Evaluation of the prediction effectiveness for geochemical mapping using machine learning methods: A case study from northern Guangdong Province in China.

This study compares seven machine learning models to investigate whether they improve the accuracy of geochemical mapping compared to ordinary kriging (OK). Arsenic is widely present in soil due to human activities and soil parent material, posing significant toxicity. Predicting the spatial distribution of elements in soil has become a current research hotspot. Lianzhou City in northern Guangdong Province, China, was chosen as the study area, collecting a total of 2908 surface soil samples from 0 to 20 cm depth. Seven machine learning models were chosen: Random Forest (RF), Support Vector Machine (SVM), Ridge Regression (Ridge), Gradient Boosting Decision Tree (GBDT), Artificial Neural Network (ANN), K-Nearest Neighbors (KNN), and Gaussian Process Regression (GPR). Exploring the advantages and disadvantages of machine learning and traditional geological statistical models in predicting the spatial distribution of heavy metal elements, this study also analyzes factors affecting the accuracy of element prediction. The two best-performing models in the original model, RF (R2 = 0.445) and GBDT (R2 = 0.414), did not outperform OK (R2 = 0.459) in terms of prediction accuracy. Ridge and GPR, the worst-performing methods, have R2 values of only 0.201 and 0.248, respectively. To improve the models' prediction accuracy, a spatial regionalized (SR) covariate index was added. Improvements varied among different methods, with RF and GBDT increasing their R2 values from 0.4 to 0.78 after enhancement. In contrast, the GPR model showed the least significant improvement, with its R2 value only reaching 0.25 in the improved method. This study concluded that choosing the right machine learning model and considering factors that influence prediction accuracy, such as regional variations, the number of sampling points, and their distribution, are crucial for ensuring the accuracy of predictions. This provides valuable insights for future research in this area.

Geochemical characteristics and health risks of heavy metals in agricultural soils and crops from a coal mining area in Anhui province, China.

Soil contamination by heavy metals (HMs) in mining areas is a major issue because of its significant impact on the environmental quality and physical health of residents. Mining of minerals used in energy production, particularly coal, has led to HMs entering the surrounding soil through geochemical pathways. In this study, a total of 166 surface soil and 100 wheat grain samples around the Guobei coal mine in southeast China were collected, and trace metal levels were determined via inductively coupled plasma mass spectrometry (ICP-MS). The average HMs (Ni, As, Cr, Cu, Pb, Cd, and Zn) concentrations were lower than the screening values in China (GB 15618-2018) but higher than the soil background values in the Huaibei Bozhou area of Anhui Province (except Zn), indicating HMs enrichment. Based on the geoaccumulation index (Igeo) and ecological risk index (IER), Cd pollution levels were low, while for the other metals the samples were pollution-free, and therefore no ecological risk warning was issued for the mining area. Both Cr and Pb had a higher noncarcinogenic health risks for adults and children. The lifetime carcinogenic risks (LCR) of Cr, Pb, and Cd were within acceptable levels. A positive matrix factorization (PMF) model identified two factors that could explain the HMs sources: factor 1 for Zn, Cd, and Pb, factor 2 for Ni, As, Cr, and Cu. Furthermore, HMs enrichment was observed in surface soil and the Carboniferous-Permian coal seams in the Guobei coal mine, which may suggest that coal mining is an important source for HMs enrichment in surface soil. Overall, this study provides a theoretical basis for undertaking the management and assessment of soil HMs pollution around a coal mine.