Continuum Removal Research Articles

Improved multivariate modeling for soil organic matter content estimation using hyperspectral indexes and characteristic bands.

Soil organic matter (SOM) is a key index of soil fertility. Calculating spectral index and screening characteristic band reduce redundancy information of hyperspectral data, and improve the accuracy of SOM prediction. This study aimed to compare the improvement of model accuracy by spectral index and characteristic band. This study collected 178 samples of topsoil (0-20 cm) in the central plain of Jiangsu, East China. Firstly, visible and near-infrared (VNIR, 350-2500 nm) reflectance spectra were measured using ASD FieldSpec 4 Std-Res spectral radiometer in the laboratory, and inverse-log reflectance (LR), continuum removal (CR), first-order derivative reflectance (FDR) were applied to transform the original reflectance (R). Secondly, optimal spectral indexes (including deviation of arch, difference index, ratio index, and normalized difference index) were calculated from each type of VNIR spectra. Characteristic bands were selected from each type of spectra by the competitive adaptive reweighted sampling (CARS) algorithm, respectively. Thirdly, SOM prediction models were established based on random forest (RF), support vector regression (SVR), deep neural networks (DNN) and partial least squares regression (PLSR) methods using optimal spectral indexes, denoted here as SI-based models. Meanwhile, SOM prediction models were established using characteristic wavelengths, denoted here as CARS-based models. Finally, this research compared and assessed accuracy of SI-based models and CARS-based models, and selected optimal model. Results showed: (1) The correlation between optimal spectral indexes and SOM was enhanced, with absolute value of correlation coefficient between 0.66 and 0.83. The SI-based models predicted SOM content accurately, with the coefficient of determination (R2) and root mean square error (RMSE) values ranging from 0.80 to 0.87, 2.40 g/kg to 2.88 g/kg in validation sets, and relative percent deviation (RPD) value between 2.14 and 2.52. (2) The accuracy of CARS-based models differed with models and spectral transformations. For all spectral transformations, PLSR and SVR combined with CARS displayed the best prediction (R2 and RMSE values ranged from 0.87 to 0.92, 1.91 g/kg to 2.56 g/kg in validation sets, and RPD value ranged from 2.41 to 3.23). For FDR and CR spectra, DNN and RF models achieved more accuracy (R2 and RMSE values ranged from 0.69 to 0.91, 1.90 g/kg to 3.57 g/kg in validation sets, and RPD value ranged from 1.73 to 3.25) than LR and R spectra (R2 and RMSE values from 0.20 to 0.35, 5.08 g/kg to 6.44 g/kg in validation sets, and RPD value ranged from 0.96 to 1.21). (3) Overall, the accuracy of SI-based models was slightly lower than that of CARS-based models. But spectral index had a good adaptability to the models, and each SI-based model displayed the similar accuracy. For different spectra, the accuracy of CARS-based model differed from modeling methods. (4) The optimal CARS-based model was model CARS-CR-SVR (R2 and RMSE: 0.92 and 1.91 g/kg in validation set, RPD: 3.23). The optimal SI-based model was model SI3-SVR (R2 and RMSE: 0.87 and 2.40 g/kg in validation set, RPD: 2.57) and model SI-SVR (R2 and RMSE: 0.84 and 2.63 g/kg in validation set, RPD: 2.35).

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.

Selection of sensitive bands for assessing Alernaria blight diseased severity grades in mustard crops using hyperspectral reflectance

Recent development in remote sensing technology using hyperspectral reflectance or spectroscopic data was enabled the rapid and ongoing progression of monitoring, mapping, and surveillance/detection of insects tools for better crop management. This study describes a spectroscopic based methodology to escalation the efficiency of present surveillance practices (insect traps and human examinations) for detection pest infestation (e.g., Alternaria blight in mustard crop). The methodology uses ground based hyperspectral data across the spectral bands 350-2500nm at 1 nm interval. Three different statistical procedures such as correlation (between reflectance, 1st and 2nd derivatives with diseased severity grades), continuum removal analysis was implemented for selection of sensitive bands. In this method, we explore the combinations of different selected sensitive spectral bands and regions to separate diseased crops. The objectives of this research is to develop a novel methodology for selection of sensitive bands to Alternaria blight diseased crops. The development of such methodology would provide researchers, Agronomist, and remote sensing practitioners reliable and stable method to achieve faster technique with higher accuracy to mapping of Alternaria blight diseased crops.

Spectral characteristics analysis of typical ground objects in Poyang Lake wetland based on “Zhuhai-1” hyperspectral data

Hyperspectral image data provides new ideas and methods for the fine classification of wetland. Research on wetland spectral characteristics lays the foundation for wetland classification and improves classification accuracy. Based on “Zhuhai-1” hyperspectral image data, combined with the Pure Pixel Index (PPI), this paper extracted the average spectral curves of 11 typical ground objects in Poyang Lake wetland. Two mathematical transformation methods, namely, the continuum removal and the first derivative, were used to analyze the spectral characteristics of the ground objects before and after transformation, in combination with spectral characteristic parameters. The method of combining the mean distance of ground objects with the range of data error was used to select characteristic wavelengths before and after spectral transformation. Finally, the Mahalanobis distance method was used to verify the recognition effect. The results demonstrate that: (1) Spectral transformation can effectively amplify the differences between ground objects. The continuum removal led to an increase in the characteristic bands of four types of vegetation and the emergence of characteristic bands of four types of other ground objects. The first derivative method extended the characteristic bands of four vegetation from red-edge to near-infrared. (2) The method of combining the mean distance and the data error range can effectively screened out the spectral characteristic bands of typical ground objects in Poyang Lake wetland, resulting in hyperspectral dimensionality reduction. (3) The Mahalanobis distance method validates the recognition effect of the characteristic bands. In the screened characteristic bands, the Mahalanobis distance between different ground objects is larger than that between the same ground object, except between shoaly land and road. This study offers valuable insights into spectral recognition and classification of freshwater lake wetlands, and also demonstrates the potential of “Zhuhai-1” hyperspectral image data in wetland research.

Hyperspectral Characteristic Band Selection and Estimation Content of Soil Petroleum Hydrocarbon Based on GARF-PLSR.

With continuous improvements in oil production, the environmental problems caused by oil exploitation are becoming increasingly serious. Rapid and accurate estimation of soil petroleum hydrocarbon content is of great significance to the investigation and restoration of environments in oil-producing areas. In this study, the content of petroleum hydrocarbon and the hyperspectral data of soil samples collected from an oil-producing area were measured. For the hyperspectral data, spectral transforms, including continuum removal (CR), first- and second-order differential (CR-FD, CR-SD), and Napierian logarithm (CR-LN), were applied to eliminate background noise. At present, there are some shortcomings in the method of feature band selection, such as large quantity, time of calculation, and unclear importance of each feature band obtained. Meanwhile, redundant bands easily exist in the feature set, which seriously affects the accuracy of the inversion algorithm. In order to solve the above problems, a new method (GARF) for hyperspectral characteristic band selection was proposed. It combined the advantage that the grouping search algorithm can effectively reduce the calculation time with the advantage that the point-by-point search algorithm can determine the importance of each band, which provided a clearer direction for further spectroscopic research. The 17 selected bands were used as the input data of partial least squares regression (PLSR) and K-nearest neighbor (KNN) algorithms to estimate soil petroleum hydrocarbon content, and the leave-one-out method was used for cross-validation. The root mean squared error (RMSE) and coefficient of determination (R2) of the estimation result were 3.52 and 0.90, which implemented a high accuracy with only 8.37% of the entire bands. The results showed that compared with the traditional characteristic band selection methods, GARF can effectively reduce the redundant bands and screen out the optimal characteristic bands in the hyperspectral data of soil petroleum hydrocarbon with the method of importance assessment, which retained the physical meaning. It provided a new idea for the research of other substances in soil.

Quantifying Soil Goethite/Hematite Ratios: A New Method Based on Diffuse Reflectance Spectra

AbstractGoethite/hematite ratios in soils are widely used to reconstruct past climatic changes, but their accurate measurements have remained challenging due to the matrix effect. Here we present a new method for measuring soil goethite/hematite ratios by characterizing the band position of electron pair transition (EPT) based on the diffuse reflectance spectra processed by continuum removal. We introduce a “half‐band‐area wavelength”, λ1/2, to characterize the EPT band position and validate the method using synthetic standards made from mixing pure goethite and hematite and four sets of goethite‐ and hematite‐free matrices derived from arid aeolian deposits and tropical saprolite. A consistent λ1/2‐goethite/hematite relation across four matrices demonstrates that our method eliminates the matrix effect. We further validate our method by applying it to quantify goethite/hematite ratios in 180‐Kyr loess‐paleosol sequences and comparing the results to the reported paleoclimatic records. Our new method is promising for improving the measurement of goethite/hematite ratios in sediments.

Identification of wheat kernel varieties based on hyperspectral imaging technology and grouped convolutional neural network with feature intervals

Variety identification of seeds is essential for evaluating seed purity and ensuring crop yields. Hyperspectral imaging is a mainstream nondestructive testing method for seed purity. The hyperspectral data contains spectral and spatial information, which is large and redundant. According to the characteristics of hyperspectral data, this study used spectral feature intervals coupled with a grouped convolutional network to construct a seed variety identification model. Firstly, three spectral wavelength interval selection methods are used to constrain the spectrum, which are interval continuum removal (iCR), backward interval partial least squares (BiPLS), and interval random frog (iRF). Since spectral feature intervals in the hyperspectral image represent different physical and chemical characteristics, it is more effective to extract features of each interval independently by group convolution (GC). Then, the features are integrated into the network structure. The results showed that the combination of feature wavelength and grouping convolution enabled classification models effectively to obtain better classification accuracy and improve the inference speed of the model. The iCR-GC CNN model had the highest classification accuracy with a 4.4% increase and the fastest inference speed with a 44.21% reduction by comparing with the reference CNN classification model.

A novel algorithm for mapping carbonates using CRISM hyperspectral data

The algorithms for mapping carbonates from Compact Reconnaissance Imaging Spectrometer for Mars (CRISM) data use the depths of the diagnostic carbonate absorption features at ∼2.3 μm and ∼2.5 μm. However, because the band depths are estimated using fixed shoulder wavelengths, subtle shifts in band centres caused by different cations in the carbonates could result in false negatives for carbonates or false positives for other minerals that have absorption features in a similar wavelength range (eg. phyllosilicates, zeolites). This paper proposes a new algorithm that is based on the following attributes of carbonate spectra in the 2.0 to 3.0 μm range: (1) presence of two diagnostic overtones features around ∼2.3 μm and ∼2.5 μm; however, these features may show red shift or blue shift depending on the nature of cation(s); (2) the inter band gap between ∼2.3 μm and ∼2.5 μm carbonate absorption features, which remains relatively constant at ∼0.2 μm, even if there is a shift in the absorption features; (3) the contiguity of these two features, that is, carbonate spectra do not show any absorption features in between the above two features. The algorithm also includes a novel geometric continuum removal technique for locating the absorption features. The effectiveness of the algorithm is demonstrated using laboratory spectra, CRISM machine learning toolkit's mineral dataset, as well as CRISM images. The true positive rate (TPR), true negative rate (TNR) and overall accuracy for the method over the CRISM machine learning toolkit's mineral dataset are 29%, 87% and 83%, respectively.

Estimation of Winter Wheat Canopy Chlorophyll Content Based on Canopy Spectral Transformation and Machine Learning Method

Canopy chlorophyll content (CCC) is closely related to crop nitrogen status, crop growth and productivity, detection of diseases and pests, and final yield. Thus, accurate monitoring of chlorophyll content in crops is of great significance for decision support in precision agriculture. In this study, winter wheat in the Guanzhong Plain area of the Shaanxi Province, China, was selected as the research subject to explore the feasibility of canopy spectral transformation (CST) combined with a machine learning method to estimate CCC. A hyperspectral canopy ground dataset in situ was measured to construct CCC prediction models for winter wheat over three growth seasons from 2014 to 2017. Sensitive-band reflectance (SR) and narrow-band spectral index (NSI) were established based on the original spectrum (OS) and CSTs, including the first derivative spectrum (FDS) and continuum removal spectrum (CRS). Winter wheat CCC estimation models were constructed using univariate regression, partial least squares (PLS) regression, and random forest (RF) regression based on SR and NSI. The results demonstrated the reliability of CST combined with the machine learning method to estimate winter wheat CCC. First, compared with OS-SR (683 nm), FDS-SR (630 nm) and CRS-SR (699 nm) had a larger correlation coefficient between canopy reflectance and CCC; secondly, among the parametric regression methods, the univariate regression method with CRS-NDSI as the independent variable achieved satisfactory results in estimating the CCC of winter wheat; thirdly, as a machine learning regression method, RF regression combined with multiple independent variables had the best winter wheat CCC estimation accuracy (the determination coefficient of the validation set (Rv2) was 0.88, the RMSE of the validation set (RMSEv) was 3.35 and relative prediction deviation (RPD) was 2.88). Thus, this modeling method could be used as a basic method to predict the CCC of winter wheat in the Guanzhong Plain area.

UAV-Hyperspectral Imaging to Estimate Species Distribution in Salt Marshes: A Case Study in the Cadiz Bay (SW Spain)

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.

Identification of Constructive Species and Degraded Plant Species in the Temperate Typical Grassland of Inner Mongolia Based on Hyperspectral Data

In recent years, grassland degradation has become a global ecological problem. The identification of degraded grassland species is of great significance for monitoring grassland ecological environments and accelerating grassland ecological restoration. In this study, a ground spectral measurement experiment of typical grass species in the typical temperate grassland of Inner Mongolia was performed. An SVC XHR-1024i spectrometer was used to obtain field measurements of the spectra of grass species in the typical grassland areas of the study region from 6–29 July 2021. The parametric characteristics of the grass species’ spectral data were extracted and analyzed. Then, the spectral characteristic parameters + vegetation index, first-order derivative (FD) and continuum removal (CR) datasets were constructed by using principal component analysis (PCA). Finally, the RF, SVM, BP, CNN and the improved CNN model were established to identify Stipa grandis (SG), Cleistogenes squarrosa (CS), Caragana microphylla Lam. (CL), Leymus chinensis (LC), Artemisia frigida (AF), Allium ramosum L. (AL) and Artemisia capillaris Thunb. (AT). This study aims to determine a high-precision identification method based on the measured spectrum and to lay a foundation for related research. The obtained research results show that in the identification results based on ground-measured spectral data, the overall accuracy of the RF model and SVM model identification for different input datasets is low, but the identification accuracies of the SVM model for AF and AL are more than 85%. The recognition result of the CNN model is generally worse than that of the BP neural network model, but its recognition accuracy for AL is higher, while the recognition effect of the BP neural network model for CL is better. The overall accuracy and average accuracy of the improved CNN model are all the highest, and the recognition accuracy of AF and CL is stable above 98%, but the recognition accuracy of CS needs to be improved. The improved CNN model in this study shows a relatively significant grass species recognition performance and has certain recognition advantages. The identification of degraded grassland species can provide important scientific references for the realization of normal functions of grassland ecosystems, the maintenance of grassland biodiversity richness, and the management and planning of grassland production and life.

PHANGS–JWST First Results: Mapping the 3.3 μm Polycyclic Aromatic Hydrocarbon Vibrational Band in Nearby Galaxies with NIRCam Medium Bands

We present maps of the 3.3 μm polycyclic aromatic hydrocarbon (PAH) emission feature in NGC 628, NGC 1365, and NGC 7496 as observed with the Near-Infrared Camera imager on JWST from the PHANGS–JWST Cycle 1 Treasury project. We create maps that isolate the 3.3 μm PAH feature in the F335M filter (F335MPAH) using combinations of the F300M and F360M filters for removal of starlight continuum. This continuum removal is complicated by contamination of the F360M by PAH emission and variations in the stellar spectral energy distribution slopes between 3.0 and 3.6 μm. We modify the empirical prescription from Lai et al. to remove the starlight continuum in our highly resolved galaxies, which have a range of starlight- and PAH-dominated lines of sight. Analyzing radially binned profiles of the F335MPAH emission, we find that between 5% and 65% of the F335M intensity comes from the 3.3 μm feature within the inner 0.5 r 25 of our targets. This percentage systematically varies from galaxy to galaxy and shows radial trends within the galaxies related to each galaxy’s distribution of stellar mass, interstellar medium, and star formation. The 3.3 μm emission is well correlated with the 11.3 μm PAH feature traced with the MIRI F1130W filter, as is expected, since both features arise from C–H vibrational modes. The average F335MPAH/F1130W ratio agrees with the predictions of recent models by Draine et al. for PAHs with size and charge distributions shifted toward larger grains with normal or higher ionization.

Application of hyperspectral imaging technology to digitally protect murals in the Qutan temple

Hyperspectral imaging technology is a research hotspot in the field of cultural heritage protection. It can be used to quickly and noninvasively obtain detailed spectral information from the surfaces of cultural relics of different categories. We can intuitively analyse pigment compositions, line characteristics, painting skills and patterns using spectral information. Hyperspectral imaging has high scientific significance and application value for the protection, restoration and research of ancient murals and other cultural relics. In this study, a mural from Daheitian hall in the Qutan temple, Qinghai Province, China, was used as a sample. The hyperspectral data were acquired and analysed for several purposes. Pigment spectral matching and abundance inversion were carried out to obtain the pigment distribution. These data were enhanced by continuum removal and histogram stretching to obtain hidden information. The dark channel prior, Criminisi and Retinex methods were used to virtually restore the image of the mural. The results indicated that by using hyperspectral imaging data, the constructed pure pigment spectrum library and suitable approaches, the types and distributions of mural pigments can be quantitatively analysed, and the lines in murals can be extracted. Hyperspectral images are helpful for identifying information hidden by pigments or surface materials. Mural images can be enhanced, and hidden information can be highlighted using enhancement methods, such as continuum removal and histogram linear stretching. In addition, hyperspectral imaging data have unique advantages in the restoration of mural images, and the combination of defogging methods and image inpainting algorithms can realize the virtual restoration of mural images. In brief, hyperspectral imaging technology was found to have a highly favourable effect on pigment analysis, line extraction, information enhancement, hidden information extraction and the virtual restoration of ancient murals.

A method for detecting underground natural gas pipeline micro-leakage in vegetated areas using high spatial resolution hyperspectral imagery

Natural gas is an important clean energy source that is mainly transported through buried pipelines. However, slight leakage during transportation is inevitable and needs to be identified in time to reduce the risk of related accidents. For this purpose, remote sensing can be used as an indirect and non-destructive technique to detect natural gas leakage through vegetation. Abundant spectral and detailed spatial information enables the high spatial resolution hyperspectral imagery to capture subtle stress responses from vegetation. In this study, we designed a simulation experiment of natural gas leakage in vegetated areas, and collected the high spatial resolution hyperspectral images of three plant species. Considering the shadow problem contained in high spatial resolution images, a new vegetation pixel extraction method to eliminate the influence of background shadows was proposed. Then, two spectral transformation methods, continuum removal (CR) and variational mode decomposition (VMD), were integrated to analyze the vegetation spectra, and a spectral index which could reflect the degree of vegetation stress was designed based on the spectral characteristics, named CVI (Continuum removal - Variational mode decomposition Index). Finally, the threshold segmentation methods and the cumulative minimum circumscribed circle method were used to extract the range and location of natural gas leakage. The study demonstrated the potential of using high spatial hyperspectral imagery to map and monitor natural gas leakage through its stress on vegetation. Results of this research can be a reference for the fine identification of stressed plants and are expected to be applied to provide support for related departments and stakeholders.

Estimating the Texture of Purple Soils Using Vis-NIR Spectroscopy and Optimized Conversion Models

Soil texture is an indicator of soil physical structure which delivers many ecological functions of soils such as thermal regime, plant growth, and soil quality. However, traditional methods for soil texture measurement are time-consuming and labor-intensive. This study attempts to explore an indirect method for rapid estimating the texture of three subgroups of purple soils (i.e. calcareous, neutral, and acidic). 190 topsoil (0 - 10 cm) samples were collected from sloping croplands in Tongnan and Beibei Districts of Chongqing Municipality in China. Vis-NIR spectrum was measured and processed, and stepwise multiple linear regression (SMLR), partial least squares regression (PLSR), and back propagation neural network (BPNN) models were constructed to inform the soil texture. The clay fractions ranged from 4.40% to 27.12% while sand fractions ranged from 0.34% to 36.57%, hereby soil samples encompass three textural classes (i.e. silt, silt loam, and silty clay loam). For the original spectrum, the texture of calcareous and neutral purple soils was not significantly correlated with spectral reflectance and linear models (SMLR and PLSR) exhibited low prediction accuracy. The correlation coefficients and the goodness-of-fits between soil texture and the transformed spectra of all soil groups increased by continuum-removal (CR), first-order differential (R'), and second-order differential (R") transformations. Among them, the R" had the best performance in terms of improving the correlation coefficients and the goodness-of-fits. For the calcareous purple soil, the SMLR exceeds PLSR and BPNN with a higher coefficient of determination (R2) and the ratio of performance to inter-quartile distance (RPIQ) values and lower root mean square error of validation (RMSEV), but for the neutral and acidic purple soils, the PLSR model has a better prediction accuracy. In summary, the linear methods (SMLR and PLSR) are more reliable in estimating the texture of the three purple soil groups when using Vis-NIR spectroscopy inversion.

Soil copper concentration map in mining area generated from AHSI remote sensing imagery

Hyperspectral remote sensing has the advantages to predict and map soil heavy metal concentration over conventional monitoring methods and multispectral remote sensing. In quantitative applications of hyperspectral remote sensing imagery, the contribution of hyperspectral bands is different, and abnormal prediction values resulted from incorrectly classified bare soil images are a major problem. In this study, a variable weighting method was proposed to weight the hyperspectral bands, and a probability threshold was used to improve the classification to mitigate the problem of abnormal prediction values. The variable weighting was conducted by using the absorption depths obtained by continuum removal. Soil samples were collected from a mining area in southwestern China. Hyperspectral remote sensing imagery was acquired by the Advanced Hyperspectral Imager (AHSI) abroad on Geofen-5 (GF-5) satellite. Genetic algorithm and partial least squares regression (PLSR) were adopted to calibrate prediction models. In prediction of soil copper (Cu) concentration, root mean square error (RMSE) and coefficient of determination (R2) were 21.59 mg kg−1 and 0.60 for the prediction using raw reflectance spectra, and the values were improved to 18.33 mg kg−1 and 0.71 by using the weighted reflectance spectra. The developed prediction model was applied to the AHSI imagery to predict Cu concentration in bare soil areas. In prediction of Cu concentration using the AHSI imagery, negative prediction values were eliminated by using the bare soil image extracted by the improved classification. Based on the prediction, soil Cu concentration map was generated by kriging spatial interpolation. The result indicates that the proposed variable weighting method is effective and the problem of abnormal prediction values could be mitigated by using improved bare soil images. Further analysis indicates that some indices with proper thresholds also could be used to get improved bare soil images.

Remotely sensed carbon content: The role of tree composition and tree diversity

Optical remote sensing permits modeling of variables related to forest biomass, which is a critical determinant of carbon (C) stocks and fluxes. Plant functional characteristics can be captured by (hyper)spectral data, but it remains unclear whether the links between spectral information and C content are driven largely by tree composition, tree diversity, or by forest attributes not commonly measured in field inventories (e.g., physical canopy structure). Here, we examine the relationship between hyperspectral reflectance and aboveground C content in forests, testing the relative importance of tree composition and diversity in mediating this relationship. We use hyperspectral imaging data from an airborne survey with precisely geo-located field data on canopy trees in two forests in southern Québec, Canada. Spectral data covering visible (VIS), near infrared (NIR) and short-wave infrared (SWIR) wavelengths were extracted for 2626 tree crowns within 64 field plots distributed along an elevational gradient. We applied a continuum removal to the spectra and subsequently performed a principal component analysis to reduce the spectral dimensionality. From the spectral principal components, for each plot we quantified (i) spectral composition (based on average reflectance per plot), and (ii) spectral diversity using the convex hull volume. From field data, we calculated variables characterizing the taxonomic, functional and phylogenetic composition and diversity of canopy trees. Carbon content was calculated using allometric equations based on tree size. We applied a structural equation model based on partial-least squares to test both indirect effects of spectral composition and diversity on C storage of trees (via on-the-ground tree composition or diversity), and also direct effects (reflecting forest characteristics unmeasured in field surveys). We found that spectral composition, particularly from the VIS, is related to C content largely indirectly, via changes in tree composition along the elevational gradient (a transition from deciduous to coniferous species with increasing elevation). Though spectral diversity was significantly related to tree species diversity, no direct or indirect effects on C content were detected. Overall, our findings support (i) the importance of tree composition (but not diversity) in mediating the link between hyperspectral data and forest C content, and (ii) the use of hyperspectral remote sensing as an effective surrogate of taxonomic, functional, and phylogenetic composition of tree communities with strong links to C storage.

Geostatistical Modelling of Soil Spatial Variability by Fusing Drone-Based Multispectral Data, Ground-Based Hyperspectral and Sample Data with Change of Support

Traditional soil characterization methods are time consuming, laborious and invasive and do not allow for long-term repeatability of measurements. The overall aim of this paper was to assess and model spatial variability of the soil in an olive grove in south Italy by using data from two sensors of different types: a multi-spectral on-board drone radiometer and a hyperspectral visible-near infrared-shortwave infrared (VIS-NIR-SWIR) reflectance radiometer, as well as sample data, to arrive at a delineation of homogeneous areas. The hyperspectral data were processed using Continuum Removal (CR) methodology to obtain information about the content and composition of clay. Differently, the multispectral data were firstly upscaled to the support of soil data using geostatistics and taking into account the change of support. Secondly, the data acquired with the two different sensors were integrated with soil granulometric properties by using two multivariate geostatistical techniques: multi-collocated cokriging to achieve a more exhaustive and finer-scale soil characterization, and multi-collocated factor cokriging to extract synthetic scale-dependent indices (regionalized factors) for the delineation of soil in homogeneous zones. This paper shows the impact of change of support on the uncertainty of soil prediction that can have a significant effect on decision making in Precision Agriculture. Moreover, four regionalized factors at two different scales (two for each scale) were retained and mapped. Each factor provided a different delineation of the field with areas characterized by different granulometries and clay compositions. The applied method is sufficiently flexible and could be applied to any number and type of sensors.

Estimation of multi-media metal(loid)s around abandoned mineral processing plants using hyperspectral technology and extreme learning machine.

Hyperspectral techniques are promising alternatives to traditional methods of investigating potentially toxic metal(loid) contamination. In this study, hyperspectral technology combined with partial least squares regression (PLSR) and extreme learning machine (ELM) established estimation models to predict the contents of copper (Cu), zinc (Zn), arsenic (As), cadmium (Cd), lead (Pb) and tin (Sn) in multi-media environments (mine tailings, soils and sediments) surrounding abandoned mineral processing plants in a typical tin-polymetallic mineral agglomeration in Guangxi Autonomous Region. Four spectral preprocessing methods, Savitzky-Golay (SG) smoothing, continuum removal (CR), first derivative (FD) and continuous wavelet transform (CWT), were used to eliminate noise and highlight spectral features. The optimum combinations of spectral preprocessing and machine learning algorithms were explored, then the estimation models with best accuracy were obtained. CWT and CR were excellent spectral pretreatments for the hyperspectral data regardless of the applied algorithms. The coefficients of determination (R2) of estimation models for the best accuracy of various metals (loid) are as follows: Cu (CWT-ELM:0.85), Zn (CR-PLSR:0.93), As (CWT-ELM: 0.86), Cd (CR-PLSR: 0.89), Pb (CWT-PLSR: 0.75) and Sn (CR-ELM: 0.81). In contrast, ELM models had higher accuracy with R2 > 0.80 (except Cd and Pb). In conclusion, ELM-based spectral estimation models are able to predict metal (loid) concentrations with high accuracy and efficiency, providing a potential new combinatorial approach for estimating toxic metal contamination in multi-media environments.

Hyperspectral Reconnaissance: Joint Characterization of the Spectral Mixture Residual Delineates Geologic Unit Boundaries in the White Mountains, CA

We use a classic locale for geology education in the White Mountains, CA, to demonstrate a novel approach for using imaging spectroscopy (hyperspectral imaging) to generate base maps for the purpose of geologic mapping. The base maps produced in this fashion are complementary to, but distinct from, maps of mineral abundance. The approach synthesizes two concepts in imaging spectroscopy data analysis: the spectral mixture residual and joint characterization. First, the mixture residual uses a linear, generalizable, and physically based continuum removal model to mitigate the confounding effects of terrain and vegetation. Then, joint characterization distinguishes spectrally distinct geologic units by isolating residual, absorption-driven spectral features as nonlinear manifolds. Compared to most traditional classifiers, important strengths of this approach include physical basis, transparency, and near-uniqueness of result. Field validation confirms that this approach can identify regions of interest that contribute significant complementary information to PCA alone when attempting to accurately map spatial boundaries between lithologic units. For a geologist, this new type of base map can complement existing algorithms in exploiting the coming availability of global hyperspectral data for pre-field reconnaissance and geologic unit delineation.