Search

The identification of crop diversity in today's world is very crucial to ensure adaptation of the crop with changing climate for better productivity as well as food security. Towards this, Hyperspectral Remote Sensing (HRS) is an efficient technique that offers the opportunity to discriminate crop types based on morphological as well as physiological features due to availability of contiguous spectral bands. The current work utilized the benefits of Airborne Visible Infrared Imaging Spectrometer- New Generation (AVIRIS-NG) data and explored the techniques for classification and identification of crop types. The endmembers were identified using the Geo-Stat Endmember Extraction (GSEE) algorithm for pure pixels identification and to generate the spectral library of the different crop types. Spectral feature comparison was done among AVIRIS-NG, Analytical Spectral Device (ASD)-Spectroradiometer and Continuum Removed (CR) spectra. The best-fit spectra obtained with the Reference ASD-Spectroradiometer and Pure Pixel spectral library were then used for crop discrimination using the ten supervised classifiers namely Spectral Angle Mapper (SAM), Spectral Information Divergence (SID), Support Vector Machine (SVM), Minimum Distance Classifier (MDC), Binary Encoding, deep learning-based Convolution Neural Network (CNN) and different algorithms of Ensemble learning such as Tree Bag, AdaBoost (Adaptive Boosting), Discriminant and RUSBoost (Random Under Sampling). In total, nine crop types were identified, namely, wheat, maize, tobacco, sorghum, linseed, castor, pigeon pea, fennel and chickpea. The performance evaluation of the classifiers was made using various metrics like Overall Accuracy, Kappa Coefficient, Precision, Recall and F1 score. The classifier 2D-CNN was found to be the best with Overall Accuracy, Kappa Coefficient, Precision, Recall and F1 score values of 89.065 %, 0.871, 87.565%, 89.541% and 88.678% respectively. The output of this work can be utilized for large scale mapping of crop types at the species level in a short interval of time with high accuracy. [ABSTRACT FROM AUTHOR]

Salt marshes are one of the most productive ecosystems and provide numerous ecosystem services. However, they are seriously threatened by human activities and sea level rise. One of the main characteristics of this environment is the distribution of specialized plant species. The environmental conditions governing the distribution of this vegetation, as well as its variation over time and space, still need to be better understood. In this way, these ecosystems will be managed and protected more effectively. Low-altitude remote sensing techniques are excellent for rapidly assessing salt marsh vegetation coverage. By applying a high-resolution hyperspectral imaging system onboard a UAV (UAV-HS), this study aims to differentiate between plant species and determine their distribution in salt marshes, using the salt marshes of Cadiz Bay as a case study. Hyperspectral processing techniques were used to find the purest spectral signature of each species. Continuum removal and second derivative transformations of the original spectral signatures highlight species-specific spectral absorption features. Using these methods, it is possible to differentiate salt marsh plant species with adequate precision. The elevation range occupied by these species was also estimated. Two species of Sarcocornia spp. were identified on the Cadiz Bay salt marsh, along with a class for Sporobolus maritimus. An additional class represents the transition areas from low to medium marsh with different proportions of Sarcocornia spp. and S. maritimus. S. maritimus can be successfully distinguished from soil containing microphytobenthos. The final species distribution map has up to 96% accuracy, with 43.5% of the area occupied by medium marsh species (i.e., Sarcocornia spp.) in the 2.30–2.80 m elevation range, a 29% transitional zone covering in 1.91–2.78 m, and 25% covered by S. maritims (1.22–2.35 m). Basing a method to assess the vulnerability of the marsh to SLR scenarios on the relationship between elevation and species distribution would allow prioritizing areas for rehabilitation. UAV-HS techniques have the advantage of being easily customizable and easy to execute (e.g., following extreme events or taking regular measurements). The UAV-HS data is expected to improve our understanding of coastal ecosystem responses, as well as increase our capacity to detect small changes in plant species distribution through monitoring. [ABSTRACT FROM AUTHOR]

Se ha realizado el análisis mineralógico a través de las propiedades espectrales desarrolladas por muestras de suelos y sedimentos del borde noroccidental de la Cuenca del Duero. Las absorciones producidas por los óxidos y oxihidróxidos de hierro (hematites y goethita, principalmente) están localizadas en zonas del VNIR (400-1200 nm), mientras que las bandas de absorción presentes en los espectros del SWIR (1200-2500 nm) están relacionadas con la composición química de minerales arcillosos. Los espectros de reflectancia medidos en laboratorio han sido normalizados aplicando los métodos del Continuum Removal (CR) y la segunda derivada (SD). Este último puede resolver la superposición de bandas al cuantificar sutiles inflexiones de la curva. Esto ha permitido examinar las bandas de absorción por separado midiendo los parámetros geométricos desarrollados en ellas. La proporción de los minerales influye en la respuesta espectral y, por tanto, en los valores de los parámetros. Se han realizado correlaciones lineales entre estos valores y la proporción de las diferentes fases minerales obtenidas por difracción de rayos X. De los parámetros estudiados, la correlación entre la posición del centro de banda (BC) en la máxima absorción alrededor de longitudes de onda de 890-960 nm y la profundidad del rasgo de absorción a 470 nm (D470) ha permitido realizar una estimación relativa de la proporción de hematites/goethita. En cuanto a la distribución de los diferentes minerales de arcilla, se ha podido establecer una correlación entre la proporción de caolinita y la profundidad de las bandas de absorción a 1415 y 2210 nm, y en los rasgos de absorción cercanos a 1390 y 2160 nm, analizados en SD.

Salt marshes are one of the most productive ecosystems and provide numerous ecosystem services. However, they are seriously threatened by human activities and sea level rise. One of the main characteristics of this environment is the distribution of specialized plant species. The environmental conditions governing the distribution of this vegetation, as well as its variation over time and space, still need to be better understood. In this way, these ecosystems will be managed and protected more effectively. Low-altitude remote sensing techniques are excellent for rapidly assessing salt marsh vegetation coverage. By applying a high-resolution hyperspectral imaging system onboard a UAV (UAV-HS), this study aims to differentiate between plant species and determine their distribution in salt marshes, using the salt marshes of Cadiz Bay as a case study. Hyperspectral processing techniques were used to find the purest spectral signature of each species. Continuum removal and second derivative transformations of the original spectral signatures highlight species-specific spectral absorption features. Using these methods, it is possible to differentiate salt marsh plant species with adequate precision. The elevation range occupied by these species was also estimated. Two species of Sarcocornia spp. were identified on the Cadiz Bay salt marsh, along with a class for Sporobolus maritimus. An additional class represents the transition areas from low to medium marsh with different proportions of Sarcocornia spp. and S. maritimus. S. maritimus can be successfully distinguished from soil containing microphytobenthos. The final species distribution map has up to 96% accuracy, with 43.5% of the area occupied by medium marsh species (i.e., Sarcocornia spp.) in the 2.30–2.80 m elevation range, a 29% transitional zone covering in 1.91–2.78 m, and 25% covered by S. maritims (1.22–2.35 m). Basing a method to assess the vulnerability of the marsh to SLR scenarios on the relationship between elevation and species distribution would allow prioritizing areas for rehabilitation. UAV-HS techniques have the advantage of being easily customizable and easy to execute (e.g., following extreme events or taking regular measurements). The UAV-HS data is expected to improve our understanding of coastal ecosystem responses, as well as increase our capacity to detect small changes in plant species distribution through monitoring.

Hyperspectral remote sensing is a promising tool for a variety of applications including ecology, geology, analytical chemistry and medical research. This article presents the new hsdar package for R statistical software, which performs a variety of analysis steps taken during a typical hyperspectral remote sensing approach. The package introduces a new class for efficiently storing large hyperspectral data sets such as hyperspectral cubes within R. The package includes several important hyperspectral analysis tools such as continuum removal, normalized ratio indices and integrates two widely used radiation transfer models. In addition, the package provides methods to directly use the functionality of the caret package for machine learning tasks. Two case studies demonstrate the package's range of functionality: First, plant leaf chlorophyll content is estimated and second, cancer in the human larynx is detected from hyperspectral data.

Spectral mixing models for minerals can be complex, and choosing the right unmixing model is indispensable to ensure the accuracy of spectral unmixing. Continuum removal (CR) and natural log operation have the potential to eliminate nonlinear effects in spectral mixing, and have already been used in nonlinear spectral unmixing applications. In this study, the newly proposed log and CR (LCR) model and four other spectral unmixing models for mineral analysis (the linear model, CR model, natural log model, and simplified Hapke model) were summarized and applied to both laboratory mineral powder spectra and hyperspectral data of Cuprite, Nevada, USA. This paper summarizes the concept of mixing reflectance reconstruction (MRR), along with a comprehensive method to determine accuracy based on MRR results, which can be performed in different dimensions, such as spatial dimension and spectral dimension. The LCR model performed the best in both laboratory experiments and image data analysis, indicating its strong potential for practical application. The level of atmospheric correction’s influence on unmixing accuracy varied for different spectral unmixing models, among which LCR model also had the best performance.

Monitoring and management of plant water status over the critical period between flowering and veraison, plays a significant role in producing grapes of premium quality. Hyperspectral spectroscopy has been widely studied in precision farming, including for the prediction of grapevine water status. However, these studies were presented based on various combinations of transformed spectral data, feature selection methods, and regression models. To evaluate the performance of different modeling pipelines for estimating grapevine water status, a study spanning the critical period was carried out in two commercial vineyards at Martinborough, New Zealand. The modeling used six hyperspectral data groups (raw reflectance, first derivative reflectance, second derivative reflectance, continuum removal variables, simple ratio indices, and vegetation indices), two variable selection methods (Spearman correlation and recursive feature elimination based on cross-validation), an ensemble of selected variables, and three regression models (partial least squares regression, random forest regression, and support vector regression). Stem water potential (used as a proxy for vine water status) was measured by a pressure bomb. Hyperspectral reflectance was undertaken by a handheld spectroradiometer. The results show that the best predictive performance was achieved by applying partial least squares regression to simple ratio indices (R2 = 0.85; RMSE = 110 kPa). Models trained with an ensemble of selected variables comprising multicombination of transformed data and variable selection approaches outperformed those fitted using single combinations. Although larger data sizes are needed for further testing, this study compares 38 modeling pipelines and presents the best combination of procedures for estimating vine water status. This may lead to the provision of rapid estimation of vine water status in a nondestructive manner and highlights the possibility of applying hyperspectral data to precision irrigation in vineyards.

Spectral mixing models for minerals can be complex, and choosing the right unmixing model is indispensable to ensure the accuracy of spectral unmixing. Continuum removal (CR) and natural log operation have the potential to eliminate nonlinear effects in spectral mixing, and have already been used in nonlinear spectral unmixing applications. In this study, the newly proposed log and CR (LCR) model and four other spectral unmixing models for mineral analysis (the linear model, CR model, natural log model, and simplified Hapke model) were summarized and applied to both laboratory mineral powder spectra and hyperspectral data of Cuprite, Nevada, USA. This paper summarizes the concept of mixing reflectance reconstruction (MRR), along with a comprehensive method to determine accuracy based on MRR results, which can be performed in different dimensions, such as spatial dimension and spectral dimension. The LCR model performed the best in both laboratory experiments and image data analysis, indicating its strong potential for practical application. The level of atmospheric correction's influence on unmixing accuracy varied for different spectral unmixing models, among which LCR model also had the best performance. [ABSTRACT FROM AUTHOR]

Irrigation-induced salinization is an important land degradation process that affects crop yield in the Brazilian semi-arid region, and gypsum has been used as a corrective measure for saline soils. Fluvent soil samples (180) were treated with increasing levels of salinization of NaCl, MgCl2 and CaCl2. The salinity was gauged using electrical conductivity (EC). Gypsum was added to one split of these samples before they were treated by the saline solutions. Laboratory reflectance spectra were measured at nadir under a controlled environment using a FieldSpec spectrometer, a 250-W halogen lamp and a Spectralon panel. Variations in spectral reflectance and brightness were evaluated using principal component analysis, as well as the continuum-removed absorption depths of major features at 1450, 1950, 1750 and 2200 nm for both the gypsum-treated (TG) and non-treated (NTG) air-dried soil samples as a function of EC. Pearson’s correlation coefficients of reflectance and the band depth with EC were also obtained to establish the relationships with salinity. Results showed that NTG samples presented a decrease in reflectance and brightness with increasing CaCl2 and MgCl2 salinization. The reverse was observed for NaCl. Gypsum increased the spectral reflectance of the soil. The best negative correlations between reflectance and EC were observed in the 1500–2400 nm range for CaCl2 and MgCl2, probably because these wavelengths are most affected by water absorption, as Ca and Mg are much more hygroscopic than Na. These decreased after chemical treatment with gypsum. The most prominent features were observed at 1450, 1950 and 1750 nm in salinized-soil spectra. The 2200-nm clay mineral absorption band depth was inversely correlated with salt concentration. From these features, only the 1750 and 2200 nm ones are within atmospheric absorption windows and can be more easily measured using hyperspectral sensors.

Water status controls plant physiology and is key to managing vineyard grape quality and yield. Water status is usually estimated by leaf water potential (LWP), which is measured using a pressure chamber; however, this method is difficult, time-consuming, and error-prone. While traditional spectral methods based on leaf reflectance are faster and non-destructive, most are based on vegetation indices derived from satellite imagery (and so only take into account discrete bandwidths) and do not take full advantage of modern hyperspectral sensors that capture spectral reflectance for thousands of wavelengths. We used partial least squares regression (PLSR) to predict LWP from reflectance values (wavelength 350−2500 nm) captured with a field spectroradiometer. We first identified wavelength ranges that minimized regression error. We then tested several common data pre-processing methods to analyze the impact on PLSR prediction precision, finding that derivative pre-processing increased the determination coefficients of our models and reduced root mean squared error (RMSE). The models fitted with raw data obtained their best results at around 1450 nm, while the models with derivative pre-processed achieved their best estimates at 826 nm and 1520 nm.

Aboveground biomass (AGB) is one of the strategic biophysical variables of interest in vegetation studies. The main objective of this study was to evaluate the Support Vector Machine (SVM) and Partial Least Squares Regression (PLSR) for estimating the AGB of grasslands from field spectrometer data and to find out which data pre-processing approach was the most suitable. The most accurate model to predict the total AGB involved PLSR and the Maximum Band Depth index derived from the continuum removed reflectance in the absorption features between 916–1,120 nm and 1,079–1,297 nm (R2 = 0.939, RMSE = 7.120 g/m2). Regarding the green fraction of the AGB, the Area Over the Minimum index derived from the continuum removed spectra provided the most accurate model overall (R2 = 0.939, RMSE = 3.172 g/m2). Identifying the appropriate absorption features was proved to be crucial to improve the performance of PLSR to estimate the total and green aboveground biomass, by using the indices derived from those spectral regions. Ordinary Least Square Regression could be used as a surrogate for the PLSR approach with the Area Over the Minimum index as the independent variable, although the resulting model would not be as accurate.

The water column overlying the submerged aquatic vegetation (SAV) canopy presents difficulties when using remote sensing images for mapping such vegetation. Inherent and apparent water optical properties and its optically active components, which are commonly present in natural waters, in addition to the water column height over the canopy, and plant characteristics are some of the factors that affect the signal from SAV mainly due to its strong energy absorption in the near-infrared. By considering these interferences, a hypothesis was developed that the vegetation signal is better conserved and less absorbed by the water column in certain intervals of the visible region of the spectrum; as a consequence, it is possible to distinguish the SAV signal. To distinguish the signal from SAV, two types of classification approaches were selected. Both of these methods consider the hemispherical–conical reflectance factor (HCRF) spectrum shape, although one type was supervised and the other one was not. The first method adopts cluster analysis and uses the parameters of the band (absorption, asymmetry, height and width) obtained by continuum removal as the input of the classification. The spectral angle mapper (SAM) was adopted as the supervised classification approach. Both approaches tested different wavelength intervals in the visible and near-infrared spectra. It was demonstrated that the 585 to 685-nm interval, corresponding to the green, yellow and red wavelength bands, offered the best results in both classification approaches. However, SAM classification showed better results relative to cluster analysis and correctly separated all spectral curves with or without SAV. Based on this research, it can be concluded that it is possible to discriminate areas with and without SAV using remote sensing.

This study examined the relationship between the leaf reflectance of different seasons and the concentration of heavy metal elements in leaves, such as Co, Cu, Mo, and Ni in a post-mining area. The reflectance spectra and leaf samples of three typical plants were measured and collected in a whole growth cycle (June, July, August, and September). The Red Edge Position (REP), Readjustment Normalized Difference Vegetation Index (RE-NDVI), and Photochemical Reflectance Index (PRI) were extracted and used to explore its relation with the heavy metals concentrations in leaves between different seasons. The results show that all three Vegetation Indices (VIs) were insensitive indicators for monitoring the metal effects of vegetation in different seasons, which showed similar trends. Based on this, the Continuum Removal Indices (CRIs) were proposed from the continuum removed approach and extended for detecting the effects of heavy metal pollution over a full growth cycle. The relationship between the metal concentrations and CRIs of different plants was respectively analyzed by Stepwise Multiple Linear Regression (SMLR) and Partial Least Squares Regression (PLSR). It is found that a significant correlation exists between the band depth and the concentration of Cu and Ni based on the White birch data sets using the PLSR, resulting in a small deviation from the established relationships. Compared with VIs, the approach of coupling CRIs and multiple regressions was effective for improving the estimation accuracy. The presented study provides a detection model of leaf heavy metals that can be adapted to different growing cycles, even an arbitrary growing cycle.

It is demonstrated that hyperspectral imagery can be used, without atmospheric correction, to determine the presence of accessory phytoplankton pigments in coastal waters using derivative techniques. However, care must be taken not to confuse other absorptions for those caused by the presence of pigments. Atmospheric correction, usually the first step to making products from hyperspectral data, may not completely remove Fraunhofer lines and atmospheric absorption bands and these absorptions may interfere with identification of phytoplankton accessory pigments. Furthermore, the ability to resolve absorption bands depends on the spectral resolution of the spectrometer, which for a fixed spectral range also determines the number of observed bands. Based on this information, a study was undertaken to determine under what circumstances a hyperspectral sensor may determine the presence of pigments. As part of the study a hyperspectral imager was used to take high spectral resolution data over two different water masses. In order to avoid the problems associated with atmospheric correction this data was analyzed as radiance data without atmospheric correction. Here, the purpose was to identify spectral regions that might be diagnostic for photosynthetic pigments. Two well proven techniques were used to aid in absorption band recognition, the continuum removal of the spectra and the fourth derivative. The findings in this study suggest that interpretation of absorption bands in remote sensing data, whether atmospherically corrected or not, have to be carefully reviewed when they are interpreted in terms of photosynthetic pigments.

In this study we evaluated various spectral inputs for retrieval of forest chlorophyll content (Cab) and leaf area index (LAI) from high spectral and spatial resolution airborne imaging spectroscopy data collected for two forest study sites in the Czech Republic (beech forest at Štítná nad Vláří and spruce forest at Bílý Kříž). The retrieval algorithm was based on a machine learning method - support vector regression (SVR). Performance of the four spectral inputs used to train SVR was evaluated: a) all available hyperspectral bands, b) continuum removal (CR) 645 - 710 nm, c) CR 705 - 780 nm, and d) CR 680 - 800 nm. Spectral inputs and corresponding SVR models were first assessed at the level of spectral databases simulated by combined leaf-canopy radiative transfer models PROSPECT and DART. At this stage, SVR models using all spectral inputs provided good performance (RMSE for Cab < 10 μg cm-2 and for LAI < 1.5), with consistently better performance for beech over spruce site. Since application of trained SVRs on airborne hyperspectral images of the spruce site produced unacceptably overestimated values, only the beech site results were analysed. The best performance for the Cab estimation was found for CR bands in range of 645 - 710 nm, whereas CR bands in range of 680 - 800 nm were the most suitable for LAI retrieval. The CR transformation reduced the across-track bidirectional reflectance effect present in airborne images due to large sensor field of view. [ABSTRACT FROM AUTHOR]

Considering the important roles of carbonate rock fraction in karst rocky desertification areas and their potential for indicating damage to vegetation, improved knowledge is desired to assess the application of spectroscopy and remote sensing to characterizing and quantifying the biophysical constituents of karst landscapes. In this study, we examined the spectra of major surface constituents in karst areas for direct evidence of absorption features attributable to carbonate rock fraction. Using spectral feature analysis with continuum removal, we observed that there are overlapping spectral absorption in 2.149-2.398 µm by soils and non-photosynthetic vegetation. These overlapping features complicated the carbonate absorption feature near 2.340 µm in synthetic mixed spectra. To remove the overprint signal, two hyperspectral carbonate rock indices (HCRIs) were developed. Compared to the absorption features including depths, areas, and KRDSIs (karst rocky desertification synthesis indices), linear regression of HCRIs with carbonate rock fraction in linear synthetic mixtures resulted in higher correlations and lower errors. This study demonstrates that spectral variation of the surface constituents spectra in 2.270-2.398 µm region can indicate carbonate rock fraction and be used to quantify them. Still, additional research is needed to advance our understanding of the spectral influences from carbonate petrography relative to carbonate mineralogy, components and physical state of rock surface. [ABSTRACT FROM AUTHOR]

Needle-leaf chlorophyll content (Cab) of a Norway spruce stand was estimated from CHRIS-PROBA images using the canopy reflectance simulated by the PROSPECT model coupled with two canopy reflectance models: 1) discrete anisotropic radiative transfer model (DART); and 2) PARAS. The DART model uses a detailed description of the forest scene, whereas PARAS is based on the photon recollision probability theory and uses a simplified forest structural description. Subsequently, statistically significant empirical functions between the optical indices \textbfANCB\textbf{670 - \textbf{720}} and \textbfANMB\textbf{670 - \textbf{720}} and the needle-leaf Cab content were established and then applied to CHRIS-PROBA data. The Cab estimating regressions using \textbfANMB\textbf{670 - \textbf{720}} were more robust than using \textbfANCB\textbf{670 - \textbf{720}} since the latter was more sensitive to LAI, especially in case of PARAS. Comparison between Cab estimates showed strong linear correlations between PARAS and DART retrievals, with a nearly perfect one-to-one fit when using \textbfANMB\textbf{670 - \textbf{720}} (\textbfslope = \textbf1.1, \textbfoffset = \textbf11\,\upmu \textbfg \cdot \textbfcm^ - 2). Further comparison with Cab estimated from an AISA Eagle image of the same stand showed better results for PARAS (\textbfRMSE = \textbf2.7\,\upmu \textbfg \cdot \textbfcm^ - 2 for \textbfANCB\textbf{670 - \textbf{720}}; \textbfRMSE = \textbf9.5\,\upmu \textbfg \cdot \textbfcm^ - 2 for \textbfANMB\textbf{670 - \textbf{720}}) than for DART (\textbfRMSE = \textbf7.5\,\upmu \textbfg \cdot \textbfcm^ - 2 for \textbfANCB\textbf{670 - \textbf{720}}; \textbfRMSE = \textbf23\,\upmu \textbfg \cdot \textbfcm^ - 2 for \textbfANMB\textbf{670 - \mathbf{720}}). Although these results show the potential for simpler models like PARAS in estimating needle-leaf Cab from satellite imaging spectroscopy data, further analyses regarding parameterization of radiative transfer models are recommended. [ABSTRACT FROM PUBLISHER]

Irrigation-induced salinization is an important land degradation process that affects crop yield in the Brazilian semi-arid region, and gypsum has been used as a corrective measure for saline soils. Fluvent soil samples (180) were treated with increasing levels of salinization of NaCl, MgCl2 and CaCl2. The salinity was gauged using electrical conductivity (EC). Gypsum was added to one split of these samples before they were treated by the saline solutions. Laboratory reflectance spectra were measured at nadir under a controlled environment using a FieldSpec spectrometer, a 250-W halogen lamp and a Spectralon panel. Variations in spectral reflectance and brightness were evaluated using principal component analysis, as well as the continuum-removed absorption depths of major features at 1450, 1950, 1750 and 2200 nm for both the gypsum-treated (TG) and non-treated (NTG) air-dried soil samples as a function of EC. Pearson's correlation coefficients of reflectance and the band depth with EC were also obtained to establish the relationships with salinity. Results showed that NTG samples presented a decrease in reflectance and brightness with increasing CaCl2 and MgCl2 salinization. The reverse was observed for NaCl. Gypsum increased the spectral reflectance of the soil. The best negative correlations between reflectance and EC were observed in the 1500-2400 nm range for CaCl2 and MgCl2, probably because these wavelengths are most affected by water absorption, as Ca and Mg are much more hygroscopic than Na. These decreased after chemical treatment with gypsum. The most prominent features were observed at 1450, 1950 and 1750 nm in salinized-soil spectra. The 2200-nm clay mineral absorption band depth was inversely correlated with salt concentration. From these features, only the 1750 and 2200 nm ones are within atmospheric absorption windows and can be more easily measured using hyperspectral sensors. [ABSTRACT FROM AUTHOR]

Aboveground biomass (AGB) is one of the strategic biophysical variables of interest in vegetation studies. The main objective of this study was to evaluate the Support Vector Machine (SVM) and Partial Least Squares Regression (PLSR) for estimating the AGB of grasslands from field spectrometer data and to find out which data pre-processing approach was the most suitable. The most accurate model to predict the total AGB involved PLSR and the Maximum Band Depth index derived from the continuum removed reflectance in the absorption features between 916-1,120 nm and 1,079-1,297 nm (R² = 0.939, RMSE = 7.120 g/m²). Regarding the green fraction of the AGB, the Area Over the Minimum index derived from the continuum removed spectra provided the most accurate model overall (R² = 0.939, RMSE = 3.172 g/m²). Identifying the appropriate absorption features was proved to be crucial to improve the performance of PLSR to estimate the total and green aboveground biomass, by using the indices derived from those spectral regions. Ordinary Least Square Regression could be used as a surrogate for the PLSR approach with the Area Over the Minimum index as the independent variable, although the resulting model would not be as accurate. [ABSTRACT FROM AUTHOR]

A dedicated field experiment was conducted to investigate the response of a green reflectance continuum removal-based optical index, called area under the curve normalized to maximal band depth between 511nm and 557nm (ANMB511–557), to light-induced transformations in xanthophyll cycle pigments of Norway spruce [Picea abies (L.) Karst] needles. The performance of ANMB511–557 was compared with the photochemical reflectance index (PRI) computed from the same leaf reflectance measurements. Needles of four crown whorls (fifth, eighth, 10th, and 15th counted from the top) were sampled from a 27-year-old spruce tree throughout a cloudy and a sunny day. Needle optical properties were measured together with the composition of the photosynthetic pigments to investigate their influence on both optical indices. Analyses of pigments showed that the needles of the examined whorls varied significantly in chlorophyll content and also in related pigment characteristics, such as the chlorophyll/carotenoid ratio. The investigation of the ANMB511–557 diurnal behaviour revealed that the index is able to follow the dynamic changes in the xanthophyll cycle independently of the actual content of foliar pigments. Nevertheless, ANMB511–557 lost the ability to predict the xanthophyll cycle behaviour during noon on the sunny day, when the needles were exposed to irradiance exceeding 1000 µmol m–2 s–1. Despite this, ANMB511–557 rendered a better performance for tracking xanthophyll cycle reactions than PRI. Although declining PRI values generally responded to excessive solar irradiance, they were not able to predict the actual de-epoxidation state in the needles examined. [ABSTRACT FROM PUBLISHER]

Abstract: Reflectance spectroscopy provides an alternate method to non-destructively characterize key soil properties. Different approaches, including chemometrics techniques or specific absorption features, have been proposed to estimate soil properties from visible and near-infrared (VNIR, 400-1200nm) and shortwave infrared (SWIR, 1200-2500nm) reflectance domains. The main goal of this study was to test the performance of two distinct methods for soil texture estimation by VNIR-SWIR reflectance measurements: i) the Continuum Removal (CR) technique that was used to correlate specific spectral absorption features with clay, silt and sand content, and ii) the Partial Least-Squares Regression (PLSR) method, which is a classical statistical multivariate technique, that uses the full-spectrum data. At this aim, the surface reflectance of 100 soil samples collected from different sites in Sicily and covering a wide range of textures were measured in laboratory using an ASD FieldSpec Pro spectroradiometer (350-2500nm). The results of our work indicated that the PLSR technique performed better than the CR approach. Particularly, the assessment of soil texture accuracy performed using root mean squared error (RMSE) and coefficient of determination (R2) showed that the CR approach allowed to obtain a moderate prediction only for the clay texture fraction. Differently, using PLSR technique, the levels of accuracy resulted high for the clay fraction (RMSE=5.8%, R2=0.87) and satisfactory for the sand (RMSE=7.7%, R2=0.80) and silt fractions (RMSE=7.2%, R2=0.60). Moreover the use of PLSR technique allowed to establish the “key wavelengths” of the investigated spectrum range that should be considered “essential” for the prediction of soil textures, suggesting the optimal settings for airborne or satellite sensors usable in the future for accurate mapping of soil textures. [Copyright &y& Elsevier]

The water column overlying the submerged aquatic vegetation (SAV) canopy presents difficulties when using remote sensing images for mapping such vegetation. Inherent and apparent water optical properties and its optically active components, which are commonly present in natural waters, in addition to the water column height over the canopy, and plant characteristics are some of the factors that affect the signal from SAV mainly due to its strong energy absorption in the near-infrared. By considering these interferences, a hypothesis was developed that the vegetation signal is better conserved and less absorbed by the water column in certain intervals of the visible region of the spectrum; as a consequence, it is possible to distinguish the SAV signal. To distinguish the signal from SAV, two types of classification approaches were selected. Both of these methods consider the hemispherical-conical reflectance factor (HCRF) spectrum shape, although one type was supervised and the other one was not. The first method adopts cluster analysis and uses the parameters of the band (absorption, asymmetry, height and width) obtained by continuum removal as the input of the classification. The spectral angle mapper (SAM) was adopted as the supervised classification approach. Both approaches tested different wavelength intervals in the visible and near-infrared spectra. It was demonstrated that the 585 to 685-nm interval, corresponding to the green, yellow and red wavelength bands, offered the best results in both classification approaches. However, SAM classification showed better results relative to cluster analysis and correctly separated all spectral curves with or without SAV. Based on this research, it can be concluded that it is possible to discriminate areas with and without SAV using remote sensing. [ABSTRACT FROM AUTHOR]

Based on in situ water sampling and field spectral measurement from June to September 2004 in Lake Chagan, a comparison of several existing semi-empirical algorithms to determine chlorophyll-a (Chl-a) content was made by applying them to the field spectra and in situ chlorophyll measurements. Results indicated that the first derivative of reflectance was well correlated with Chl-a. The highest correlation between the first derivative and Chl-a was at 680 nm. The two-band model, NIR/red ratio of R, was also an effective predictor of Chl-a concentration. Since the two-band ratios model is a special case of the three-band model developed recently, three-band model in Lake Chagan showed a higher resolution. The new algorithm named reverse continuum removal relies on the reflectance peak at 700 nm whose shape and position depend strongly upon chlorophyll concentration: The depth and area of the peak above a baseline showed a linear relationship to Chl-a concentration. All of the algorithms mentioned proved to be of value and can be used to predict Chl-a concentration. Best results were obtained by using the algorithms of the first derivative, which yielded R around 0.74 and RMSE around 6.39 μg/l. The two-band and three-band algorithms were further applied to MERIS when filed spectral were resampled with regard to their center wavelengths. Both algorithms showed an adequate precision, and the differences on the outcome were small with R = 0.70 and 0.71. [ABSTRACT FROM AUTHOR]

It is demonstrated that hyperspectral imagery can be used, without atmospheric correction, to determine the presence of accessory phytoplankton pigments in coastal waters using derivative techniques. However, care must be taken not to confuse other absorptions for those caused by the presence of pigments. Atmospheric correction, usually the first step to making products from hyperspectral data, may not completely remove Fraunhofer lines and atmospheric absorption bands and these absorptions may interfere with identification of phytoplankton accessory pigments. Furthermore, the ability to resolve absorption bands depends on the spectral resolution of the spectrometer, which for a fixed spectral range also determines the number of observed bands. Based on this information, a study was undertaken to determine under what circumstances a hyperspectral sensor may determine the presence of pigments. As part of the study a hyperspectral imager was used to take high spectral resolution data over two different water masses. In order to avoid the problems associated with atmospheric correction this data was analyzed as radiance data without atmospheric correction. Here, the purpose was to identify spectral regions that might be diagnostic for photosynthetic pigments. Two well proven techniques were used to aid in absorption band recognition, the continuum removal of the spectra and the fourth derivative. The findings in this study suggest that interpretation of absorption bands in remote sensing data, whether atmospherically corrected or not, have to be carefully reviewed when they are interpreted in terms of photosynthetic pigments. [ABSTRACT FROM AUTHOR]

Monitoring and management of plant water status over the critical period between flowering and veraison, plays a significant role in producing grapes of premium quality. Hyperspectral spectroscopy has been widely studied in precision farming, including for the prediction of grapevine water status. However, these studies were presented based on various combinations of transformed spectral data, feature selection methods, and regression models. To evaluate the performance of different modeling pipelines for estimating grapevine water status, a study spanning the critical period was carried out in two commercial vineyards at Martinborough, New Zealand. The modeling used six hyperspectral data groups (raw reflectance, first derivative reflectance, second derivative reflectance, continuum removal variables, simple ratio indices, and vegetation indices), two variable selection methods (Spearman correlation and recursive feature elimination based on cross-validation), an ensemble of selected variables, and three regression models (partial least squares regression, random forest regression, and support vector regression). Stem water potential (used as a proxy for vine water status) was measured by a pressure bomb. Hyperspectral reflectance was undertaken by a handheld spectroradiometer. The results show that the best predictive performance was achieved by applying partial least squares regression to simple ratio indices (R2 = 0.85; RMSE = 110 kPa). Models trained with an ensemble of selected variables comprising multicombination of transformed data and variable selection approaches outperformed those fitted using single combinations. Although larger data sizes are needed for further testing, this study compares 38 modeling pipelines and presents the best combination of procedures for estimating vine water status. This may lead to the provision of rapid estimation of vine water status in a nondestructive manner and highlights the possibility of applying hyperspectral data to precision irrigation in vineyards. [ABSTRACT FROM AUTHOR]

The miniaturisation of hyperspectral sensors for use on drones has provided an opportunity to obtain hyper temporal data that may be used to identify and monitor non-native grass species. However, a good understanding of variation in spectra for species over time is required to target such data collections. Five taxological and morphologically similar non-native grass species were hyper spectrally characterised from multitemporal spectra (17 samples over 14 months) over phenological seasons to determine their temporal spectral response. The grasses were sampled from maintained plots of homogenous non-native grass cover. A robust in situ standardised sampling method using a non-imaging field spectrometer measuring reflectance across the 350–2500 nm wavelength range was used to obtain reliable spectral replicates both within and between plots. The visible-near infrared (VNIR) to shortwave infrared (SWIR) and continuum removed spectra were utilised. The spectra were then resampled to the VNIR only range to simulate the spectral response from more affordable VNIR only hyperspectral scanners suitable to be mounted on drones. We found that species were separable compared to similar but different species. The spectral patterns were similar over time, but the spectral shape and absorption features differed between species, indicating these subtle characteristics could be used to distinguish between species. It was the late dry season and the end of the wet season that provided maximum separability of the non-native grass species sampled. Overall the VNIR-SWIR results highlighted more dissimilarity for unlike species when compared to the VNIR results alone. The SWIR is useful for discriminating species, particularly around water absorption. [ABSTRACT FROM AUTHOR]

Biocrusts, topsoil communities formed by mosses, lichens, liverworts, algae, and cyanobacteria, are a key biotic component of dryland ecosystems worldwide. Experiments carried out with lichen- and moss-dominated biocrusts indicate that climate change may dramatically reduce their cover and diversity. Therefore, the development of reproducible methods to monitor changes in biocrust diversity and abundance across multiple spatio-temporal scales is key for evaluating how climate change may impact biocrust communities and the myriad of ecosystem functions and services that rely on them. In this study, we collected lichen-dominated biocrust samples from a semi-arid ecosystem in central Spain. Their α-diversity was then evaluated using very high spatial resolution hyperspectral images (pixel size of 0.091 mm) measured in laboratory under controlled conditions. Support vector machines were used to map the biocrust composition. Traditional α-diversity metrics (i.e., species richness, Shannon's, Simpson's, and Pielou's indices) were calculated using lichen fractional cover data derived from their classifications in the hyperspectral imagery. Spectral diversity was calculated at different wavelength ranges as the coefficient of variation of different regions of the reflectance spectra of lichens and as the standard deviation of the continuum removal algorithm (SD_CR). The accuracy of the classifications of the images obtained was close to 100%. The results showed the best coefficient of determination (r2 = 0.47) between SD_CR calculated at 680 nm and the α-diversity calculated as the Simpson's index, which includes species richness and their evenness. These findings indicate that this spectral diversity index could be used to track spatio-temporal changes in lichen-dominated biocrust communities. Thus, they are the first step to monitor α-diversity of biocrust-forming lichens at the ecosystem and regional levels, a key task for any program aiming to evaluate changes in biodiversity and associated ecosystem services in drylands. [ABSTRACT FROM AUTHOR]

Water status controls plant physiology and is key to managing vineyard grape quality and yield. Water status is usually estimated by leaf water potential (LWP), which is measured using a pressure chamber; however, this method is difficult, time-consuming, and error-prone. While traditional spectral methods based on leaf reflectance are faster and non-destructive, most are based on vegetation indices derived from satellite imagery (and so only take into account discrete bandwidths) and do not take full advantage of modern hyperspectral sensors that capture spectral reflectance for thousands of wavelengths. We used partial least squares regression (PLSR) to predict LWP from reflectance values (wavelength 350–2500 nm) captured with a field spectroradiometer. We first identified wavelength ranges that minimized regression error. We then tested several common data pre-processing methods to analyze the impact on PLSR prediction precision, finding that derivative pre-processing increased the determination coefficients of our models and reduced root mean squared error (RMSE). The models fitted with raw data obtained their best results at around 1450 nm, while the models with derivative pre-processed achieved their best estimates at 826 nm and 1520 nm. [ABSTRACT FROM AUTHOR]

This study examined the relationship between the leaf reflectance of different seasons and the concentration of heavy metal elements in leaves, such as Co, Cu, Mo, and Ni in a post-mining area. The reflectance spectra and leaf samples of three typical plants were measured and collected in a whole growth cycle (June, July, August, and September). The Red Edge Position (REP), Readjustment Normalized Difference Vegetation Index (RE-NDVI), and Photochemical Reflectance Index (PRI) were extracted and used to explore its relation with the heavy metals concentrations in leaves between different seasons. The results show that all three Vegetation Indices (VIs) were insensitive indicators for monitoring the metal effects of vegetation in different seasons, which showed similar trends. Based on this, the Continuum Removal Indices (CRIs) were proposed from the continuum removed approach and extended for detecting the effects of heavy metal pollution over a full growth cycle. The relationship between the metal concentrations and CRIs of different plants was respectively analyzed by Stepwise Multiple Linear Regression (SMLR) and Partial Least Squares Regression (PLSR). It is found that a significant correlation exists between the band depth and the concentration of Cu and Ni based on the White birch data sets using the PLSR, resulting in a small deviation from the established relationships. Compared with VIs, the approach of coupling CRIs and multiple regressions was effective for improving the estimation accuracy. The presented study provides a detection model of leaf heavy metals that can be adapted to different growing cycles, even an arbitrary growing cycle. [ABSTRACT FROM AUTHOR]