Search

The optimal selection of characteristic bands and retrieval models for the hyperspectral retrieval of soil heavy metal concentrations poses a significant challenge. Additionally, satellite-based hyperspectral retrieval encounters several issues, including atmospheric effects, limitations in temporal and radiometric resolution, and data acquisition, among others. Given this, the retrieval performance of the soil arsenic (As) concentration in Pingtan Island, the largest island in Fujian Province and the fifth largest in China, is currently unclear. This study aimed to elucidate this issue by identifying optimal characteristic bands from the full spectrum from both statistical and physical perspectives. We tested three linear models, namely Multiple Linear Regression (MLR), Partial Least Squares Regression (PLSR) and Geographically Weighted Regression (GWR), as well as three nonlinear machine learning models, including Back Propagation Neural Network (BP), Support Vector Machine Regression (SVR) and Random Forest Regression (RFR). We then retrieved soil arsenic content using ground-based soil full spectrum data on Pingtan Island. Our results indicate that the RFR model consistently outperformed all others when using both original and optimal characteristic bands. This superior performance suggests a complex, nonlinear relationship between soil arsenic concentration and spectral variables, influenced by diverse landscape factors. The GWR model, which considers spatial non-stationarity and heterogeneity, outperformed traditional models such as BP and SVR. This finding underscores the potential of incorporating spatial characteristics to enhance traditional machine learning models in geospatial studies. When evaluating retrieval model accuracy based on optimal characteristic bands, the RFR model maintained its top performance, and linear models (MLR, PLSR and GWR) showed notable improvement. Specifically, the GWR model achieved the highest r value for the validation data, indicating that selecting optimal characteristic bands based on high Pearson's correlation coefficients (e.g., abs(Pearson's correlation coefficient) ≥0.45) and high sensitivity to soil active materials successfully mitigates uncertainties linked to characteristic band selection solely based on Pearson's correlation coefficients. Consequently, two effective retrieval models were generated: the best-performing RFR model and the improved GWR model. Our study on Pingtan Island provides theoretical and technical support for monitoring and evaluating soil arsenic concentrations using satellite-based spectroscopy in densely populated, relatively independent island towns in China and worldwide. [ABSTRACT FROM AUTHOR]

The widespread occurrence of late Mesozoic volcanic rocks in SE China is associated with widespread mineralization. Most geologists have accepted the model of Pacific plate subduction beneath the eastern Asian continent, but there are still controversies, especially the initial timing of the tectonic transition. In order to understand the tectonic evolution of the palaeo-Pacific plate subduction, an integrated study of zircon U–Pb, Lu–Hf isotope compositions and whole-rock geochemistry was carried out for Mesozoic volcanic rocks in eastern Fujian Province. According to the field observations and zircon U–Pb ages, these volcanic rocks can be divided into three phases: an early stage of Late Jurassic volcanic rocks (Phase 1, 159–153 Ma), a late stage of Late Jurassic volcanic rocks (Phase 2, 152–146 Ma) and an early stage of Early Cretaceous volcanic rocks (Phase 3, 143–139 Ma). Overall, these volcanic rocks are composed of intermediate–acid pyroclastic rocks and lava, with high SiO2, Na2O, K2O and Al2O3 contents, belonging to the high-K calc-alkaline and peraluminous series, with enrichment in large ion lithophile and light rare earth elements but depletion in high-field-strength elements and heavy rare earth elements. However, the Phase 1 and 2 volcanic rocks contain different zircon Hf isotopic compositions and whole-rock geochemistry to the Phase 3 volcanic rocks, implying that they have a different petrogenesis. Our study combined with previous research shows that the decreasing zircon ϵHf(t) values of the Middle–Late Jurassic volcanic rocks indicate a decreasing mantle-derived material contribution. On the contrary, the majority of the Early Cretaceous volcanic rocks have variable ϵHf(t) values, requiring varied degrees of involvement of juvenile components in their origin. Thus, we consider that the Late Jurassic volcanic rocks were generated in a compressional tectonic environment during the early stage (> 146 Ma) of palaeo-Pacific subduction. In contrast, the Cretaceous volcanic rocks were formed in an extensional tectonic setting during a later stage (< 143 Ma) of subduction. [ABSTRACT FROM AUTHOR]