Distribution and Influencing Factors of Metals in Surface Soil from the Yellow River Delta, China

Remote sensing inversion on heavy metal content in salinized soil of Yellow River Delta based on Random Forest Regression-a case study of Gudao Town

To explore the potential of using the mineral alteration information extracted by remote sensing technology to indirectly estimate the heavy metal content of salinized soil, 23 sampling points were uniformly set up in the town of Gudao in the Yellow River Delta as the research area in 2022. The concentrations of seven heavy metals, Cr, Cu, Pb, Zn, As, Mn and Ni, at the sampling points were determined in laboratory tests. Spectral derivative indices, topographic factors, and mineral alteration information (iron staining, hydroxyl, and carbonate ions) were extracted and screened as modeling factors using Sentinel 2 imagery. An inverse model of heavy metal content was constructed using the random forest algorithm, and the model accuracy was evaluated using the cross-validation method. The results of the study show that: (1) Hydroxyl and carbonate ion alteration can be effectively used for the inversion of soil As and Ni content in this study area. Iron-stained alteration can be used as a modeling factor in the inversion of Cr, Cu, Pb, Zn, and Mn concentrations. (2) The inclusion of alteration information improves the accuracy of heavy metal content inversion. The Cu concentration was verified to be the best predictor, with an RMSE of 3.309, MAPE of 11.072%, and R2 of 0.904, followed by As, Ni, and Zn; the predictive value of Mn, Cr and Pb was average. (3) Based on the results of concentration inversion, the high concentration areas of As, Ni, and Mn are primarily distributed on both sides of the river and around lakes and ponds. The high-concentration areas of Zn were mainly distributed in the farmland areas on both sides of the river. Areas with high concentrations of Cu were mainly distributed in the eastern oil extraction area, both sides of the rivers, and around lakes.

Mercury and other trace elements distribution and profiling of microbial community in the surface sediments of East Siberian Sea

In this study, total mercury (THg), methylmercury (MeHg), various trace elements, and microbial communities were measured in surface sediments of the East Siberian Sea (ESS). The results showed that the average values of THg and MeHg were 58.8 ± 15.21 μg/kg and 0.50 ± 0.22 μg/kg, respectively. The notable levels of trace elements present in both surface sediment and porewater were Al, Fe, and Mn. The enrichment factor and geoaccumulation index analyses found that both natural phenomena and anthropogenic activities contributed to elevated concentrations of metals in the ESS. The redox proxy metals, pH, and SO₄^2- were the major factors influencing the THg and MeHg distributions. Microbial profiles were substantially affected by metals and other abiotic factors. Proteobacteria and Thaumarchaeota were the most abundant phyla. Overall, the findings presented here facilitate the understanding of the current status of metal contamination, its influencing factors, and metal-microbiota-interactions in ESS.

Estimation of Heavy Metal Content in Soil Based on Machine Learning Models

Heavy metal pollution in soil is threatening the ecological environment and human health. However, field measurement of heavy metal content in soil entails significant costs. Therefore, this study explores the estimation method of soil heavy metals based on remote sensing images and machine learning. To accurately estimate the heavy metal content, we propose a hybrid artificial intelligence model integrating least absolute shrinkage and selection operator (LASSO), genetic algorithm (GA) and error back propagation neural network (BPNN), namely the LASSO-GA-BPNN model. Meanwhile, this study compares the accuracy of the LASSO-GA-BPNN model, SVR (Support Vector Regression), RF (Random Forest) and spatial interpolation methods with Huanghua city as an example. Furthermore, the study uses the LASSO-GA-BPNN model to estimate the content of eight heavy metals (including Ni, Pb, Cr, Hg, Cd, As, Cu, and Zn) in Huanghua and visualize the results in high resolution. In addition, we calculate the Nemerow index based on the estimation results. The results denote that, the simultaneous optimization of BPNN by LASSO and GA can greatly improve the estimation accuracy and generalization ability. The LASSO-GA-BPNN model is a more accurate model for the estimate heavy metal content in soil compared to SVR, RF and spatial interpolation. Moreover, the comprehensive pollution level in Huanghua is mainly low pollution. The overall spatial distribution law of each heavy metal content is very similar, and the local spatial distribution of each heavy metal is different. The results are of great significance for soil pollution estimation.