxies calculated from single-source sensor domains rather than using data in a synergistic way. We identified new ways forward as guidance for improved synergistic usage of spectral domains for stress detection: (1) combined acquisition of data from multiple sensors for analysing multiple stress responses simultaneously (holistic view); (2) simultaneous retrieval of plant traits combining multi-domain radiative transfer models and machine learning methods; (3) assimilation of estimated plant traits from distinct spectral domains into integrated crop growth models. As a future outlook, we recommend combining multiple remote sensing data streams into crop model assimilation schemes to build up Digital Twins of agroecosystems, which may provide the most efficient way to detect the diversity of environmental and biotic stresses and thus enable respective management decisions.

Rosemary (Salvia rosmarinus (L.) Schleid., Handb. syn. Rosmarinus officinalis L.) extracts are widely used as natural preservatives due to their antimicrobial and antioxidant properties, which are attributed to the phenolic diterpenoid carnosic acid (CA). Growers are rewarded based on CA content in their rosemary leaf harvested. Conventional methods for estimating leaf CA content are destructive and often time-consuming. This preliminary study presents a spectral non-destructive approach for in vivo estimation of CA content in different rosemary cultivars based on the reflectance spectra of their canopy. The proposed approach is based on the characteristic rosemary absorption features along the visible and shortwave infrared spectral regions at 550 nm, 1200 nm, and 1690 nm, respectively, attributed to leaf color, the oxygen-hydrogen bond bending in water molecules, and distinctive carbon-hydrogen bond features typical for terpenes and phenolic compounds. Correlations between measured CA content by high-performance liquid chromatography (HPLC) and leaf reflectance spectra, normalized spectral indices, and latent components obtained by genetic algorithm-based partial least squares regression (GA-PLSR) were assessed using data collected from 79 rosemary cultivars. The GA-PLSR model successfully predicted the CA content among the various cultivars, further providing evidence of high weightage to the above-mentioned absorption features also obtained from two best-wavelength combination selections. Randomly selected canopy spectra were used to calibrate and simultaneously cross-validate 100 iterations, using the ‘leave-k-out’ approach. The root mean squared error (RMSE) obtained for calibration and cross-validation were 0.86% and 1.15% CA content from the dry leaf matter, and the residual prediction deviation (RPD) were reported to be 2.71 and 2.05, respectively. This work will set the stage for precise planning of harvesting time to ensure increased yield and income for the farmers and improved utilization of resources.

The bidirectional reflectance distribution function (BRDF) is crucial in determining the quantity of reflected light on the earth’s surface as a function of solar and view angles (i.e., azimuth and zenith angles). The Vegetation and ENvironment monitoring Micro-Satellite (VENµS) provides a unique opportunity to acquire data from the same site, with the same sensor, with almost constant solar and view zenith angles from two (or more) view azimuth angles. The present study was aimed at exploring the view angles’ effect on the stability of the values of albedo and of two vegetation indices (VIs): the normalized difference vegetation index (NDVI) and the red-edge inflection point (REIP). These products were calculated over three polygons representing urban and cultivated areas in April, June, and September 2018, under a minimal time difference of less than two minutes. Arithmetic differences of VIs and a change vector analysis (CVA) were performed. The results show that in urban areas, there was no difference between the VIs, whereas in the well-developed field crop canopy, the REIP was less affected by the view azimuth angle than the NDVI. Results suggest that REIP is a more appropriate index than NDVI for field crop studies and monitoring. This conclusion can be applied in a constellation of satellites that monitor ground features simultaneously but from different view azimuth angles.

To meet the ever-growing global population necessities, integrating climate-change-relevant plant traits into breeding programs is required. Developing new tools for fast and accurate estimation of chlorophyll parameters, chlorophyll a (Chl-a) content, chlorophyll b (Chl-b) content, and their ratio (Chl-a/b), can promote breeding programs of wheat with enhanced climate adaptability. Spectral reflectance of leaves is affected by changes in pigment concentration and can be used to estimate chlorophyll parameters. The current study identified and validated the top known spectral indices and developed new vegetation indices (VIs) for Chl-a and Chl-b content estimation and used them to non-destructively estimate Chl-a/b values and compare them to hyperspectral estimations. Three wild emmer introgression lines, with contrasting drought stress responsiveness dynamics, were selected. Well-watered and water-limited irrigation regimes were applied. The wheat leaves were spectrally measured with a handheld spectrometer to acquire their reflectance in the 330 to 790 nm range. Regression models based on calculated VIs as well as all hyperspectral curves were calibrated and validated against chlorophyll extracted values. The developed normalized difference spectral indices (NDSIs) resulted in high accuracy of Chl-a (NDSI415,614) and Chl-b (NDSI406,525) estimation, allowing for indirect non-destructive estimation of Chl-a/b with root mean square error (RMSE) values that could fit 6 to 10 times in the range of the measured values. They also performed similarly to the hyperspectral models. Altogether, we present here a new tool for a non-destructive estimation of Chl-a/b, which can serve as a basis for future breeding efforts of climate-resilient wheat as well as other crops.

Multiple and heterogenous Earth observation (EO) platforms are broadly used for a wide array of applications, and the integration of these diverse modalities facilitates better extraction of information than using them individually. The detection capability of the multispectral unmanned aerial vehicle (UAV) and satellite imagery can be significantly improved by fusing with ground hyperspectral data. However, variability in spatial and spectral resolution can affect the efficiency of such dataset's fusion. In this study, to address the modality bias, the input data was projected to a shared latent space using cross-modal generative approaches or guided unsupervised transformation. The proposed adversarial networks and variational encoder-based strategies used bi-directional transformations to model the cross-domain correlation without using cross-domain correspondence. It may be noted that an interpolation-based convolution was adopted instead of the normal convolution for learning the features of the point spectral data (ground spectra). The proposed generative adversarial network-based approach employed dynamic time wrapping based layers along with a cyclic consistency constraint to use the minimal number of unlabeled samples, having cross-domain correlation, to compute a cross-modal generative latent space. The proposed variational encoder-based transformation also addressed the cross-modal resolution differences and limited availability of cross-domain samples by using a mixture of expert-based strategy, cross-domain constraints, and adversarial learning. In addition, the latent space was modelled to be composed of modality independent and modality dependent spaces, thereby further reducing the requirement of training samples and addressing the cross-modality biases. An unsupervised covariance guided transformation was also proposed to transform the labelled samples without using cross-domain correlation prior. The proposed latent space transformation approaches resolved the requirement of cross-domain samples which has been a critical issue with the fusion of multi-modal Earth observation data. This study also proposed a latent graph generation and graph convolutional approach to predict the labels resolving the domain discrepancy and cross-modality biases. Based on the experiments over different standard benchmark airborne datasets and real-world UAV datasets, the developed approaches outperformed the prominent hyperspectral panchromatic sharpening, image fusion, and domain adaptation approaches. By using specific constraints and regularizations, the network developed was less sensitive to network parameters, unlike in similar implementations. The proposed approach illustrated improved generalizability in comparison with the prominent existing approaches. In addition to the fusion-based classification of the multispectral and hyperspectral datasets, the proposed approach was extended to the classification of hyperspectral airborne datasets where the latent graph generation and convolution were employed to resolve the domain bias with a small number of training samples. Overall, the developed transformations and architectures will be useful for the semantic interpretation and analysis of multimodal data and are applicable to signal processing, manifold learning, video analysis, data mining, and time series analysis, to name a few.

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.

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.

In-vivo foliar spectroscopy, also known as contact hyperspectral reflectance, enables rapid and non-destructive characterization of plant physiological status. This can be used to assess pathogen impact on plant condition both prior to and after visual symptoms appear. Challenging this capacity is the fact that dead tissue yields relatively consistent changes in leaf optical properties, negatively impacting our ability to distinguish causal pathogen identity. Here, we used in-situ spectroscopy to detect and differentiate Phytophthora infestans (late blight) and Alternaria solani (early blight) on potato foliage over the course of disease development and explored non-destructive characterization of contrasting disease physiology. Phytophthora infestans, a hemibiotrophic pathogen, undergoes an obligate latent period of two–seven days before disease symptoms appear. In contrast, A. solani, a necrotrophic pathogen, causes symptoms to appear almost immediately when environmental conditions are conducive. We found that respective patterns of spectral change can be related to these differences in underlying disease physiology and their contrasting pathogen lifestyles. Hyperspectral measurements could distinguish both P. infestans-infected and A. solani-infected plants with greater than 80% accuracy two–four days before visible symptoms appeared. Individual disease development stages for each pathogen could be differentiated from respective controls with 89–95% accuracy. Notably, we could distinguish latent P. infestans infection from both latent and symptomatic A. solani infection with greater than 75% accuracy. Spectral features important for late blight detection shifted over the course of infection, whereas spectral features important for early blight detection remained consistent, reflecting their different respective pathogen biologies. Shortwave infrared wavelengths were important for differentiation between healthy and diseased, and between pathogen infections, both pre- and post-symptomatically. This proof-of-concept work supports the use of spectroscopic systems as precision agriculture tools for rapid and early disease detection and differentiation tools, and highlights the importance of careful consideration of underlying pathogen biology and disease physiology for crop disease remote sensing.

The capability of unmanned aerial vehicle (UAV) spectral imagery to assess maize yield under full and deficit irrigation is demonstrated by a Tetracam MiniMCA12 11 bands camera. The MiniMCA12 was used to image an experimental field of 19 maize hybrids. Yield prediction models were explored for different maize development stages, with the best model found using maize plant development stage reproductive 2 (R2) for both maize grain yield and ear weight (respective R2 values of 0.73 and 0.49, and root mean square error of validation (RMSEV) values of 2.07 and 3.41 metric tons per hectare using partial least squares regression (PLS-R) validation models). Models using vegetation indices for inputs rather than superspectral data showed similar R2 but higher RMSEV values, and produced best results for the R4 development stage. In addition to being able to predict yield, spectral models were able to distinguish between different development stages and irrigation treatments. These abilities potentially allow for yield prediction of maize plants whose development stage and water status are unknown.