Red-edge Region Research Articles

Sentinel-2 Poplar Index for Operational Mapping of Poplar Plantations over Large Areas

Poplar (Populus spp.) is a fast-growing tree planted to meet the growing global demand for wood products. In France, the country with the largest area planted with poplar in Europe, accurate and up-to-date maps of its spatial distribution are not available at the national scale. This makes it difficult to estimate the extent and location of the poplar resource and calls for the development of a robust and timely stable approach for mapping large areas in order to ensure efficient monitoring. In this study, we investigate the potential of the Sentinel-2 time series to map the diversity of poplar plantations at the French countrywide scale. By comparing multiple configurations of spectral features based on spectral bands and indices over two years (2017 and 2018), we identify the optimal spectral regions with their respective time periods to distinguish poplar plantations from other deciduous species. We also define a novel poplar detection index (PI) with four variants that combine the best discriminative spectral bands. The results highlight the relevance of SWIR followed by red edge regions, mainly in the growing season, to accurately detect poplar plantations, reflecting the sensitivity of poplar trees to water content throughout their phenological cycle. The best performances with stable results were obtained with the PI2 poplar index combining the B5, B11, and B12 spectral bands. The PI2 index was validated over two years with an average producer’s accuracy of 92% in 2017 and 95% in 2018. This new index was used to produce the national map of poplar plantations in 2018. This study provides an operational approach for monitoring the poplar resource over large areas for forest managers.

Assessing rice blast disease severity through hyperspectral remote sensing

Remote sensing is being increasingly used in stress management in different agricultural practices. It is useful for real time analysis for crop stress which is not possible for visual observation alone. Rice blast caused by fungus Pyricularia Oryzae is a serious constrain in rice production in India. There is hardly any basic information available for spectral characteristics of rice blast disease for its real-time detection and management. Present study is to characterize spectral reflectance of blast affected rice in order to identify the sensitive spectral range. Disease severity of 10 different genotypes of rice was graded 0 to 9 based on the extent of host organ covered by symptom or lesion. Result shows that severely infected plant (score 9) have higher reflectance at visible region and lower reflectance at NIR region. Change in the reflectance for the infected plant as compare to the healthy plant was more pronounced in the VNIR, 550 to 760 nm and 1140 and 1300 nm having correlation coefficient above 0.6. The study of change in the reflectance with the change in wavelength (1st derivative) revealed that VNIR region have high correlation with the disease severity. Maximum rate of change value at red edge position (REP) is called as red edge value (REV) which has good relation with disease severity levels. Amplitude of the red edge peak decreases with the increase in severity levels. Amplitude of score 0 and 9 was 0.00929 and 0.002301, respectively for upland land condition whereas the amplitude of the score 0 and 9 was 0.010421 and 0.00193, respectively for upland land rice. This study identifies that VNIR and red edge region are sensitive for detecting rice blast, which could be utilized to aerial or satellite based monitoring blast affected rice cropping region.

The Impact of NPV on the Spectral Parameters in the Yellow-Edge, Red-Edge and NIR Shoulder Wavelength Regions in Grasslands

Even though research has shown that the spectral parameters of yellow-edge, red-edge and NIR (near-infrared) shoulder wavelength regions are able to estimate green cover and leaf area index (LAI), a large amount of dead materials in grasslands challenges the accuracy of their estimation using hyperspectral remote sensing. However, the exact impact of dead vegetation cover on these spectral parameters remains unclear. Therefore, we evaluated the influences of dead materials on the spectral parameters in the wavelength regions of yellow-edge, red-edge and NIR shoulder by comparing normalized difference vegetation indices (NDVI) including the common red valley at 670 nm and NDVI using the red valley extracted by a new statistical method. This method, based on the concept of segmented linear regression, was developed to extract the spectral parameters and calculate NDVI automatically from the hyper-spectra. To fully understand the impact of dead cover on the spectral parameters (i.e., consider full coverage combinations of green vegetation, dead materials and bare soil), both in situ measured and simulated hyper-spectra were analyzed. The impact of dead cover on LAI estimation by those spectral parameters and NDVI were also evaluated. The results show that: (i) without considering the influence of bare soil, dead materials decreases the slope of red-edge, the slope of NIR shoulder and NDVI, while dead materials increases the slope of yellow-edge; (ii) the spectral characteristics of red valley disappear when dead cover exceeds 67%; (iii) large amount of dead materials also result in a blue shift of the red-edge position; (iv) accurate extraction of the red valley position enhances LAI estimation and reduces the influences of dead materials using hyperspectral NDVI; (v) the accuracy of LAI estimation using the slope of yellow-edge, the slope of red-edge, red-edge position and NDVI significantly drops when dead cover exceeds 72.3–74.5% (variation among indices).

Suitability of different multivariate analysis methods for monitoring leaf N accumulation in winter wheat using in situ hyperspectral data

Leaf nitrogen accumulation (LNA) is an important indicator of crop growth, and the real-time and nondestructive estimation of LNA by hyperspectral remote sensing is crucial for crop N management. In this study, five field experiments were conducted over four successive years at three ecological sites (Xinyang, Zhengzhou and Zhoukou) in Henan, China, incorporating different N amounts and wheat varieties. The canopy spectral data were obtained by a ground-based spectrometer, and the original spectral reflectance (R) was transformed using continuum removal (CR), first-derivative reflectance (FDR) and inverse-log reflectance (log (1/R)) methods. The effective bands of the above four transformed reflectance data were selected by the variable importance in projection (VIP) scores of the partial least square regression method (PLSR). Then, four multivariate regression methods (PLSR, stepwise multiple linear regression (SMLR), extreme learning machine (ELM) and support vector machine (SVM)) were used to develop an optimal forecasting model for LNA in winter wheat. The results show that FDR spectral data had the best comprehensive performance and were a better method for spectral data preprocessing. In the comparison of different nonparametric algorithms, the SVM model performed the best using the full wavelengths, in which R2cal/val and RMSEcal/val were 0.927–0.963/0.899–0.925 and 0.725–1.066/1.161–1.331 g m−2, respectively. The characteristic bands of FDR were mainly distributed in the visible light and red edge regions (445, 501, 546, 683, 747 and 771 nm, respectively), and these effective bands were consistent under different field conditions. The SVM regression method using the effective wavelengths of FDR exhibited excellent performance for LNA prediction with R2val = 0.875 and RMSEval = 1.294. In addition, the FDR-PLSR-SVM model produced satisfactory inversion results under different field conditions. The accuracy of the filling period was better than that of the reviving-anthesis growth period, which might be due to diminished N dilution and stable canopy structure during the reproductive stage. R2val and RMSEval of the FDR-PLSR-SVM model during the filling period were 0.914 and 1.156 g m−2 in Xinyang, 0.825 and 1.542 g m−2 in Zhengzhou and 0.796 and 1.902 g m−2 in Zhoukou, respectively. Considering the advantages of simple and efficient computer calculations, the FDR-PLSR-SVM algorithm is strongly recommended to predict the LNA in winter wheat. This study provides a reference basis for the selection of effective wavelengths for N nutrition diagnosis by unmanned aerial vehicles and satellite remote sensing in the future.

Newly-developed three-band hyperspectral vegetation index for estimating leaf relative chlorophyll content of mangrove under different severities of pest and disease

Hyperspectral imaging-derived vegetation indices (VIs) have rarely been developed to estimate leaf chlorophyll content of mangrove forests under pest and disease stress. Moreover, the optimal newly-developed hyperspectral VI is generally chosen through comparison of model accuracy alone with all possible VI combinations, which might render the conclusion one-sided. With SOC710 hyperspectral images of 119 mangrove leaf samples, this study aimed to develop a new hyperspectral VI sensitive to leaf relative chlorophyll content (SPAD value) by comprehensive comparison from five aspects (estimation accuracy, sensitivity, anti-noise performance, application to simulated EnMAP and PRISMA sensors, and spatial visualization quality). Eight types of newly-developed VIs were constructed from the sensitive wavebands selected by successive projection algorithm (SPA) method, and simple linear regression model was established using each VI. The results showed that the three-band VI ((λ757.9-λ709.4)/(λ709.4-λ708.1)) was the optimal for leaf SPAD estimation, because it had stronger correlation with SPAD, higher model accuracy of SPAD estimation using leaf and simulated hyperspectral imageries, stronger resistance to Gaussian noise, more sensitivity to extremely high chlorophyll content, and reasonable spatial visualization of SPAD. The four types of three-band VIs had higher model accuracy than the four types of two-band VIs, while two-band VIs had stronger resistance to higher Gaussian noise. Moreover, the wavelengths in the red edge region were efficient to develop hyperspectral VIs sensitive to leaf SPAD, and leaf SPAD could be more accurately estimated with pest and disease severity of 15–25%. We concluded that three-band VI consisting wavebands in the red edge region derived from leaf hyperspectral images is effective in capturing the changes of leaf chlorophyll content, which could provide great potentials for early warning of mangrove pest and disease with fine visualization details of chlorophyll content.

Machine learning-based prediction of nutritional status in oil palm leaves using proximal multispectral images

This study evaluated the application of proximal multispectral images accompanied by 4 machine learning approaches for estimating the nutritional status of oil palm leaves. The image responded for five bands: blue, green, red, red edge, and near-infrared regions with a center wavelength of 475, 560, 668, 717, and 840 nm. Average and standard deviation (SD) values from the leaf pixels of each band were extracted, obtaining 5 average and 5 SD values from 5 bands. Thirty-four vegetation variables were generated based on those average and SD values. In total, forty-four variables consisted of 10 average-and SD-based features, and 34 vegetation variables were used as the input candidates for analyses against 10 target variables: nitrogen (N), phosphorus (P), potassium (K), calcium (Ca), magnesium (Mg), iron (Fe), manganese (Mn), zinc (Zn), boron (B), and chlorophyll (SPAD). No significant input came out for modeling with P and Zn based on the stepwise selection. Therefore, 8 nutritional models were proposed in this study. A training set with 50 samples was used to be modeled for each target, and a test set with 15 samples was employed to evaluate the models' performances. Based on random forest (RF), support vector regression (SVR), partial least square regression (PLSR), and artificial neuron network (ANN) applied to be modeled, the models for chlorophyll, N, and Ca predictions were acceptable for screening, and those for K and Mg predictions were acceptable for rough screening. The chlorophyll model developed based on the RF had the predictive statistics in terms of coefficient of determination for prediction (r2), root mean square error of prediction (RMSEP), and standard error of prediction (SEP) of 0.752, 5.46 SPAD, and 5.65 SPAD, respectively. The other 2 screening models developed based on SVR and RF for N and Ca, respectively, gave the performances with the r2, RMSEP, and SEP ranging from 0.655 to 0.718, 0.12 to 0.17%, and 0.12 to 0.18%, respectively. In the case of the 2 rough screening models established using the RF algorithm, the predictive statistics ranged from 0.496 to 0.530 for the r2 and 0.07–0.16% for both RMSEP and SEP. In this study, the Fe, Mn, and B models had poor results presenting the range of r2, RMSEP, and SEP of 0.308–0.491, 2.39–72.9 ppm, and 2.45–62.8 ppm, respectively. Based on the results, this study confirmed that the proximal multispectral information of oil palm leaves had enough significance to account for the status of chlorophyll and macro-nutrients: N, K, Ca, and Mg in the leaves.

Uncertainty in the evaluation of photosynthetic canopy traits using the green leaf area index

The green leaf area index (GLAI) has been widely used in agriculture, forestry, and environmental sciences for the analysis and modeling of many biophysical processes of vegetation, including the attenuation of light through the canopy, transpiration, photosynthesis, and carbon and nutrient cycles. Nevertheless, its usefulness is hampered by the uncertainty introduced through the lack of quantitative information on leaf biochemistry, particularly leaf chlorophyll content, in its computation. Thus far, this uncertainty has not been properly recognized nor quantified. The main goal of this study was to quantify the uncertainty of GLAI as used in the estimation of key photosynthetic canopy traits, namely canopy chlorophyll content (CCC). This uncertainty was assessed through the evaluation of the relationship between GLAI and CCC in structurally and functionally contrasting crop species (Zea mays L., Glycine max (L.) Merr., and Oryza sativa L). Results show that for the same GLAI value, CCC varied 2- to 3-fold due mainly to the variability of leaf chlorophyll content. Therefore, we suggest using the absorption coefficient in the red-edge region of the electromagnetic spectrum as an alternative to GLAI for the evaluation of CCC and other important photosynthetic canopy traits. The absorption coefficient in this spectral region is particularly suitable as it has been successfully related with the gross primary productivity of vegetation canopies, the quantum yield of photosynthesis, and is sensitive to the repositioning of chloroplasts within leaf cells in response to water stress.

Early Detection of Basal Stem Rot Disease in Oil Palm Tree Using Unmanned Aerial Vehicle-Based Hyperspectral Imaging

Early detection of basal stem rot (BSR) disease in oil palm trees is important for the sustainable production of palm oil in the limited land for plantation in Southeast Asia. However, previous studies based on satellite and aircraft hyperspectral remote sensing could not discriminate oil palm trees in the early-stage of the BSR disease from healthy or late-stage trees. In this study, hyperspectral imaging of oil palm trees from an unmanned aerial vehicle (UAV) and machine learning using a random forest algorithm were employed for the classification of four infection categories of the BSR disease: healthy, early-stage, late-stage, and dead trees. A concentric disk segmentation was applied to tree crown segmentation at the sub-plant scale, and recursive feature elimination was used for feature selection. The results revealed that the classification performance for the early-stage trees is maximum at the specific tree crown segments, and only a few spectral bands in the red-edge region are sufficient to classify the infection categories. These findings will be useful for future UAV-based multispectral imaging to efficiently cover a wide area of oil palm plantations for the early detection of BSR disease.

Estimating Aboveground Biomass in Dense Hyrcanian Forests by the Use of Sentinel-2 Data

Due to the challenges brought by field measurements to estimate the aboveground biomass (AGB), such as the remote locations and difficulties in walking in these areas, more accurate and cost-effective methods are required, by the use of remote sensing. In this study, Sentinel-2 data were used for estimating the AGB in pure stands of Carpinus betulus (L., common hornbeam) located in the Hyrcanian forests, northern Iran. For this purpose, the diameter at breast height (DBH) of all trees thicker than 7.5 cm was measured in 55 square plots (45 × 45 m). In situ AGB was estimated using a local volume table and the specific density of wood. To estimate the AGB from remotely sensed data, parametric and nonparametric methods, including Multiple Regression (MR), Artificial Neural Network (ANN), k-Nearest Neighbor (kNN), and Random Forest (RF), were applied to a single image of the Sentinel-2, having as a reference the estimations produced by in situ measurements and their corresponding spectral values of the original spectral (B2, B3, B4, B5, B6, B7, B8, B8a, B11, and B12) and derived synthetic (IPVI, IRECI, GEMI, GNDVI, NDVI, DVI, PSSRA, and RVI) bands. Band 6 located in the red-edge region (0.740 nm) showed the highest correlation with AGB (r = −0.723). A comparison of the machine learning methods indicated that the ANN algorithm returned the best ABG-estimating performance (%RMSE = 19.9). This study demonstrates that simple vegetation indices extracted from Sentinel-2 multispectral imagery can provide good results in the AGB estimation of C. betulus trees of the Hyrcanian forests. The approach used in this study may be extended to similar areas located in temperate forests.

Estimation of chlorophyll content in pepper leaves using spectral transmittance red-edge parameters

The objective of this work was to monitor the growth status of pepper and provide precise guidance on fertilization through non-destructive detection methods for chlorophyll content based on spectral transmittance. The analysis of the narrower red-edge spectral region (680-760 nm) reduced the requirements for light sources and light detection sensors, and provided a simpler and more accurate method of data acquisition for the process of developing instruments for estimating chlorophyll content in leaves. The red-edge region of spectral transmittance was demonstrated to be closely related to chlorophyll content. Regression models for estimating chlorophyll content with seven different methods were developed using the four red-edge parameters extracted from the red-edge region. The problems of multicollinearity of red-edge parameters and errors in model coefficients were solved by the ridge regression method in the process of building a multivariate regression model. The results indicated that the ridge regression method reduces the errors of the model coefficients and constant terms while improving the detection accuracy, thus the ridge regression model could estimate the leaf chlorophyll content more accurately and repeatedly. Keywords: pepper leaf, chlorophyll content, red-edge parameters, ridge regression DOI: 10.25165/j.ijabe.20221505.7350 Citation: Huang S, Wu Y, Wang Q L, Liu J L, Han Q Y, Wang J F. Estimation of chlorophyll content in pepper leaves using spectral transmittance red-edge parameters. Int J Agric & Biol Eng, 2022; 15(5): 85–90.

Estimation of leaf nitrogen levels in sugarcane using hyperspectral models

ABSTRACT: Sugarcane is a good source of renewable energy and helps reduce the emission of greenhouse gases. Nitrogen has a critical role in plant growth; therefore,estimating nitrogen levels is essential, and remote sensing can improve fertilizer management. This field study selects wavelengths from hyperspectral data on a sugarcane canopy to generate models for estimating leaf nitrogen concentrations. The study was carried out in the municipalities of Piracicaba, Jaú, and Santa Maria da Serra, state of São Paulo, in the 2013/2014 growing season. The experiments were carried out using a completely randomized block design with split plots (three sugarcane varieties per plot [variety SP 81-3250 was common to all plots] and four nitrogen concentrations [0, 50, 100, and 150 kgha-1] per subplot) and four repetitions. The wavelengths that best correlated with leaf nitrogen were selected usingsparse partial least square regression. The wavelength regionswere combinedby stepwise multiple linear regression. Spectral bands in the visible (700-705 nm), red-edge (710-720 nm), near-infrared (725, 925, 955, and 980 nm), and short-wave infrared (1355, 1420, 1595, 1600, 1605, and 1610 nm) regions were identified. The R² and RMSE of the model were 0.50 and 1.67 g.kg-1, respectively. The adjusted R² and RMSE of the models for Piracicaba, Jaú, and Santa Maria were 0.31 (unreliable) and 1.30 g.kg-1, 0.53 and 1.96 g.kg-1, and 0.54 and 1.46 g.kg-1, respectively. Our results showed that canopy hyperspectral reflectance can estimate leaf nitrogen concentrations and manage nitrogen application in sugarcane.

Exploring the utility of Sentinel-2 for estimating maize chlorophyll content and leaf area index across different growth stages

ABSTRACT This study investigated the utility of Sentinel-2 spectral data for estimating leaf area index (LAI), leaf and canopy chlorophyll content of maize at different growth stages. Vegetation indices based on the visible-near infrared and red-edge regions of the spectrum were computed from Sentinel-2 imagery acquired within one or two days of field data collection. Results showed that green chlorophyll index (CIgreen) and red-edge chlorophyll index (CIred-edge), using the red-edge variant centred at 705 nm, consistently showed higher relationship to maize LAI with r 2 of 0.65 and 0.63 during the early stages of growth, respectively, and an r 2 of 0.79 and 0.81 during tassel stage, respectively. Regarding canopy chlorophyll content the results indicated the spectral advantage of the Sentinel-2 sensor with the presence of two red-edge bands for continuous monitoring of maize chlorophyll content. Overall, the results indicated that maize biophysical variables can be monitored at satellite level using Sentinel-2 data.

Estimating near-infrared reflectance of vegetation from hyperspectral data

Disentangling the individual contributions from vegetation and soil in measured canopy reflectance is a grand challenge to the remote sensing and ecophysiology communities. Since Solar Induced chlorophyll Fluorescence (SIF) is uniquely emitted from vegetation, it can be used to evaluate how well reflectance-based vegetation indices (VIs) can separate the vegetation and soil components. Due to the residual soil background contributions, Near-infrared (NIR) reflectance of vegetation (NIRv) and Difference Vegetation index (DVI) present offsets when compared to SIF (i.e., the value of NIRv or DVI is non-zero when SIF is zero). In this study, we proposed a simple framework for estimating the true NIR reflectance of vegetation from Hyperspectral measurements (NIRvH) with minimal soil impacts. NIRvH takes advantage of the spectral shape variations in the red-edge region to minimize the soil effects. We evaluated the capability of NIRvH, NIRv and DVI in isolating the true NIR reflectance of vegetation using the data from both the model-based simulations and Hyperspectral Plant imaging spectrometer (HyPlant) measurements. Benchmarked by simultaneously measured SIF, NIRvH has the smallest offset (0–0.037), as compared to an intermediate offset of 0.047–0.062 from NIRv, and the largest offset of 0.089–0.112 from DVI. The magnitude of the offset can vary with different soil reflectance spectra across spatio-temporal scales, which may lead to bias in the downstream NIRv-based photosynthesis estimates. NIRvH and SIF measurements from the same sensor platform avoided complications due to different geometry, footprint and time of observation across sensors when studying the radiative transfer of reflected photons and SIF. In addition, NIRvH was primarily determined by canopy structure rather than chlorophyll content and soil brightness. Our work showcases that NIRvH is promising for retrieving canopy structure parameters such as leaf area index and leaf inclination angle, and for estimating fluorescence yield with current and forthcoming hyperspectral satellite measurements.

Leaf nitrogen content estimation using top-of-canopy airborne hyperspectral data

Remote estimation of leaf nitrogen content is a critical requirement for precision farm management. Precise knowledge of nitrogen distribution in the crop enables farmers to decide the fertilisation amount required at specific locations on the farm. Importantly, nitrogen related molecules in plants are transported using water molecules, and water molecules surround the amide bonds (a plant protein created from nitrogen). Consequently, the nitrogen in various crop parts loses its activity in the absence of sufficient water molecules. The association of water molecules around plant proteins makes the optical remote estimation of plant nitrogen challenging as nitrogen and water molecules simultaneously affect the reflectance data. Moreover, the coarse spatial resolution of satellite data and sparse canopy coverage at early growth stages of the crop make it challenging to estimate leaf-level nitrogen contents. Accordingly, this research developed a leaf nitrogen content estimation model using drone-based top-of-canopy 400–1000 nm pure pixel hyperspectral images collected from a maize research farm treated with different water and nitrogen levels. Leaf level spectral signatures were also collected using a field spectroradiometer and used to identify indices more sensitive to nitrogen than water. The leaves were also destructively sampled for obtaining ground truth leaf water and nitrogen content. Red-edge region bands of electromagnetic spectra were identified to be sensitive to leaf nitrogen content. A synthetic data was created using maximum and minimum values of these indices and crop growth stage information, which was further used for training a gradient-boosting machine model to estimate leaf nitrogen content from drone-based hyperspectral images. The estimated leaf nitrogen content values from drone observations were critically analysed with respect to leaf water content values. For water-stressed areas, the model gave an R2 and RMSE of 0.63 and 2.74 mg/g, respectively. However, the model did not perform adequately for well irrigated areas, having an R2 and RMSE of 0.26 and 4.54 mg/g, respectively.

Identifying the Spectral Signatures of Invasive and Native Plant Species in Two Protected Areas of Pakistan through Field Spectroscopy

Globally, biological invasions are considered as one of the major contributing factors for the loss of indigenous biological diversity. Hyperspectral remote sensing plays an important role in the detection and mapping of invasive plant species. The main objective of this study was to discriminate invasive plant species from adjacent native species using a ground-based hyperspectral sensor in two protected areas, Lehri Reserve Forest and Jindi Reserve Forest in Punjab, Pakistan. Field spectral measurements were collected using an ASD FieldSpec handheld2TM spectroradiometer (325–1075 nm) and the discrimination between native and invasive plant species was evaluated statistically using hyperspectral indices as well as leaf wavelength spectra. Finally, spectral separability was calculated using Jeffries Matusita distance index, based on selected wavebands. The results reveal that there were statistically significant differences (p < 0.05) between the different spectral indices of most of the plant species in the forests. However, the red-edge parameters showed the highest potential (p < 0.001) to discriminate different plant species. With leaf spectral signatures, the mean reflectance between all plant species was significantly different (p < 0.05) at 562 (75%) wavelength bands. Among pairwise comparisons, invasive Leucaena leucocephala showed the best discriminating ability, with Dodonaea viscosa having 505 significant wavebands showing variations between them. Jeffries Matusita distance analysis revealed that band combinations of the red-edge region (725, 726 nm) showed the best spectral separability (85%) for all species. Our findings suggest that it is possible to identify and discriminate invasive species through field spectroscopy for their future monitoring and management. However, the upscaling of hyperspectral measurements to airborne and satellite sensors can provide a reliable estimation of invasion through mapping inside the protected areas and can help to conserve biodiversity and environmental ecosystems in the future.

Hyperspectral imaging for high-throughput vitality monitoring in ornamental plant production

Ornamental heather (Calluna vulgaris) production is characterized by high risks such as occurrence of fungal diseases and plant losses. Given the general absence of formal research on this economically important production system, farmers depend on their own approaches to assess plant vitality. We provide a reproducible, affordable and transparent workflow for assessing ornamental plant vitality with spectroscopy data. We use hyperspectral imaging as a non-invasive alternative for monitoring plant performance by combining the long-term experience of experts with hyperspectral images taken with a portable hyperspectral camera. We tested a custom-made setup deployed in a horticultural production facility and screened thousands of heather plants over a period of 14 weeks during their development from cuttings to young plants under production conditions. The vitality of shoots and roots was classified by experts for comparison with spectral signatures of shoot tips of healthy and stressed plants. To identify wavelengths that allow distinguishing between healthy and stressed heather plants, we evaluated the datasets using Partial Least Squares regression. Reflectance in the green (519–575 nm) and red-edge (712–718 nm) region of the spectrum was identified as most important for classifying plants as healthy or stressed. We transferred the trained Partial Least Squares regression model to independent test data obtained on a different date, correctly classifying 98.1% of the heather plants. The setup we describe here is adjustable and can be used to measure different plant species. We identify challenges in data evaluation, point out promising evaluation approaches, and make our dataset available to facilitate further studies on plant vitality in horticultural production systems.

Crop Nitrogen Retrieval Methods for Simulated Sentinel-2 Data Using In-Field Spectrometer Data.

Nitrogen (N) is one of the key nutrients supplied in agricultural production worldwide. Over-fertilization can have negative influences on the field and the regional level (e.g., agro-ecosystems). Remote sensing of the plant N of field crops presents a valuable tool for the monitoring of N flows in agro-ecosystems. Available data for validation of satellite-based remote sensing of N is scarce. Therefore, in this study, field spectrometer measurements were used to simulate data of the Sentinel-2 (S2) satellites developed for vegetation monitoring by the ESA. The prediction performance of normalized ratio indices (NRIs), random forest regression (RFR) and Gaussian processes regression (GPR) for plant-N-related traits was assessed on a diverse real-world dataset including multiple crops, field sites and years. The plant N traits included the mass-based N measure, N concentration in the biomass (Nconc), and an area-based N measure approximating the plant N uptake (NUP). Spectral indices such as normalized ratio indices (NRIs) performed well, but the RFR and GPR methods outperformed the NRIs. Key spectral bands for each trait were identified using the RFR variable importance measure and the Gaussian processes regression band analysis tool (GPR-BAT), highlighting the importance of the short-wave infrared (SWIR) region for estimation of plant Nconc—and to a lesser extent the NUP. The red edge (RE) region was also important. The GPR-BAT showed that five bands were sufficient for plant N trait and leaf area index (LAI) estimation and that a surplus of bands effectively reduced prediction performance. A global sensitivity analysis (GSA) was performed on all traits simultaneously, showing the dominance of the LAI in the mixed remote sensing signal. To delineate the plant-N-related traits from this signal, regional and/or national data collection campaigns producing large crop spectral libraries (CSL) are needed. An improved database will likely enable the mapping of N at the agro-ecosystem level or for use in precision farming by farmers in the future.

Investigating the potential of Sentinel-2 configuration to predict the quality of Mediterranean permanent grasslands in open woodlands

The assessment of pasture quality in permanent grasslands is essential for their conservation and management, as it can contribute to making real-time decisions for livestock management. In this study, we assessed the potential of Sentinel-2 configuration to predict forage quality in high diverse Mediterranean permanent grasslands of open woodlands. We evaluated the performance of Partial Least Squares Regression (PLS) models to predict crude protein (CP), neutral detergent fibre (NDF), acid detergent fibre (ADF) and enzyme digestibility of organic matter (EDOM) by using three different reflectance datasets: (i) laboratory measurements of reflectance of dry and ground pasture samples re-sampled to Sentinel-2 configuration (Spec-lab) (ii) field in-situ measurements of grasslands canopy reflectance resampled to Sentinel-2 configuration (Spec-field); (iii) and Bottom Of Atmosphere Sentinel-2 imagery. For the three reflectance datasets, the models to predict CP content showed moderate performance and predictive ability. Mean R2test = 0.68 were obtained using Spec-lab data, mean R2test decreased by 0.11 with Spec-field and by 0.18 when Sentinel-2 reflectance was used. Statistics for NDF showed worse predictions than those obtained for CP: predictions produced with Spec-lab showed mean R2test = 0.64 and mean RPDtest = 1.73. The mean values of R2test = 0.50 and RPDtest = 1.54 using Sentinel-2 BOA reflectance were marginally better than the values obtained with Spec-field (mean R2test = 0.48, mean RPDtest = 1.43). For ADF and EDOM, only predictions made with Spec-lab produced acceptable results. Bands from the red-edge region, especially band 5, and the SWIR regions showed the highest contribution to estimating CP and NDF. Bands 2, blue and 4, red also seem to be important. The implementation of field spectroscopy in combination with Sentinel-2 imagery proved to be feasible to produce forage quality maps and to develop larger datasets. This study contributes to increasing knowledge of the potential and applicability of Sentinel-2 to predict the quality of Mediterranean permanent grasslands in open woodlands.

Leaf Anthocyanin Content Retrieval with Partial Least Squares and Gaussian Process Regression from Spectral Reflectance Data.

Leaf pigment content retrieval is an essential research field in remote sensing. However, retrieval studies on anthocyanins are quite rare compared to those on chlorophylls and carotenoids. Given the critical physiological significance of anthocyanins, this situation should be improved. In this study, using the reflectance, partial least squares regression (PLSR) and Gaussian process regression (GPR) were sought to retrieve the leaf anthocyanin content. To our knowledge, this is the first time that PLSR and GPR have been employed in such studies. The results showed that, based on the logarithmic transformation of the reflectance (log(1/R)) with 564 and 705 nm, the GPR model performed the best (R2/RMSE (nmol/cm2): 0.93/2.18 in the calibration, and 0.93/2.20 in the validation) of all the investigated methods. The PLSR model involved four wavelengths and achieved relatively low accuracy (R2/RMSE (nmol/cm2): 0.87/2.88 in calibration, and 0.88/2.89 in validation). GPR apparently outperformed PLSR. The reason was likely that the non-linear property made GPR more effective than the linear PLSR in characterizing the relationship for the absorbance vs. content of anthocyanins. For GPR, selected wavelengths around the green peak and red edge region (one from each) were promising to build simple and accurate two-wavelength models with R2 > 0.90.

Hotspot analysis of spatial distribution of algae blooms in small and medium water bodies.

Intensive land use favors eutrophication processes and algae bloom proliferation in freshwaters, which is considered to be one of the main environmental issues worldwide. In general, and particularly in South America, inland water monitoring only covers the main water bodies due to the high costs and efforts involved. In order to improve the coverage of spatial and temporal of algae bloom monitoring, remote sensing serves as an alternative tool. Thereby, the analysis of significant spatial clusters of high values (hotspots) and low values (coldspots) of chlorophyll-a has been applied in coastal studies; however, at present, there are no studies in freshwaters. In this study, Getis-Ord Gi* hotspot analysis was applied to detect spatial distribution patterns of algae bloom dynamics in small- and medium-sized freshwater bodies. Four in situ samplings were carried out in five suburban lakes of Uruguay, in agreement with the satellite capture. Total and cyanobacterial chlorophyll-a concentration, and suspended solids were evaluated. Linear models were developed by combining pre-established indexes with additional Sentinel-2 spectral bands and in situ data. The relationship between red and red edge regions allowed mapping the chlorophyll-a in the study lakes with an adjustment of R2 = 0.83. Hotspot analysis was performed with the selected linear model, and significant chlorophyll-a variability within each lake was successfully detected. The novel application of hotspots analyses presented in this work represents a contribution to advance knowledge in the remote detection of algae bloom dynamics and improve monitoring capabilities of inland water bodies.