Further to quantification of content, can reflectance spectroscopy determine the speciation of cobalt and nickel on a mine waste dump surface?

Toxic elements released due to mining activities are of the most important environmental concerns, characterised not only by their concentration, but also by their distribution among different chemical species, known as speciation. These are conventionally determined using chemical analysis and sequential extraction, which are expensive and time-demanding. In this study, the possibility of using visible-near-infrared-shortwave infrared (VNIR-SWIR) reflectance spectroscopy was investigated as an alternative technique to quantify the contents of cobalt (Co) and nickel (Ni) in soil samples collected from Sarcheshmeh copper mine waste dump surface, in Iran. As a novel approach, the capability of VNIR-SWIR spectroscopy was also investigated in speciation of those elements. Three machine learning (ML) techniques (i.e., extreme gradient boosting (EGB), random forest (RF) and support vector regression (SVR)) were used to make relationships between soil spectral responses and Co and Ni contents of the samples. For all ML algorithms, the best prediction accuracies were obtained by the models developed on the first derivative (FD) spectra (for Co: RMSEp values of 7.82, 8.03 and 9.22 mg·kg-1, and for Ni: RMSEp values of 9.88, 10.32 and 11.02 mg·kg-1, using EGB, RF and SVR, respectively). Spatial variability maps of elements showed relatively similar patterns between observed and predicted values. Correlation and ML (EGB, RF, SVR)-based methods revealed that the most important wavelengths for Co and Ni prediction were those related to iron oxides/hydroxides and clay minerals, as two main soil properties responsible for controlling their speciation. This study demonstrated that the EGB technique was successful at indirect quantification and spatial variability mapping of Co and Ni on the mine waste dump surface. In addition, it provided an inspiration for implementation of the VNIR-SWIR reflectance spectroscopy as a potentially fast and cost-effective method for speciation studies of toxic elements, especially in heterogeneous soil environments.

Soil toxic elements determination using integration of Sentinel-2 and Landsat-8 images: Effect of fusion techniques on model performance.

Finding an appropriate satellite image as simultaneous as possible with the sampling time campaigns is challenging. Fusion can be considered as a method of integrating images and obtaining more pixels with higher spatial, spectral and temporal resolutions. This paper investigated the impact of Landsat 8-OLI and Sentinel-2A data fusion on prediction of several toxic elements at a mine waste dump. The 30 m spatial resolution Landsat 8-OLI bands were fused with the 10 m Sentinel-2A bands using various fusion techniques namely hue-saturation-value (HSV), Brovey, principal component analysis (PCA), Gram-Schmidt (GS), wavelet, and area-to-point regression kriging (ATPRK). ATPRK was the best method preserving both spectral and spatial features of Landsat 8-OLI and Sentinel-2A after fusion. Furthermore, the partial least squares regression (PLSR) model developed on genetic algorithm (GA)-selected laboratory visible-near infrared-shortwave infrared (VNIR-SWIR) spectra yielded more accurate prediction results compared to the PLSR model calibrated on the entire spectra. It was hence, applied to both individual sensors and their ATPRK-fused image. In case of the individual sensors, except for As, Sentinel-2A provided more robust prediction models than Landsat 8-OLI. However, the best performances were obtained using the fused images, highlighting the potential of data fusion to enhance the toxic elements' prediction models.

vis-NIR and XRF Data Fusion and Feature Selection to Estimate Potentially Toxic Elements in Soil.

Soil contamination by potentially toxic elements (PTEs) is intensifying under increasing industrialization. Thus, the ability to efficiently delineate contaminated sites is crucial. Visible-near infrared (vis-NIR: 350-2500 nm) and X-ray fluorescence (XRF: 0.02-41.08 keV) spectroscopic techniques have attracted tremendous attention for the assessment of PTEs. Recently, the application of fused vis-NIR and XRF spectroscopy, which is based on the complementary effect of data fusion, is also increasing. Moreover, different data manipulation methods, including feature selection approaches, affect the prediction performance. This study investigated the feasibility of using single and fused vis-NIR and XRF spectra while exploring feature selection algorithms for the assessment of key soil PTEs. The soil samples were collected from one of the most heavily polluted areas of the Czech Republic and scanned using laboratory vis-NIR and XRF spectrometers. Univariate filter (UF) and genetic algorithm (GA) were used to select the bands of greater importance for the PTE prediction. Support vector machine (SVM) was then used to train the models using the full-range and feature-selected spectra of single sensors and their fusion. It was found that XRF spectra alone (primarily GA-selected) performed better than single vis-NIR and fused spectral data for predictions of PTEs. Moreover, the prediction models that were derived from the fused data set (particularly the GA-selected) enhanced the models' accuracies as compared with the single vis-NIR spectra. In general, the results suggest that the GA-selected spectra obtained from the single XRF spectrometer (for As and Pb) and from the fusion of vis-NIR and XRF (for Pb) are promising for accurate quantitative estimation detection of the mentioned PTEs.

Modelling potentially toxic elements in forest soils with vis-NIR spectra and learning algorithms.

The surface organic horizons in forest soils have been affected by air and soil pollutants, including potentially toxic elements (PTEs). Monitoring of PTEs requires a large number of samples and adequate analysis. Visible-near infrared (vis-NIR: 350-2500 nm) spectroscopy provides an alternative method to conventional laboratory measurements, which are time-consuming and expensive. However, vis-NIR spectroscopy relies on an empirical calibration of the target attribute to the spectra. This study examined the capability of vis-NIR spectra coupled with machine learning (ML) techniques (partial least squares regression (PLSR), support vector machine regression (SVMR), and random forest (RF)) and a deep learning (DL) approach called fully connected neural network (FNN) to assess selected PTEs (Cr, Cu, Pb, Zn, and Al) in forest organic horizons. The dataset consists of 2160 samples from 1080 sites in the forests over all the Czech Republic. At each site, we collected two samples from the fragmented (F) and humus (H) organic layers. The content of all PTEs was higher in horizon H compared to F horizon. Our results indicate that the reflectance of samples tended to decrease with increased PTEs concentration. Cr was the most accurately predicted element, regardless of the algorithm used. SVMR provided the best results for assessing the H horizon (R2 = 0.88 and RMSE = 3.01 mg/kg for Cr). FNN produced the best predictions of Cr in the combined F + H layers (R2 = 0.89 and RMSE = 2.95 mg/kg) possibly due to the larger number of samples. In the F horizon, the PTEs were not predicted adequately. The study shows that PTEs in forest soils of the Czech Republic can be accurately estimated with vis-NIR spectra and ML approaches. Results hint in availability of a large sample size, FNN provides better results.

Estimation of potentially toxic elements contamination in anthropogenic soils on a brown coal mining dumpsite by reflectance spectroscopy: a case study.

In order to monitor Potentially Toxic Elements (PTEs) in anthropogenic soils on brown coal mining dumpsites, a large number of samples and cumbersome, time-consuming laboratory measurements are required. Due to its rapidity, convenience and accuracy, reflectance spectroscopy within the Visible-Near Infrared (Vis-NIR) region has been used to predict soil constituents. This study evaluated the suitability of Vis-NIR (350-2500 nm) reflectance spectroscopy for predicting PTEs concentration, using samples collected on large brown coal mining dumpsites in the Czech Republic. Partial Least Square Regression (PLSR) and Support Vector Machine Regression (SVMR) with cross-validation were used to relate PTEs data to the reflectance spectral data by applying different preprocessing strategies. According to the criteria of minimal Root Mean Square Error of Prediction of Cross Validation (RMSEPcv) and maximal coefficient of determination (R2cv) and Residual Prediction Deviation (RPD), the SVMR models with the first derivative pretreatment provided the most accurate prediction for As (R2cv) = 0.89, RMSEPcv = 1.89, RPD = 2.63). Less accurate, but acceptable prediction for screening purposes for Cd and Cu (0.66 ˂ R2cv) ˂ 0.81, RMSEPcv = 0.0.8 and 4.08 respectively, 2.0 ˂ RPD ˂ 2.5) were obtained. The PLSR model for predicting Mn (R2cv) = 0.44, RMSEPcv = 116.43, RPD = 1.45) presented an inadequate model. Overall, SVMR models for the Vis-NIR spectra could be used indirectly for an accurate assessment of PTEs' concentrations.

Visible, near-infrared, and mid-infrared spectroscopy applications for soil assessment with emphasis on soil organic matter content and quality: state-of-the-art and key issues.

Visible near-infrared (Vis-NIR) reflection spectroscopy and mid-infrared (mid-IR) reflection spectroscopy are cost- and time-effective and environmentally friendly techniques that could be alternatives to conventional soil analysis methods. Successful determination of spectrally active soil components, including soil organic matter (SOM), depends on the selection of suitable pretreatment and multivariate calibration techniques. The objective of the present review is to critically examine the suitability of Vis-NIR (350-2500 nm) and mid-IR (4000-400 cm(-1)) spectroscopy as a tool for SOM quantity and quality determination. Particular attention is paid to different pretreatment and calibration procedures and methods, and their ability to predict SOM content from Vis-NIR and mid-IR data is discussed. We then review the most recent research using spectroscopy in different calibration scales (local, regional, or global). Finally, accuracy and robustness, as well as uncertainty in Vis-NIR and mid-IR spectroscopy, are considered. We conclude that spectroscopy, especially the mid-IR technique in association with Savitzky-Golay smoothing and derivatization and the least squares support vector machine (LS-SVM) algorithm, can be useful in determining SOM quantity and quality. Future research conducted for the standardization of protocols and soil conditions will allow more accurate and reliable results on a global and international scale.