Leaf Reflectance Spectra Research Articles

Expression of Trichoderma spp. endochitinase gene improves red rot disease resistance in transgenic sugarcane.

Sugarcane (Saccharum spp.)is an economically useful crop grown globally for sugar, ethanol and biofuel production. The crop is vulnerable to fungus Colletotrichum falcatum known to cause red rot disease. The pathogen hydrolyses stalk parenchyma cells where sucrose is accumulated resulting in upto 75% losses in sugar recovery. In this study, transgenic sugarcane having resistance against red rot was developed by introducing Trichoderma spp. endochitinase following Agrobacterium mediated transformation. The transgene introduction and expression in genetically modified plants were verified through qRT-PCR revealing upto 6-fold enhancement in endochitinase expression than non-transgenic plants. Hyperspectral Imaging of transgenic plants displayed altered leaf reflectance spectra and vegetative indices that were positively correlated with ransgene expression. The bioassay with virulent pathotypes of C. falcatumCF08 and CF13 known for epiphytotic occurrence resulted in identification of resistant plant Chit 3-13.The plants with higher reflectance also displayed improved disease resistance, implying their early classification into resistant/susceptible. The losses in sucrose content were minimized (up to 4-fold) in inoculated resistant plant Chit 3-13 as compared to susceptible non-transgenic plant, and a fewer pathogen hyphae were detected in vascular cells of the former through optical microscopy. The electron micrographs confirmed sucrose-filled stalk parenchyma cells in Chit 3-13; in contrast, cells of non-transgenic inoculated plant were depleted of sucrose. The active sites involved in cleaving 1-4 β-glycoside bonds of N-acetyl-d-glucosaminein the pathogen hyphal walls were detected through endochitinase protein structural modelling. The transgenic sugarcane is an important source for in trogressingred rot resistance in plant breeding programs.

Integrating non-invasive VIS-NIR and bioimpedance spectroscopies for stress classification of sweet basil (Ocimum basilicum L.) with machine learning

Plant stress diagnosis is essential for efficient crop management and productivity increase. Under stress, plants undergo physiological and compositional changes. Vegetation indices obtained from leaf reflectance spectra and bioimpedance spectroscopy provide information about the external and internal aspects of plant responses, respectively. In this study, bioimpedance and vegetation indices were noninvasively acquired from sweet basil (Ocimum basilicum L.) leaves exposed to three types of stress (drought, salinity, and chilling). Integrating the vegetation index, a novel approach, contains information about the surface of plants and bioimpedance data, which indicates the internal changes of plants. The fusion of these two datasets was examined to classify the types and severity of stress. Among the eight supervised machine learning models (three linear and five non-linear), the support vector machine (SVM) exhibited the highest accuracy in classifying stress types. Bioimpedance spectroscopy alone exhibited an accuracy of 0.86 and improved to 0.90 when fused with vegetation indices. Additionally, for drought and salinity stresses, it was possible to classify the early stage of stress with accuracies of 0.95 and 0.93, respectively. This study will allow us to classify the different types and severity of plant stress, prescribe appropriate treatment methods for efficient cost and time management of crop production, and potentially apply them to low-cost field measurement systems.

Grass Evolutionary Lineages Can Be Identified Using Hyperspectral Leaf Reflectance

AbstractHyperspectral remote sensing has the potential to map numerous attributes of the Earth’s surface, including spatial patterns of biological diversity. Grasslands are one of the largest biomes on Earth. Accurate mapping of grassland biodiversity relies on spectral discrimination of endmembers of species or plant functional types. We focused on spectral separation of grass lineages that dominate global grassy biomes: Andropogoneae (C4), Chloridoideae (C4), and Pooideae (C3). We examined leaf reflectance spectra (350–2,500 nm) from 43 grass species representing these grass lineages from four representative grassland sites in the Great Plains region of North America. We assessed the utility of leaf reflectance data for classification of grass species into three major lineages and by collection site. Classifications had very high accuracy (94%) that were robust to site differences in species and environment. We also show an information loss using multispectral sensors, that is, classification accuracy of grass lineages using spectral bands provided by current multispectral satellites is much lower (accuracy of 85.2% and 61.3% using Sentinel 2 and Landsat 8 bands, respectively). Our results suggest that hyperspectral data have an exciting potential for mapping grass functional types as informed by phylogeny. Leaf‐level hyperspectral separability of grass lineages is consistent with the potential increase in biodiversity and functional information content from the next generation of satellite‐based spectrometers.

Novel spectral indices for enhanced estimations of 3-dimentional flavonoid contents for Ginkgo plantations using UAV-borne LiDAR and hyperspectral data

Leaf flavonoid content (LFC) is a marked indicator of the protection signals from biotic and abiotic stresses, as well as the potential in the recovery of phenolic compounds from plants for producing potent antioxidants. LFC has been non-destructively retrieved from leaf reflectance spectra in recent studies. However, the LFC estimation from canopy-level spectra remains poorly understood and challenging arise from the confounding effects of other pigments and canopy structure. To address this limitation, this study proposed a suite of new 3-Dimentional spectral indices (SIs), in which the leaf-level standard flavonoid indices (FIs) are normalized by structure indices or chlorophyll indices. The hypothesis investigated is that these new SIs, derived from UAV-based hyperspectral point cloud data (fused by canopy hyperspectral images and LiDAR point cloud data), can enhance detecting LFC distribution within the canopies of Ginkgo plantations, by mitigating the effects of canopy structure and chlorophyll absorption. The results demonstrated that most chlorophyll-based normalized indices (CV-R2 = 0.56–0.65) outperformed the structure-based normalized indices (CV-R2 = 0.44–0.57) and the standard FIs (CV-R2 = 0.19–0.54). In specific, FI420,710/SR800,710 (CV-R2 = 0.65) out of chlorophyll-based normalized indices performed better than other indices. With the use of FI420,710/SR800,710, the 3-Dimentional distribution of LFC within Ginkgo canopies can be well mapped. In summary, this study indicates marked potentials of the developed normalized indices for mapping LFC distribution, as well as providing new insight into alleviating the confounding effects of chlorophyll and structure on LFC estimation of Ginkgo plantations, with simulations conducted by the canopy radiative transfer model.

Evaluating potential of leaf reflectance spectra to monitor plant genetic variation

Remote sensing of vegetation by spectroscopy is increasingly used to characterize trait distributions in plant communities. How leaves interact with electromagnetic radiation is determined by their structure and contents of pigments, water, and abundant dry matter constituents like lignins, phenolics, and proteins. High-resolution (“hyperspectral”) spectroscopy can characterize trait variation at finer scales, and may help to reveal underlying genetic variation—information important for assessing the potential of populations to adapt to global change. Here, we use a set of 360 inbred genotypes of the wild coyote tobacco Nicotiana attenuata: wild accessions, recombinant inbred lines (RILs), and transgenic lines (TLs) with targeted changes to gene expression, to dissect genetic versus non-genetic influences on variation in leaf spectra across three experiments. We calculated leaf reflectance from hand-held field spectroradiometer measurements covering visible to short-wave infrared wavelengths of electromagnetic radiation (400–2500 nm) using a standard radiation source and backgrounds, resulting in a small and quantifiable measurement uncertainty. Plants were grown in more controlled (glasshouse) or more natural (field) environments, and leaves were measured both on- and off-plant with the measurement set-up thus also in more to less controlled environmental conditions. Entire spectra varied across genotypes and environments. We found that the greatest variance in leaf reflectance was explained by between-experiment and non-genetic between-sample differences, with subtler and more specific variation distinguishing groups of genotypes. The visible spectral region was most variable, distinguishing experimental settings as well as groups of genotypes within experiments, whereas parts of the short-wave infrared may vary more specifically with genotype. Overall, more genetically variable plant populations also showed more varied leaf spectra. We highlight key considerations for the application of field spectroscopy to assess genetic variation in plant populations.

Quantitative monitoring of salt stress in rice with solar-induced chlorophyll fluorescence

Under salt stress, rice leaves usually accumulate sodium and chloride ions, causing water loss. The consequent nutrition imbalance and damage to photosynthetic systems ultimately affects growth and development. Therefore, early identification of rice salt stress is important for timely amelioration to reduce rice yield loss. Solar-induced chlorophyll fluorescence (SIF) shows substantial effectiveness for its quick and sensitive response to early-stage stress, suggesting its potential for early crop stress detection. To further assess the capacity of SIF for salt stress detection, this study conducted field plot experiments with a single rice cultivar across two growth stages – jointing and booting. The leaf reflectance spectrum of rice was obtained using an ASD FieldSpec Pro FR portable field spectrometer (Analytical Spectral Devices, Boulder, Colorado, USA) and a leaf clip holder. The leaf solar-induced chlorophyll fluorescence (SIF) spectrum was obtained from an ASD coupling filter and FluoWat, which filters out incident sunlight beyond 650 nm. We calculated nine SIF yield indices (FYs), including ↑FY687 (upward fluorescence yield at 687 nm), ↑FY739 (upward fluorescence yield at 739 nm), ↓FY739 (downward fluorescence yield at 739 nm), totFY687 (total of upward and downward fluorescence yield at 687 nm), totFY739 (total upward and downward fluorescence yield at 739 nm). We also explored the adaptive regulation of three biological rice parameters under salt stress: the net photosynthetic rate (Photo), chlorophyll content (Chl), and maximum photochemical efficiency of photosystem II (Fv/Fm). Photo was the most sensitive to salt stress, and showed significant differences on the first day under salt stress. A salt stress response index (SSRI), which combines physiological and biochemical parameters, was constructed to describe the salt stress level. SSRI showed a significant difference on the first day of salt stress, and the dynamics of SSRI were consistent with that of Photo. In addition, we clarified the change rule of SIF for rice leaves under the salt stress. The gray correlation analysis identified five SIF fluorescence yield indices (FYs) that are highly correlated with SSRI: totFY739, ↓FY739, ↑FY739, totFY687, and ↑FY687. Based on the results of gray correlation analysis, a support vector regression model of SSRI was established, which gave an excellent result as follow: R2 of the calibration for the all dataset, booting dataset, and jointing dataset were 0.74, 0.74, and 0.70, respectively, and R2 of the validation data were 0.71, 0.73, and 0.68. In summary, the proposed method to quantitatively detect rice leaf salt stress based on SIF technology allows the early monitoring of rice leaf salt stress.

Evaluation of forage quality in a pea breeding program using a hyperspectral sensing system

Forage quality evaluation is essential in breeding and selecting forage crops to improve livestock health and reduce greenhouse gas emissions. A non-destructive and high-throughput process to assess forage quality can advance cultivar development research and commercial feed analysis. The overall objective of this study was to estimate 12 biomass quality traits of field peas in the 2019 and 2020 field seasons using in-field hyperspectral spectroscopy (350–2500 nm) at the leaf level. Six machine-learning models were utilized to develop the relationships between each quality trait and four feature extraction datasets (first derivative reflectance data, vegetation indices, normalized difference spectral indices, and ratio spectral indices) of leaf reflectance spectra from the hyperspectral data. The high and consistent performance of all quality traits was produced from only ridge regression, elastic net regression, and random forest regression models in first derivative reflectance and vegetation indices datasets. In addition, higher prediction performance (0.81 < R2 < 0. 93; 0.05 < root mean square error (%) < 1.80; 0.03 < mean absolute error (%) < 1.32) was found in the random forest model using normalized difference spectral indices and ratio spectral indices datasets after utilizing a feature selection technique (leave one feature out). The results suggest that the proposed evaluation approach of spectroscopy may be applied to predict field pea quality traits in a timely fashion to assist breeders and farmers in their decision-making.

Why are biting flies attracted to blue objects?

Diurnal biting flies are strongly attracted to blue objects. This behaviour is widely exploited for fly control, but its functional significance is debated. It is hypothesized that blue objects resemble animal hosts; blue surfaces resemble shaded resting places; and blue attraction is a by-product of attraction to polarized light. We computed the fly photoreceptor signals elicited by a large sample of leaf and animal integument reflectance spectra, viewed under open/cloudy illumination and under woodland shade. We then trained artificial neural networks (ANNs) to distinguish animals from leaf backgrounds, and shaded from unshaded surfaces, in order to find the optimal means of doing so based upon the sensory information available to a fly. After training, we challenged ANNs to classify blue objects used in fly control. Trained ANNs could make both discriminations with high accuracy. They discriminated animals from leaves based upon blue-green photoreceptor opponency and commonly misclassified blue objects as animals. Meanwhile, they discriminated shaded from unshaded stimuli using achromatic cues and never misclassified blue objects as shaded. We conclude that blue-green opponency is the most effective means of discriminating animals from leaf backgrounds using a fly's sensory information, and that blue objects resemble animal hosts through such mechanisms.

Miniaturized Vis–NIR handheld spectrometer for non-invasive pigment quantification in agritech applications

Advanced precision agriculture requires the objective measurement of the structural and functional properties of plants. Biochemical profiles in leaves can differ depending on plant growing conditions. By quantitatively detecting these changes, farm production processes can be optimized to achieve high-yield, high-quality, and nutrient dense agricultural products. To enable the rapid and non-destructive detection on site, this study demonstrates the development of a new custom-designed portable handheld Vis–NIR spectrometer that collects leaf reflectance spectra, wirelessly transfers the spectral data through Bluetooth, and provides both raw spectral data and processed information. The spectrometer has two preprogramed methods: anthocyanin and chlorophyll quantification. Anthocyanin content of red and green lettuce estimated with the new spectrometer showed an excellent correlation coefficient of 0.84 with those determined by a destructive gold standard biochemical method. The differences in chlorophyll content were measured using leaf senescence as a case study. Chlorophyll Index calculated with the handheld spectrometer gradually decreased with leaf age as chlorophyll degrades during the process of senescence. The estimated chlorophyll values were highly correlated with those obtained from a commercial fluorescence-based chlorophyll meter with a correlation coefficient of 0.77. The developed portable handheld Vis–NIR spectrometer could be a simple, cost-effective, and easy to operate tool that can be used to non-invasively monitor plant pigment and nutrient content efficiently.

Towards automated detection of hyperhydricity in plant in vitro culture

Hyperhydricity (HH) is one of the most important physiological disorders that negatively affects various plant tissue culture techniques. The objective of this study was to characterize optical features to allow an automated detection of HH. For this purpose, HH was induced in two plant species, apple and Arabidopsis thaliana, and the severity was quantified based on visual scoring and determination of apoplastic liquid volume. The comparison between the HH score and the apoplastic liquid volume revealed a significant correlation, but different response dynamics. Corresponding leaf reflectance spectra were collected and different approaches of spectral analyses were evaluated for their ability to identify HH-specific wavelengths. Statistical analysis of raw spectra showed significantly lower reflection of hyperhydric leaves in the VIS, NIR and SWIR region. Application of the continuum removal hull method to raw spectra identified HH-specific absorption features over time and major absorption peaks at 980 nm, 1150 nm, 1400 nm, 1520 nm, 1780 nm and 1930 nm for the various conducted experiments. Machine learning (ML) model spot checking specified the support vector machine to be most suited for classification of hyperhydric explants, with a test accuracy of 85% outperforming traditional classification via vegetation index with 63% test accuracy and the other ML models tested. Investigations on the predictor importance revealed 1950 nm, 1445 nm in SWIR region and 415 nm in the VIS region to be most important for classification. The validity of the developed spectral classifier was tested on an available hyperspectral image acquisition in the SWIR-region.

Discerning Oriental from European beech by leaf spectroscopy: Operational and physiological implications

European beech (Fagus sylvatica L.) forests have recently experienced severe diebacks that are expected to increase in future. Oriental beech (Fagus sylvatica spp. orientalis (Lipsky) Greut. & Burd) is a potential candidate for assisted migration (AM) in European forests due to its greater genetic diversity and potentially higher drought resistance. Yet AM entails not only benefits, but also risks, and it is therefore important to monitor the progression of introduced (sub)species. Here, we demonstrate the potential of leaf spectroscopy to replace resource-intensive genetic analysis and field phenotyping for the discrimination and characterization of these two beech subspecies.We studied two European beech forests, one in France and one in Switzerland, where Oriental beech from the Greater Caucasus was introduced over 100 years ago. During two summers (2021, 2022), we measured leaf spectral reflectance, leaf morphological and biochemical traits from genotyped adult trees. Subspecies prediction models were developed separately for top-of-canopy leaves (amenable to remote sensing) and bottom-of-canopy leaves (easier to harvest) using partial least squares discriminant analysis (PLS-DA) and different sets of spectral predictors.Morphological, biochemical and spectra-derived leaf traits indicated that Oriental beech trees at the sites studied were characterized by higher lignin and nitrogen per unit leaf area than European beech, suggesting more protein-rich leaves on a per-area basis. The model based on top-of-canopy leaf reflectance spectra in the short-wave-infrared region (SWIR I: 1450–1750 nm) most accurately distinguished Oriental from European beech (BA = 0.86 ± 0.08, k = 0.72 ± 0.15), closely followed by models based on SWIR II, and on spectra-derived traits (BA ≥ 0.84, k ≥ 0.67).This study provides a proof-of-principle for the development of spectroscopy-based approaches when monitoring introduced species, subspecies or provenances. Our findings hold promise for upscaling to large forest areas using airborne remote sensing.

Detecting Grapevine Virus Infections in Red and White Winegrape Canopies Using Proximal Hyperspectral Sensing.

Grapevine virus-associated disease such as grapevine leafroll disease (GLD) affects grapevine health worldwide. Current diagnostic methods are either highly costly (laboratory-based diagnostics) or can be unreliable (visual assessments). Hyperspectral sensing technology is capable of measuring leaf reflectance spectra that can be used for the non-destructive and rapid detection of plant diseases. The present study used proximal hyperspectral sensing to detect virus infection in Pinot Noir (red-berried winegrape cultivar) and Chardonnay (white-berried winegrape cultivar) grapevines. Spectral data were collected throughout the grape growing season at six timepoints per cultivar. Partial least squares-discriminant analysis (PLS-DA) was used to build a predictive model of the presence or absence of GLD. The temporal change of canopy spectral reflectance showed that the harvest timepoint had the best prediction result. Prediction accuracies of 96% and 76% were achieved for Pinot Noir and Chardonnay, respectively. Our results provide valuable information on the optimal time for GLD detection. This hyperspectral method can also be deployed on mobile platforms including ground-based vehicles and unmanned aerial vehicles (UAV) for large-scale disease surveillance in vineyards.

GSV-L: A general spectral vector model for hyperspectral leaf spectra simulation

Leaf optical spectra determine vegetation canopy optical spectra. Physically based leaf models are relatively complicated as they require many biophysical and biochemical parameters that are usually difficult to obtain. The aim of this study is to develop a new empirical model, the general spectral vector-leaf (GSV-L) model using globally collected leaf spectra data. A global field-measured leaf spectra database, including 66,478 leaf reflectance and 3575 transmittance spectra in the wavelength range of 400–2400 nm, was first constructed. The singular value decomposition (SVD) method was applied to the field data matrix to derive the spectral vectors for leaf spectral modeling. The SVD method was also compared with the successive approximation (SA) and principal component analysis (PCA) methods using the same training and validation datasets, and the GSV-L model was compared with two other physical models, PROSPECT and LEAF-SIP. The GSV-L model can be used to simulate full leaf reflectance and transmittance spectra using a few wavelengths in different bands with very high R2 (0.99, 0.99), small RMSE (0.014, 0.014) and bias (0, 0.002) values. The model also performs better than the PROSPECT and LEAF-SIP models for leaf spectral simulation. The coefficients of the reflectance spectral vectors can be used to estimate leaf structure parameters, equivalent water thickness, and leaf biochemical contents. As an efficient and accurate approach for leaf hyperspectral modeling, GSV-L can also be integrated with various canopy reflectance and land surface models.

Variation in Leaf Reflectance Spectra Across the California Flora Partitioned by Evolutionary History, Geographic Origin, and Deep Time

AbstractEvolutionary relatedness underlies patterns of functional diversity in the natural world. Hyperspectral remote sensing has the potential to detect these patterns in plants through inherited patterns of leaf reflectance spectra. We collected leaf reflectance data across the California flora from plants grown in a common garden. Regions of the reflectance spectra vary in the depth and strength of phylogenetic signal. We also show that these differences are much greater than variation due to the geographic origin of the plant. At the phylogenetic extent of the California flora, spectral variation explained by the combination of ecotypic variation (divergent evolution) and convergent evolution of disparate lineages was minimal (3%–7%) but statistically significant. Interestingly, at the extent of a single genus (Arctostaphylos) no unique variation could be attributed to geographic origin. However, up to 18% of the spectral variation among Arctostaphylos individuals was shared between phylogeny and intraspecific variation stemming from ecotypic differences (i.e., geographic origin). Future studies could conduct more structured experiments (e.g., transplants or observations along environmental gradients) to disentangle these sources of variation and include other intraspecific variation (e.g., plasticity). We constrain broad‐scale spectral variability due to ecotypic sources, providing further support for the idea that phylogenetic clusters of species might be detectable through remote sensing. Phylogenetic clusters could represent a valuable dimension of biodiversity monitoring and detection.

Recuperação do teor de clorofila de folhas em laranja do umbigo Gannan com base na fusão de índices de vegetação hiperespectral usando algoritmos de inteligência artificial

ABSTRACT: Estimating leaf chlorophyll contents through leaf reflectance spectra is efficient and nondestructive. The literature base regarding optical indices (particularly chlorophyll indices) is wide ranging and extensive. However, it is without much consensus regarding robust indices for Gannan navel orange. To address this problem, this study investigated the performance of 19 published indices using RDS (raw data spectrum), FDS (first derivative data spectrum) and SDS (second derivative data spectrum) for the estimation of chlorophyll content in navel orange leaves. The single spectral index and combination of multiple spectral indices were compared for their accuracy in predicting chlorophyll a content (Chla), chlorophyll b content (Chlb) and total chlorophyll content (Chltot) content in navel orange leaves by using partial least square regression (PLSR), adaboost regression (AR), random forest regression (RFR), decision tree regression (DTR) and support vector machine regression (SVMR) models. Through the comparison of the above data in three datasets, the optimal modeling data set is RDS data, followed by FDS data, and the worst is SDS data. In modeling with multiple spectral indices, good results were obtained for Chla (NDVI750, NDVI800), Chlb (Datt, DD, Gitelson 2) and Chltot (Datt, DD, Gitelson2) by corresponding index combinations. Overall, we can find that the AR is also the best regression method judging by prediction performance from the results of single spectral index models and multiple spectral indices models. In comparison, result of multiple spectral indices models is better than single spectral index models in predicting Chla and Chltot content using FDS data and SDS data, respectively.

Classification of Plant Endogenous States Using Machine Learning-Derived Agricultural Indices.

Leaf color patterns vary depending on leaf age, pathogen infection, and environmental and nutritional stresses; thus, they are widely used to diagnose plant health statuses in agricultural fields. The visible-near infrared-shortwave infrared (VIS-NIR-SWIR) sensor measures the leaf color pattern from a wide spectral range with high spectral resolution. However, spectral information has only been employed to understand general plant health statuses (e.g., vegetation index) or phytopigment contents, rather than pinpointing defects of specific metabolic or signaling pathways in plants. Here, we report feature engineering and machine learning methods that utilize VIS-NIR-SWIR leaf reflectance for robust plant health diagnostics, pinpointing physiological alterations associated with the stress hormone, abscisic acid (ABA). Leaf reflectance spectra of wild-type, ABA2-overexpression, and deficient plants were collected under watered and drought conditions. Drought- and ABA-associated normalized reflectance indices (NRIs) were screened from all possible pairs of wavelength bands. Drought associated NRIs showed only a partial overlap with those related to ABA deficiency, but more NRIs were associated with drought due to additional spectral changes within the NIR wavelength range. Interpretable support vector machine classifiers built with 20 NRIs predicted treatment or genotype groups with an accuracy greater than those with conventional vegetation indices. Major selected NRIs were independent from leaf water content and chlorophyll content, 2 well-characterized physiological changes under drought. The screening of NRIs, streamlined with the development of simple classifiers, serves as the most efficient means of detecting reflectance bands that are highly relevant to characteristics of interest.

The Application of Machine Learning Models Based on Leaf Spectral Reflectance for Estimating the Nitrogen Nutrient Index in Maize

Non-destructive acquisition and accurate real-time assessment of nitrogen (N) nutritional status are crucial for nitrogen management and yield prediction in maize production. The objective of this study was to develop a method for estimating the nitrogen nutrient index (NNI) of maize using in situ leaf spectroscopy. Field trials with six nitrogen fertilizer levels (0, 75, 150, 225, 300, and 375 kg N ha−1) were performed using eight summer maize cultivars. The leaf reflectance spectrum was acquired at different growth stages, with simultaneous measurements of leaf nitrogen content (LNC) and leaf dry matter (LDW). The competitive adaptive reweighted sampling (CARS) algorithm was used to screen the raw spectrum’s effective bands related to the NNI during the maize critical growth period (from the 12th fully expanded leaf stage to the milk ripening stage). Three machine learning methods—partial least squares (PLS), artificial neural networks (ANN), and support vector machines (SVM)—were used to validate the NNI estimation model. These methods indicated that the NNI first increased and then decreased (from the 12th fully expanded leaf stage to the milk ripening stage) and was positively correlated with nitrogen application. The results showed that combining effective bands and PLS (CARS-PLS) achieved the best model for NNI estimation, which yielded the highest coefficient of determination (R2val), 0.925, and the lowest root mean square error (RMSEval), 0.068, followed by the CARS-SVM model (R2val, 0.895; RMSEval, 0.081), and the CARS-ANN model (R2val, 0.814; RMSEval, 0.108), which performed the worst. The CARS-PLS model was used to successfully predict the variation in the NNI among cultivars and different growth stages. The estimated R2 of eight cultivars by the NNI was between 0.86 and 0.97; the estimated R2 of the NNI at different growth stages was between 0.92 and 0.94. The overall results indicated that the CARS-PLS allows for rapid, accurate, and non-destructive estimation of the NNI during maize growth, providing an efficient tool for accurately monitoring nitrogen nutrition.

Using Machine Learning for Nutrient Content Detection of Aquaponics-Grown Plants Based on Spectral Data

Nutrients derived from fish feed are insufficient for optimal plant growth in aquaponics; therefore, they need to be supplemented. Thus, estimating the amount of supplementation needed can be achieved by looking at the nutrient contents of the plant. This study aims to develop trustworthy machine learning models to estimate the nitrogen (N), phosphorus (P), and potassium (K) contents of aquaponically grown lettuce. A FieldSpec4, Pro FR portable spectroradiometer (ASD Inc., Analytical Spectral Devices Boulder, Boulder, CO, USA) was used to measure leaf reflectance spectra, and 128 lettuce seedlings given four NPK treatments were used for spectra acquisition and total NPK estimation. Principal component analysis (PCA), genetic algorithms (GA), and sequential forward selection (SFS) were applied to select the optimal wavebands. Partial least squares regression (PLSR), back-propagation neural network (BPNN), and random forest (RF) approaches were used to develop the predictive models of NPK contents using the selected optimal wavelengths. Good and significantly correlated predictive accuracy was obtained in comparison with the laboratory-measured freshly cut lettuce leaves with R2 ≥ 0.94. The proposed approach provides a pathway toward automatic nutrient estimation of aquaponically grown lettuce. Consequently, aquaponics will become more intelligent, and will be adopted as a precision agriculture technology.

Seasonal patterns of spectral diversity at leaf and canopy scales in the Cedar Creek prairie biodiversity experiment

The relationship between biodiversity and spectral diversity is highly scale-dependent, and temporal variation in leaf morphological, biochemical traits and canopy structure can alter this relationship. However, the temporal dependence of the spectral diversity – biodiversity relationship is poorly understood, in part due to the difficulties of obtaining consistent measurements across space and time. Using leaf pigments and leaf and canopy reflectance throughout a growing season in the Cedar Creek prairie biodiversity experiment, we explored phenological effects on the scale dependence of the spectral biodiversity – biodiversity relationship. Leaf reflectance spectra displayed larger among-species variation than leaf pigments, indicating that leaf reflectance contained more information for distinguishing species than some leaf trait measurements. At the canopy scale, spectral variation derived using reflectance was mainly driven by among-species variation. The canopy scale spectral diversity was also influenced by changing vegetation percent cover, key phenological events (e.g., flowering), and disturbance (drought). Our results revealed that contrasting phenological patterns of spectral diversity metrics emerged at leaf and canopy scales. Because a misunderstanding of these contrasting temporal effects across spatial scales can lead to possible misinterpretations of the spectral diversity – biodiversity relationship or of their underlying causes, more research effort is needed to understand these cross-scale temporal effects.

Hyperspectral and genome-wide association analyses of leaf phosphorus status in local Thai indica rice

Phosphorus (P) is an essential mineral nutrient and one of the key factors determining crop productivity. P-deficient plants exhibit visual leaf symptoms, including chlorosis, and alter spectral reflectance properties. In this study, we evaluated leaf inorganic phosphate (Pi) contents, plant growth and reflectance spectra (420–790 nm) of 172 Thai rice landrace varieties grown hydroponically under three different P supplies (overly sufficient, mildly deficient and severely deficient conditions). We reported correlations between Pi contents and reflectance ratios computed from two wavebands in the range of near infrared (720–790 nm) and visible energy (green-yellow and red edge) (r > 0.69) in Pi-deficient leaves. Artificial neural network models were also developed which could classify P deficiency levels with 85.60% accuracy and predict Pi content with R2 of 0.53, as well as highlight important waveband sections. Using 217 reflectance ratio indices to perform genome-wide association study (GWAS) with 113,114 SNPs, we identified 11 loci associated with the spectral reflectance traits, some of which were also associated with the leaf Pi content trait. Hyperspectral measurement offers a promising non-destructive approach to predict plant P status and screen large germplasm for varieties with high P use efficiency.