Prediction of the concentration of antimony in agricultural soil using data fusion, terrain attributes combined with regression kriging

Improving prediction of soil heavy metal(loid) concentration by developing a combined Co-kriging and geographically and temporally weighted regression (GTWR) model

The study of heavy metal(loid) (HM) contamination in soil using extensive data obtained from published literature is an economical and convenient method. However, the uneven distribution of these data in time and space limits their direct applicability. Therefore, based on the concentration data obtained from the published literature (2000-2020), we investigated the relationship between soil HM accumulation and various anthropogenic activities, developed a hybrid model to predict soil HM concentrations, and then evaluated their ecological risks. The results demonstrated that various anthropogenic activities were the main cause of soil HM accumulation using Geographically and temporally weighted regression (GTWR) model. The hybrid Co-kriging + GTWR model, which incorporates two of the most influential auxiliary variables, can improve the accuracy and reliability of predicting HM concentrations. The predicted concentrations of eight HMs all exceeded the background values for soil environment in China. The results of the ecological risk assessment revealed that five HMs accounted for more than 90% of the area at the "High risk" level (RQ ≥ 1), with the descending order of Ni (100%) = Cu (100%) > As (98.73%) > Zn (95.50%) > Pb (94.90%). This study provides a novel approach to environmental pollution research using the published data.

A three-dimensional sampling design based on the coefficient of variation method for soil environmental damage investigation

A traditional grid model for soil sampling may suffer from poor efficiency and low accuracy. With a nonferrous metal processing plant as the study area, a three-dimensional kriging interpolation model was built based on this plant's preliminary investigation data for arsenic (As), and a detailed survey sampling programme was proposed. The sampling density at the pollution interval of the surface soil was estimated by the coefficient of variation method, and the sampling depth was determined by the pollution interval of the vertical prediction results. The results showed that the encrypted soil sampling distribution optimisation method obtains greater pointing accuracy with fewer points. The sampling accuracy was 87.62% after optimising the depth of pointing. Moreover, this approach could save 66.13% of the sampling costs and 56.93% of the testing costs compared to a full deployment programme. This study provides a new and cost-effective method for predicting the extent of contamination exceedance at a site and provides valuable information to guide post-remediation strategies for contaminated sites.

Spatial distribution and source identification of potentially toxic elements in Yellow River Delta soils, China: An interpretable machine-learning approach

Identifying the driving factors and quantifying the sources of potentially toxic elements (PTEs) are essential for protecting the ecological environment of the Yellow River Delta. In this study, data from 201 surface soil samples and 16 environmental variables were collected, and the random forest (RF) and Shapley additive explanations (SHAP) methods were then combined to explore the key factors affecting soil PTEs. An innovative t-distributed random neighbor embedding-RF-SHAP model was then constructed, based on the absolute principal component score and multivariate linear regression model, to quantitatively determine PTE sources. Although average PTE concentrations did not exceed the risk control values, PTE distributions exhibited significant differences. It was found that sodium, soil organic matter, and phosphorus contents were the three most important factors affecting PTEs, and human activities and natural environmental factors both influence PTE contents by altering the soil properties. The proposed model successfully determined PTE sources in the soil, outperforming the original linear regression model with a significantly lower RMSE. Source analysis revealed that the parent material was the main contributor to soil PTEs, accounting for more than half of the total PTE content. Industrial and agricultural activities also contributed to an increase in soil PTEs, with average contributions of 19.91 % and 17.44 %, respectively. Unknown sources accounted for 10.83 % of the total PTE content. Thus, the proposed model provides innovative perspectives on source parsing. These findings provide valuable scientific insights for policymakers seeking to develop effective environmental protection measures and improve the quality of saline-alkali land in the Yellow River Delta.

A novel directional-oriented method for predicting shear wave velocity through empirical rock physics relationship using geostatistics analysis

This study attempts to design a novel direction-oriented approach for estimating shear wave velocity (VS) through geostatistical methods (GM) using density employing geophysical log data. The research area involves three hydrocarbon wells drilled in carbonate reservoirs that are comprised of oil and water. Firstly, VS was estimated using the four selected empirical rock physics relationships (ERR) in well A (target well), and then all results were evaluated by ten statistical benchmarks. All results show that the best ERR is Greenberg and Castagna, with R2 = 0.8104 and Correlation = 0.90, while Gardner's equation obtained the poorest results with R2 = 0.6766 and correlation = 0.82. Next, Gardner's method was improved through GM by employing Ordinary Kriging (OKr) in two directions in well A, and then Cross-Validation and Jack-knife methods (JKm and CVm, respectively) were used to assess OKr's performance and efficiency. Initially, CVm and JKm were employed to estimate Vs using the available density and its relationship with shear wave velocity, where the performance of CVm was better with R2 = 0.8865 and correlation = 0.94. In this step, some points from the original VS were used to train the data. Finally, Vs was estimated through JKm and using the relationship between the shear wave velocity of two wells near the target well, including wells B and C; however, in this step, the original shear wave velocity of the target well was completely ignored. Reading the results, JKm could show excellent performance with R2 = 0.8503 and Corr = 0.922. In contrast to previous studies that used only Correlation and R-squared (R2), this study further provides accurate results by employing a wide range of statistical benchmarks to investigate all results. In contrast to traditional empirical rock physics relationships, the developed direction-oriented technique demonstrated improved predicted accuracy and robustness in the investigated carbonate field. This work demonstrates that GM can effectively estimate Vs and has a significant potential to enhance VS estimation using density.