Abstract
According to historical information, more than 300 metal smelting enterprises have been in the southwest of Xiongan for 300 years; however, these polluting enterprises have been gradually closed with the increased intensity of environmental protection. In the paper, 264 soil samples were collected and analyzed in the range of 400 nm–2500 nm by the spectra vista corporation (SVC), and the spectral noise was smoothed by the Savitzky–Golay filter. In order to enhance the spectral differences and curve shapes, mathematical transformations, such as the standard normal variate (SNV), first-order differential (FD), second-order differential (SD), multiple scattering correction (MSC), and continuum removal (CR), were performed on the data, and the correlation between spectral transformation and contents of REEs was analyzed. Moreover, three machine learning models—partial least-squares (PLS), random forest (RF), back propagation neural network (BPNN)—were used to predict the contents of REEs. Experimental results prove that REEs are combined with spectral active substances, such as organic compounds, clay minerals, and iron oxide, and it is possible to determine the contents of REEs using the reflection spectrum. The R2 between the predicted values and measured contents reached 0.986 by using BPNN after FD transformation. More importantly, the predicted values basically agree with the actual situation for CASI/SASI airborne hyperspectral images, and this is an effective technique to obtain the contents of REEs in soil at the study area.
Highlights
Rare earth elements (REEs) comprise several metal elements such as lanthanum (La), yttrium (Y), promethium (Pm), and scandium (Sc), and they are characterized by unique magnetic and catalytic properties, along with other important physical and chemical properties [1]
The basic characteristics of the 264 samples are shown in Table 1, and the average contents of La, Ce, Nd, Sm, and Y in soil are 40.9, 76.0, 38.4, 6.19, and 27.5 mg/kg respectively, where Ce, Nd, and Sm are slightly lower than the average national contents and La and Y are higher than the average national contents
Soil samples were collected by a spectra vista corporation (SVC) spectrometer in the southwest of Xiongan to monitor the contents of REEs in the soil, spectral transformation was utilized to enhance the absorption characteristics of REEs, and machine learning models were used to conduct inversion modeling
Summary
Rare earth elements (REEs) comprise several metal elements such as lanthanum (La), yttrium (Y), promethium (Pm), and scandium (Sc), and they are characterized by unique magnetic and catalytic properties, along with other important physical and chemical properties [1]. Large-scale mining, and agriculture activities, increasing numbers of REEs are being spread to the natural environment. There is currently an increasing interest in the biological responses of plants to REEs, and most studies focus on the effects of REEs on crop plants, such as rice, soybean, and wheat. These studies have found that REEs are not essential for biological growth, but they induce a hormesis effect; that is, REEs are able to promote crop biomass production at low concentrations and inhibit crop growth at high concentrations [6,7]. Thermophosphate, single superphosphate, and NPK fertilizers in phosphate express the highest mass fractions of REEs, and the resultant increase of contents in soil causes harmful effects to the environment [12]. It is necessary to constantly monitor the contents of REEs and the corresponding change trend in soil that reduces adverse environmental consequences
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
