Continuum Removal Research Articles

Limits for the Identification of Smectites Mixed with Common Minerals Based on Short-Wave Infrared Spectroscopy

The identification of minerals, particularly clay minerals, using visible, near-infrared, and short-wave infrared (VNIR-SWIR) spectroscopy has gained prominence due to its efficiency and the advancement of remote hyperspectral sensors. However, identifying minerals in polymineralic samples remains challenging due to overlapping absorption features. This study prepared systematic binary mixtures of two smectites (dioctahedral and trioctahedral) with common non-clay minerals (calcite, dolomite, gypsum, quartz, and feldspar). Spectra from these mixtures were obtained using the ASD FieldSpec 4 Hi-Res spectroradiometer and analyzed with continuum removal and second derivative preprocessing to define detection limits. These limits indicate the minimum percentage of each mineral required for clear identification in various smectite–non-clay combinations. After continuum removal, smectites are identified at ≥5%–10% in mixtures with carbonates, quartz, and feldspar, but ≥70% is needed for gypsum. Non-clay minerals have detection limits of ≥70% for calcite and 20% for gypsum in the presence of smectites, while dolomite remains undetectable. The second derivative improves these limits, enabling smectite identification at 5% in carbonate mixtures and 5%–15% in gypsum mixtures. Calcite detection limits are 65%, and dolomite can be identified at ≥65% and ≥85% with dioctahedral and trioctahedral smectites, respectively. Gypsum detection limits are reduced to 10%, while quartz and feldspar cannot be identified due to lacking absorption features.

Spectral Characteristics and Identification of Degraded Alpine Meadow in Qinghai–Tibetan Plateau Based on Hyperspectral Data

Grassland degradation poses a significant challenge to achieving the Sustainable Development Goals (SDGs) on the Qinghai–Tibetan Plateau (QTP). Effective monitoring of grassland degradation is essential for ecological restoration. Hyperspectral technology offers efficient and accurate identification of degradation. However, the influence of observation time, data analysis methods and classification techniques on the accuracy of identifying alpine grasslands remains unclear. In this study, the spectral reflectance of degraded alpine meadow, alpine meadow, alpine shrub and Tibetan barley was measured from May to September 2023 using a ground spectrometer in the northeastern QTP. First-order derivatives (FDR) and continuum removal were applied to the spectra, and characteristic parameters and vegetation indices were calculated. Support vector machine (SVM), random forest (RF), artificial neural network (ANN) and decision tree (DT) were then used to compare the classification accuracy between different months, transformation methods and characteristic parameters. The results showed that the spectral reflectance peaked in July, with significant differences in the near infrared (NIR) bands between alpine meadow and degraded alpine meadow. Alpine shrub and Tibetan barley showed greater differences in reflectance compared to other vegetation types, especially in the NIR bands. Data transformations improved reflectance and absorption characteristics in the NIR and visible bands. Indices such as DVI, RVI and NDGI effectively differentiated vegetation types. Optimal accuracy for the identification of degraded alpine meadow in July was achieved using FDR transformations and ANN or SVM for classification. This study provides methodological insights for monitoring grassland degradation on the QTP.

Potential of Hyperspectral Data Combined With Optimal Band Combination Algorithm for Estimating Soil Organic Carbon Content in Lakeside Oasis

ABSTRACTAccurate estimation of soil organic carbon (SOC) content is essential for promoting regional sustainable agriculture and improving land quality. Visible and near‐infrared (Vis‐NIR) near‐Earth remote sensing spectroscopy has become an effective alternative to the traditional time‐consuming and costly methods due to its high‐resolution and nondestructive application, but it is vulnerable to the redundancy of spectral information and the overlap between bands. This study delves into the potential of optimal spectral parameters for estimating SOC in arid lakeside oases, using Bosten Lake in Xinjiang, China, as a focal point. Soil samples (0–10 cm, 10–20 cm, 20–30 cm, 30–40 cm) were collected, and their SOC content and hyperspectral reflectance were measured. The spectral data underwent preprocessing techniques, including continuum removal (CR), standard normal variate (SNV), and continuous wavelet transform (CWT). SOC content was predicted using back propagation neural network models constructed based on one‐dimensional (1D), two‐dimensional (2D), and three‐dimensional (3D) correlation coefficients. Results showcased the effectiveness of the CWT method in accentuating potential spectral information and enhancing variable correlation. Among the indices, 3D exhibited the highest performance (R2 = 0.82, RPD = 2.02 for TDI‐1 at 0–10 cm; R2 = 0.85, RPD = 2.28 for TDI‐2 at 10–20 cm; R2 = 0.83, RPD = 2.24 for TDI‐1 at 20–30 cm; R2 = 0.86, RPD = 2.53 for TDI‐4 at 30–40 cm), followed by 2D and then 1D. These insights offer guidance for future strategies in hyperspectral data preprocessing and spectral index determination, facilitating SOC spatial distribution mapping and advancing sustainable agricultural planning. They also have implications for determining the spatial distribution of SOC content based on spatial interpolation, which would contribute to regional agricultural planning and sustainable development.

Prediction of soil heavy metal content around mine tailings using multiple methods combined with transformed hyperspectral reflectance data

The extensive accumulation of tailings can potentially cause heavy metal contamination in the surrounding farmland soil. Accurately predicting the spatial distribution of heavy metals in farmland soil is crucial for assessing the potential environmental hazards of tailings.This study focuses on the spatial distribution and the quantitative prediction of heavy metals (chromium (Cr), vanadium (V), and copper (Cu)) in soils surrounding mine tailings using advanced spectral data analysis and multiple prediction models. The original hyperspectral reflectance data were processed using first-order differential (FD), second-order differential (SD), reciprocal logarithmic (LR), and continuum removal (CR) transformations to highlight the positions of characteristic bands. Multiple linear regression (MLR), stepwise linear regression (SLR), partial least squares regression (PLSR), random forest (RF), and back propagation artificial neural network (BP-ANN) models were used to establish inversion models for Cr, V, and Cu based on bands with high correlation coefficients. The performance of the inversion models was evaluated using the coefficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE), and residual predictive deviation (RPD). The results indicate that the raw hyperspectral data from the measured soil exhibit a weak response to heavy metal content in the study area. However, applying FD, SD, and CR transformations significantly enhances the sensitivity of soil spectral data to heavy metal concentrations, facilitating subsequent modeling. Among these, the SD transformation is particularly beneficial for modeling the Cr and Cu elements in the soil. For the V element, the FD transformation yields data that are more suitable for modeling. Regarding the inversion models based on the measured spectral data, the BP-ANN model exhibited the best predictive performance. Specifically, when combined with SD spectral data, the BP-ANN achieved the highest predictive accuracy for Cu content (R² = 0.85, RPD = 2.12). The RF model demonstrated the next best performance, with its optimal inversion model also utilizing SD spectral data for predicting Cu content (R² = 0.76, RPD = 1.90). On the other hand, the MLR model exhibited the poorest performance and is unsuitable for predicting heavy metal content in the region using the measured spectral data. This study highlights the potential of spectral data in environmental monitoring and provides a technical reference for the inversion assessment and regulation of heavy metals in farmlands surrounding tailing sites.

Feature Selection and Spectral Indices for Identifying Maize Stress Types

This study aims to identify different types of stress on maize leaves using feature selection and spectral index methods. Spectral data were collected from leaves under heavy metal, water, fertilizer stress, as well as under normal healthy conditions. Preprocessing steps such as continuum removal (CR), standard normal variable (SNV) transformation, multiple scattering correction (MSC), detrend correction (DT), and first-order derivative (FOD) were applied to the raw spectra. Various feature selection methods including ReliefF, chi-square test, recursive feature elimination (FRE), mutual information (MI), random forest (RF), and gradient boosting tree (GBT) were employed to determine the importance scores of different spectral bands, thus identifying sensitive spectral features capable of distinguishing various stress types. Spectral indices for stress type differentiation were constructed using label correlation method. Classification models were built using support vector machine (SVM), K-nearest neighbors (KNN), Gaussian naive Bayes (GNB), extreme gradient boosting (XGBoost), RF, and adaptive boosting (AdaBoost) algorithms. Results indicate that the characteristic spectral bands for differentiating stress types are primarily distributed around the red edge (near 700–800 nm) and water absorption valley (near 1900 nm). Spectral indices constructed using combinations of spectral bands around the near-infrared plateau absorption valley (near 1185 nm) and water absorption valley (near 1460 nm) effectively differentiate maize stress types. Among the modeling classification algorithms, RF and AdaBoost algorithms exhibited optimal performance, demonstrating high classification accuracy on both training and validation sets. These findings hold promise for providing new technical support for maize stress monitoring and diagnosis in agricultural production.

Classifying Plant Communities in the North American Coastal Plain With PRISMA Spaceborne Hyperspectral Imagery and the Spectral Mixture Residual

AbstractThe effort to map terrestrial biodiversity, in recent years limited mostly to the use of broadband multispectral remote sensing at decameter scales, can be greatly enhanced by harnessing hyperspectral imagery. Interpretation of hyperspectral imagery may be aided by the Mixture Residual (MR) spectral preprocessing transformation. MR integrates the benefits of spectral mixture analysis with the absorption peak‐enhancing characteristics of continuum removal. MR characterizes each pixel as a linear combination of generic end‐members estimating the spectral continuum, from which the residual of each wavelength is computed and treated as a source of additional information. Using Hyperspectral Precursor of the Application Mission (PRISMA) imagery, we tested the ability of MR‐transformed reflectance as compared to untransformed surface reflectance (SR) to map plant associations and land cover using ground truthing and random forest classifications across four landscapes within the North American Coastal Plain. We used a forward stepwise selection algorithm to choose bands for each classification and subsequently compared these between SR and MR. Our MR classifications distinguished land cover with 5% greater balanced accuracy on average than the SR‐based classifications across all four landscapes. The MR‐based classification that integrated data from all landscapes into a unified model encompassing all 21 land cover types achieved a 76% average balanced accuracy over three iterations. Generally, MR utilized the near‐infrared region to a greater degree than SR while deemphasizing the green peak. Based on our results, MR improves the accuracy of mapping terrestrial biodiversity, likely extending to other current and planned satellite hyperspectral missions.

Reflectance spectroscopy analysis and lithium content estimation in lithium-rich rocks and stream sediments: Insights from Tuanjie Peak, Western Kunlun, China

Lithium, a rare metal of strategic importance, has garnered heightened global attention. This investigation delves into the laboratory visible-near infrared and short-wavelength infrared reflectance (VNIR-SWIR 350 nm–2500 nm) spectral properties of lithium-rich rocks and stream sediments, aiming to elucidate their quantitative relationship with lithium concentration. This research seeks to pave new avenues and furnish innovative technical solutions for probing sedimentary lithium reserves. Conducted in the Tuanjie Peak region of Western Kunlun, Xinjiang, China, this study analyzed 614 stream sediments and 222 rock specimens. Initial steps included laboratory VNIR-SWIR spectral reflectance measurements and lithium quantification. Following the preprocessing of spectral data via Savitzky-Golay (SG) smoothing and continuum removal (CR), the absorption positions (Pos2210nm, Pos1910nm) and depths (Depth2210, Depth1910) in the rock spectra, as well as the Illite Spectral Maturity (ISM) of the rock samples, were extracted. Employing both the Successive Projections Algorithm (SPA) and genetic algorithm (GA), wavelengths indicative of lithium content were identified. Integrating the lithium-sensitive wavelengths identified by these feature selection methods, A quantitative predictive regression model for lithium content in rock and stream sediments was developed using partial least squares regression (PLSR), support vector regression (SVR), and convolutional neural network (CNN). Spectral analysis indicated that lithium is predominantly found in montmorillonite and illite, with its content positively correlating with the spectral maturity of illite and closely related to Al-OH absorption depth (Depth2210) and clay content. The SPA algorithm was more effective than GA in extracting lithium-sensitive bands. The optimal regression model for quantitative prediction of lithium content in rock samples was SG-SPA-CNN, with a correlation coefficient prediction (Rp) of 0.924 and root-mean-square error prediction (RMSEP) of 0.112. The optimal model for the prediction of lithium content in stream sediment was SG-SPA-CNN, with an Rp and RMSEP of 0.881 and 0.296, respectively. The higher prediction accuracy for lithium content in rocks compared to sediments indicates that rocks are a more suitable medium for predicting lithium content. Compared to the PLSR and SVR models, the CNN model performs better in both sample types. Despite the limitations, this study highlights the effectiveness of hyperspectral technology in exploring the potential of clay-type lithium resources in the Tuanjie Peak area, offering new perspectives and approaches for further exploration.

MoonIndex, an Open‐Source Tool to Generate Spectral Indexes for the Moon From M3 Data

AbstractSpectral indexes are tools widely used to analyze the composition of planetary surfaces. Many indexes have been formulated over the years to map the lunar surface, but there is no unified database for them. In this work we describe an Open‐Source Python package called MoonIndex, that recreates 38 indexes compiled from the literature, using data from the Moon Mineralogy Mapper (M3). The processing started with the filtering of the data cubes to reduce the noise, the continuum of the spectrum was then removed using a convex hull or a second‐and‐first‐order fit method. Later, the indexes were calculated, following as possible the original formulations. The results on spectral indexes calculated before the continuum removal were similar to those of the original formulations. Conversely, the results obtained for spectral indexes calculated after the continual removal were not always coherent. Some indexes, like the band depth, are especially sensitive to the removal method, as well as the derived band areas and asymmetries. We also recreated RGB composite maps, our results highlight the compositional patterns in a similar way as the ones in the literature, even if the color ramps can differ. The products of MoonIndex are open, ready for interpretation, versatile, consistent, and cross‐comparable.

Modeling risk assessment of soil heavy metal pollution using partial least squares and fuzzy logic: A case study of a gully type coal-based solid waste dumpsite

Continuous release and migration of heavy metals from coal-based solid waste (CSW) dumpsites often results in significant encroachment on ecological lands and pollution of natural environments. As a result, there is an urgent need for long-term and rapid monitoring, analysis, and assessment to control environmental risks associated with large CSW dumpsites. We constructed a new composite model (PLS-FL) that uses partial least squares regression (PLSR) and fuzzy logic inference (FLI) to accurately predict heavy metal concentrations in soils and assess pollution risk levels. The potential application of the PLS-FL was tested through a gully type CSW case study. We compared 20 modeling strategies using the PLS-FL: five types heavy metals (Cd, Zn, Pb, Cr and As) * four spectral transformation methods (first derivative (FD), second derivative (SD), reverse logarithm (RL), and continuum removal (CR)) * one variable selection method (competitive adaptive reweighted sampling (CARS)). The results showed that the combination of derivative transformation and CARS was recommended for estimation, with R2C > 0.80 and R2P > 0.50. When comparing the PLSR model with four traditional machine learning methods (Support Vector Machines (SVM), Random Forests (RF), Extreme Learning Machines (ELM), and KNN), the PLSR model demonstrated the highest average prediction accuracy. Additionally, the FLI process no longer relies on human perception and expert opinion, enhancing the model's objectivity and reliability. The evaluation results revealed that the heavy metal contamination areas of the CSW dumpsite are concentrated at the bottom of the gully, with more severe contamination in the north. Furthermore, a high-risk zone exists in the interim storage area for CSW to the east of the dump. These findings align with the initial detections at the sampling sites and highlight the need for targeted monitoring and control in these areas. The application of the model will empower regulators to quickly assess the overall situation of large-scale heavy metal pollution and provide scientific program and data support for continuous large-scale pollution risk monitoring and sustainable risk management.

Machine Learning and Feature Selection for soil spectroscopy. An evaluation of Random Forest wrappers to predict soil organic matter, clay, and carbonates

Soil spectroscopy estimates soil properties using the absorption features in soil spectra. However, modelling soil properties with soil spectroscopy is challenging due to the high dimensionality of spectral data. Feature Selection wrapper methods are promising approaches to reduce the dimensionality but are barely used in soil spectroscopy. The aim of this study is to evaluate the performance of two feature selection wrapper methods, Sequential Forward Selection (SFS) and Sequential Flotant Forward Selection (SFFS) built using the Random Forest (RF) algorithm, for dimensionality reduction of spectral data and predictive modelling of modelling soil organic matter (SOM), clay and carbonates. The reflectance of 100 soil samples, acquired from Sierra de las Nieves (Spain), was measured under laboratory conditions using ASD FieldSpec Pro JR. Four different datasets were obtained after applying two spectral preprocessing methods to raw spectra: raw spectra, Continuum Removal (CR), Multiplicative Scatter Correction (MSC), and a so-called “Global” dataset composed of raw, CR and MSC features. The performance of RF models built with feature selection methods was compared to that of Partial Least Squares Regression (PLSR) and RF (alone).RF models built with SFS and SFFS outperformed PLSR and RF alone models: The best RF models with feature selection had a respective ratio of performance to interquartile distance of 1.93, 0.38 and 2.56. PLSR models had an accuracy of 1.41, 0.29 and 1.81 for SOM, carbonates, and clay, respectively. RF alone had a respective performance of 1.29, 0.29 and 1.81. The application of feature selection wrapper methods reduced the number of features to less than 1 % of the starting features. Features were selected across all spectra for SOM and clay, and around 900 nm, 1900 nm, and 2350 nm for carbonates. However, feature selection highlighted features around 1100 nm in SOM modelling, as well as other features around 2200 nm, which is considered a main absorption feature of clay. The application of feature selection with Random Forest was very important in improving modelling accuracy, reducing the redundant features and avoiding the curse of dimensionality or Hughes effect. Thus, this research showed an alternative to dimensionality reduction approaches that have been applied to date to model soil properties with spectroscopy and paves the way for further scientific investigation based on feature selection methods and machine learning.

Selection of Spectral Parameters and Optimization of Estimation Models for Soil Total Nitrogen Content during Fertilization Period in Apple Orchards

The rapid and accurate diagnosis of nitrogen content in apple orchard soil is of great significance for the rational application of nitrogen fertilizer in orchards to improve apple yield and quality. An apple orchard in Shuangquan Town, Changqing District, Jinan City, Shandong Province, was taken as the experimental area. The optimal method for extracting spectral characteristic bands and screening spectral characteristic indices (SCIs) of soil total nitrogen (TN) for independent and comprehensive fertilization periods was explored. Independent and comprehensive soil TN content estimation models were constructed and optimized for each and the entire fertilization period, respectively. The results show that compared with the correlation coefficient method, stepwise multiple linear regression (SMLR) performs better in extracting hyperspectral characteristic bands of soil TN content. It helps to achieve a higher modeling accuracy, smaller root mean square error (RMSE), and is more conducive to avoiding the influence of multicollinearity of model variables. The sensitive areas of soil TN content in the SCI do not undergo significant changes due to different fertilization periods. Among them, the ratio spectral indices (RSIs) are in the range of 800–900 nm, 1900–1950 nm, and 2200–2300 nm, while the sensitive areas of the difference spectral index (DI) and Normalized difference spectral index (NDSI) are in the range of 1900–1950 nm and 2200–2300 nm. The combination of SCI and characteristic bands significantly improves the prediction accuracy of soil TN estimation models. The independent and comprehensive estimation models for each fertilization period based on the BP (back propagation) neural network optimized by the Mind Evolution Algorithm (MEA-BPNN) can achieve a more stable and accurate estimation of soil TN. Finally, using soil spectral characteristic bands selected through continuum removal (CR) transformation and SMLR, combined with SCI, the model based on the MEA-BPNN (CR-SCI-MEA-BPNN) has the best prediction performance. The modeling determination coefficients R2 for each fertilization period reached 0.94, 0.95, 0.92, and 0.94, respectively, with RMSE of 0.0032, 0.0024, 0.0035, and 0.0027. The R2 and RMSE of the modeling and validation set of the entire fertilization period comprehensive model are 0.899, 0.0038, and 0.89, 0.0041, respectively. The results of this article provide technical support for promoting the timely monitoring of soil TN content and guiding rational fertilization in apple orchards.

Analysis of Spectral Characteristics of Cotton Leaves at Bud Stage under Different Nitrogen Application Rates

Soil salinity affects nutrient uptake by cotton. The cotton bud stage is a very important period in the process of cotton planting and directly affects the yield of cotton. The nutritional status of the bud stage directly affects the reflectance spectra of cotton canopy leaves. Therefore, it is of great significance to nondestructively monitor the nutritional status of the cotton bud stage on salinized soil via spectroscopic techniques and perform corresponding management measures to improve cotton yield. In this study, potted plants with different nitrogen application rates were set up to obtain the reflection spectral curves of cotton bud stage leaves, analyze their spectral characteristics under different nitrogen application rates, and establish spectral estimation models of chlorophyll density. The results are as follows: in the continuum removal spectrum of the cotton bud stage, the lowest point of the absorption valley near 500 nm shifted to the shortwave direction with an increasing nitrogen application rate. The mean reflectance between 765 and 880 nm was significantly different between nitrogen-stressed and nitrogen-unstressed cotton. The average reflectance of the near-infrared band, the absorption valley depths near 500 nm and 675 nm, the first derivative of the 710 nm reflectance, and the second derivatives of the 690 nm and 730 nm reflectance increased with increasing nitrogen application and chlorophyll density, and significant correlations were observed with the chlorophyll density. These parameters were modeled using support vector regression (SVR) and artificial neural network (ANN) methods, two commonly used algorithms in the field of machine learning. The determination coefficients of the three chlorophyll samples via the ANN models were 0.92, 0.77, and 0.94 for the modeling set and 0.77, 0.69, and 0.77 for the verification set. The ratio of quartile to root-mean-square error (RPIQ) of the ANN model was greater than 2.2, and the ratio of the standard error of the measured value to the standard error of the predicted (SEL/SEP) was close to 1, indicating that the chlorophyll density estimation models built based on the ANN algorithm had robust prediction ability. Our model could accurately estimate the leaf chlorophyll density in the cotton bud stage.

Coupling normalized abundance with an improved continuum removal algorithm for quantitative inversion of carbonate minerals using hyperspectral data

Mapping or quantitatively estimating mineral content using remote sensing technology is an active way for monitoring minerals in large or inaccessible areas. Different spectral features of minerals, induced by their ionic composition, can be identified and related to mineral type or abundance. Based on the distinctive spectral absorption around 2.33 µm induced by the carbonate ion, we propose an improved continuum removal (ICR) algorithm, coupled with normalized abundance, to assess the relationship between continuum removal band depth (CRBD) and carbonate ion abundance. Through experiments using synthetic and real image data, ICR with ratio abundance normalization enhances the linear relationship between CRBD and abundance, resulting in the best performance for abundance retrieval. The synthetic data showed the lowest root mean square error of 0.04, while the lowest mean relative error for real image data reached 6.80 %. Compared it with five other algorithms, coupling normalized carbonate mineral abundance with ICR improves the accuracy of quantitative retrieval of carbonate ion. These results demonstrate that the proposed approach effectively reduces the influence of reflectance differences caused by external factors, providing a more reasonable algorithm to enhance spectral absorb features and quantitatively retrieve mineral abundance. The proposed approach has the potential to extend mineral information extraction even in the absence of sample data, and can be applied in surveys of the Moon and Mars for mineral quantitative analysis.

Methodology for Regional Soil Organic Matter Prediction with Spectroscopy: Optimal Sample Grouping, Input Variables, and Prediction Model

Soil organic matter (SOM) is an essential component of soil and is crucial for increasing agricultural production and soil fertility. The combination of hyperspectral remote sensing and deep learning can be used to predict the SOM content efficiently, rapidly, and cost-effectively on various scales. However, determining the optimal groups, inputs, and models for reducing the spatial heterogeneity of soil nutrients in large regions and to improve the accuracy of SOM prediction remains a challenge. Hyperspectral reflectance data from 1477 surface soil samples in Northeast China were utilized to evaluate three grouping methods (no groups (NG), traditional grouping (TG), and spectral grouping (SG)) and four inputs (raw reflectance (RR), continuum removal (CR), fractional-order differentiation (FOD), and spectral characteristic parameters (SCPs)). The SOM prediction accuracies of random forest (RF), convolutional neural network (CNN), and long short-term memory (LSTM) models were assessed. The results were as follows: (1) The highest accuracy was achieved using SG, SCPs, and the LSTM model, with a coefficient of determination (R2) of 0.82 and a root mean squared error (RMSE) of 0.69%. (2) The LSTM model exhibited the highest accuracy in SOM prediction (R2 = 0.82, RMSE = 0.89%), followed by the CNN model (R2 = 0.72, RMSE = 0.85%) and the RF model (R2 = 0.69, RMSE = 0.91%). (3) The SG provided higher SOM prediction accuracy than TG and NG. (4) The SCP-based prediction results were significantly better than those of the other inputs. The R2 of the SCP-based model was 0.27 higher and the RMSE was 0.40% lower than that of the RR-based model with NG. In addition, the LSTM model had higher prediction errors at low (0–2%) and high (8–10%) SOM contents, whereas the error was minimal at intermediate SOM contents (2–8%). The study results provide guidance for selecting grouping methods and approaches to improve the prediction accuracy of the SOM content and reduce the spatial heterogeneity of the SOM content in large regions.

New data-driven estimation of metal element in rocks using a hyperspectral data and geochemical data

The inversion of Cu contents in rocks based on hyperspectral remote sensing is indicative of geochemical exploration as well as mineral resource exploration. Due to the strong redundancy of band information in hyperspectral data, characteristic band selection is the key to improving the accuracy of metal element inversion models in hyperspectral data. In this study, we proposed a framework that innovatively focuses on secondary screening method (SSM) as the core, allowing users to add different data preprocessing methods and machine learning algorithms to the framework based on expert experience, to obtain high-precision metal element inversion models suitable for sampling data. we first preprocessed the measured spectral curves using the first order derivative, second order derivative, continuum removal, multiple scattering correction and variance analysis to highlight band absorption characteristics. In addition, we performed SSM to obtain Cu-related characteristic bands, which were further used as input data to train and compare the performance of Partial Least Square Regression (PLSR), Support Vector Regression (SVR), Multi-Layer Perceptron (MLP), Random Forest (RF) and Gradient Boosting Regression Tree (GBRT). The results show that both the spectral pretreatment and modeling method could potentially impact the inversion accuracy. The accuracy of the ensemble method applied in fresh faces data (i.e., a CR-SSM-RF with R2 values of 0.77 and CR-SSM-GBRT with R2 values of 0.81) performed better than other models with an accuracy improvement of up to 80%. Compared to the full band model, the accuracy of characteristic bands selection model increased 50%. This also illustrates that the CR-SSM-RF or CR-SSM-GBRT model significantly improves the accuracy of the inversion of Cu contents in rocks compared to the original spectral reflectance. Our study provides a new idea for selecting different spectral preprocessing methods as the input values for the future model and will also offer an executable framework for the inversion of Cu contents in rocks of different lithology on a large scale in the future.

Inversion of soil properties with hyperspectral reflectance in construction areas of high-standard farmland

ABSTRACT High-standard farmland construction is an important process that can enhance food security and accelerate new-style modernization agriculture. Hyperspectral remote sensing can provide data and technical support for this type of construction to provide a reference when optimizing high-standard farmland construction areas. This study was performed in Xinzheng City, the primary grain-producing areas in Henan Province. Field sampling and indoor hyperspectral spectroscopy (350~2500 nm) were combined; spectral transformations such as continuum removal (CR) were performed after Savitzky‒Golay (SG) convolution smoothing; and the best hyperspectral bands were selected as the common index of the soil properties by correlation analysis and fuzzy clustering maximum tree. A hyperspectral inversion model was built for the panel data model of the fixed effect variable coefficient based on the ordinary least squares estimation method (OLS), including panel data describing pH, organic matter, nitrogen, phosphorus, potassium, iron, chromium, cadmium, zinc, copper, and lead of 116 samples in Xinzheng City. Results show that the panel data model is of good quality overall, and the goodness of fit is higher ( R 2 = 0.9991, F = 2195.67). The precision test results indicate that the models performed well at both description and prediction, including accurate quantification, with an RPD above 2.5. Thus, the proposed model provides an important basis for soil information management, resource evaluation, and a reference when optimizing high-standard farmland construction processes.

Integration of Vis–NIR Spectroscopy and Machine Learning Techniques to Predict Eight Soil Parameters in Alpine Regions

Visible and near-infrared spectroscopy (Vis–NIR, 350–1100 nm) has great potential for predicting soil properties. However, current research on the hyperspectral prediction of soil parameters in agricultural areas of alpine regions and the types of parameters included is limited, and optimal spectral treatments and predictive models applicable to different parameters have not been sufficiently investigated. Therefore, we evaluated the accuracy of predicting total nitrogen (TN), phosphorus pentoxide (TP2O5), total potassium oxide (TK2O), alkali-hydrolyzable nitrogen (AHN), effective phosphorus (AP), effective potassium (AK), soil organic matter (SOM), and pH in the Qinghai–Tibet Plateau using the Vis–NIR technique in combination with spectral transformations, correlation analysis, feature selection, and machine learning. The results show that spectral transformations improve the correlation between spectra and parameters but are dependent on the parameter type and the method used. Continuum removal (CR), logarithmic first-order differential (FDL), and inverse first-order differential (FDR) had the most significant effects. The feature bands were extracted using the SPA and modeled using partial least squares (PLSR), random forest (RF), support vector machine (SVM), extreme gradient boosting (XGBoost), and backpropagation neural networks (BPNNs). The accuracy was evaluated based on R2, RMSE, RPD, and RPIQ. We found that the PLSR model only enables the prediction of SOM and pH with lower accuracy than the remaining models. XGBoost can predict all of the parameters but only for AHN; the prediction performance is better than other methods (R2 = 0.776, RMSE = 0.043 g/kg, and RPIQ = 2.88). The RF, SVM, and BPNN models cannot predict AK, AP, and AHN, respectively. In addition, TP2O5, AP, and pH are best suited for modeling using RF (RPIQ = 2.776, 3.011, and 3.198); TN, AK, and SOM are best suited for modeling using BPNN (RPIQ = 2.851, 2.394, and 3.085); and AHN and TK2O are best suited for XGBoost and SVM, respectively (RPIQ = 2.880 and 3.217). Therefore, this study can provide technical and data support for the accurate and efficient acquisition of soil parameters in alpine agriculture.

Estimation of the distribution patterns of heavy metal in soil from airborne hyperspectral imagery based on spectral absorption characteristics

Though soil is widely known as one of the most valuable resources for the world, its quality is going to be lower because of unsustainable economic development and social progress. Therefore, it is important for us to monitor and evaluate the quality of soil, especially its heavy metal contents which is too scarce to identify in soil spectra easily but poisonous enough to affect human health in a long run. Most of the existing estimation methods have based the characteristic bands on statistical analysis to a large extent, which is hard to accurately explain the retrieval mechanism. In this paper, the absorption characteristics of heavy metal are studied based on the soil spectra, and the distribution pattern is mapped in a large-scale continuous space, for environmental monitoring and further decision support. Taking Yitong County, China as the study area. After spectra continuum removal, the heavy metal contents were estimated by 11 features including the absorption depth, absorption area, and band ratio around 2200 nm, which showed the best performance. For arsenic (As), the best model yields Rp2 value of 0.8474, and the RMSEP value is 36.1542 (mg/kg). It is concluded that As is adsorbed by organic matter, clay minerals, and iron/manganese oxides in soil, and the adsorption of As by first two components is greater than that of the last. For airborne spectra after continuum removal, combining the spectral absorption characteristic parameters and the highly correlated bands is more accurate than using the spectral absorption characteristic parameters or bands alone. AdaBoost is presented for the heavy metal estimation, and the fitting ability of the method is found to be stronger than that of the traditional classical methods, with the Rp2 values of 0.6242 and the RMSEP value of 43.6481 (mg/kg). In summary, these results will provide a prospective basis for the rapid estimation of soil heavy metals, the risk assessment of soil heavy metals and soil environmental monitoring in a large scale.

Estimation of leaf nitrogen content in winter wheat based on continuum removal and discrete wavelet transform

ABSTRACT Accurate and rapid estimation of leaf nitrogen content (LNC) in winter wheat using hyperspectral techniques is important for growth monitoring and accurate fertilization. Based on field experiments conducted over four years at three ecological sites with four different nitrogen (N) application treatments and four different N-efficient wheat varieties in Henan Province, the canopy spectra and LNC of winter wheat were obtained simultaneously in the main growth stages. The original spectrum was subjected to continuum removal (CR), the correlation between LNC and various vegetation indices was systematically analysed, and the optimal vegetation index estimation model for LNC was constructed. Simultaneously, discrete wavelet transform (DWT) was used to further compress and extract the CR spectrum. The model was combined with partial least squares regression (PLSR) and K-nearest neighbour (KNN) algorithms to estimate LNC in winter wheat. The results showed that the spectrum treated with CR was significantly improved in its correlation with LNC and that the model established based on normalized vegetation index NDVI (CR728, CR977) combined with the CR spectrum was better compared to existing vegetation indices. The calibration and validation coefficients of determination (R2) and root mean square error (RMSE) were 0.816 and 0.799, and 0.352% and 0.342%, respectively. DWT was used to transform the CR spectrum, and the results showed that a combination of the CR spectrum and a sym8 wavelet function with PLSR based on the approximation coefficients at decomposition level 2 predicted LNC most accurately. The coefficient of determination RC 2, root mean square error RMSEC, and relative percent deviation (RPDC) of the calibration set were 0.884, 0.279%, and 2.932, respectively, and RV 2, RMSEV, and RPDV of the validation set were 0.855, 0.291%, and 2.619, respectively, indicating that the model had good stability and predictive ability. Combination of CR and DWT improved the modelling accuracy of wheat LNC and showed better prediction results for multi-year and multi-point samples. The results of the study can provide a basis and reference for rapid monitoring of LNC in winter wheat.

Estimation of the Multielement Content in Rocks Based on a Combination of Visible–Near-Infrared Reflectance Spectroscopy and Band Index Analysis

Rock geochemical methods are effective for geological surveys, but typical sampling and laboratory-based analytical methods are time-consuming and costly. However, using visible–near-infrared spectroscopy to estimate the metal element content of rock is an alternative method. This study discussed the potential of hyperspectral estimation of Cu and its significant associated elemental content. Ninety-five rock samples were collected from the Kalatage Yudai copper–nickel deposit in Hami, Xinjiang. The effects of different spectral resolutions, spectral preprocessing, band indices, and characteristic band selection on the estimation of the element contents of Fe, Cu, Co, and Ti were investigated. The results show that when the spectral resolution is 5 nm, good results are obtained for all four metal elements, Fe, Cu, Co, and Ti, with the coefficients of determination R2 reaching 0.54, 0.59, 0.41, and 0.78, respectively. The best results are obtained for all transformed spectra with continuum removal, inverse transformation, continuum removal, and logarithmic transformation, respectively. In addition, the accuracy of the estimation models constructed by combining band indices and feature band selection was superior compared with full-band spectra for Fe (R2 = 0.654, MAE = 1.27%, and RPD = 1.498), Cu (R2 = 0.694, MAE = 20.509, and RPD = 1.711), Co (R2 = 0.805, MAE = 2.573, and RPD = 2.199), and Ti (R2 = 0.501, MAE = 0.04%, and RPD = 1.412). The results indicate that using band indices can provide a more accurate estimation of metal element content, providing a new technical method for the efficient acquisition of regional mineralization indicator element content distribution.