Spatio-Temporal Analysis of Heavy Metals in Arid Soils at the Catchment Scale Using Digital Soil Assessment and a Random Forest Model

Distribution characteristics and integrated ecological risks evaluation modelling of microplastics and heavy metals in geological high background soil

The microplastics (MPs), a novel pollutant, and heavy metals (HMs) significantly affect soil ecology. The study investigated HMs and MPs in Qianxi's high geological background soil, established a model for risk evaluation with MPs types and shapes, and proposed a two-dimensional comprehensive index model for MPs-HMs combined pollution and risk evaluation criterion. The results revealed a high soil Cd concentration, with a mean value of 0.38 mg·kg-1. Additionally, soils from soybean-wheat intercropping-potato-corn rotation (SWI-PCR) exhibited significantly higher concentrations of Hg, As, and Pb compared with those from soybean-wheat intercropping-corn rotation (SWI-CR). Moreover, the soil exhibited a high abundance of MPs (8667.66 ± 3864.26 items·kg-1), mainly characterized by PS and fiber. The mean of adjusted ecological risk index (ARI) for MPs in soil was 525.27, indicating a grade 3 risk. The two-dimensional combined index (TPI) was used to assess the ecological risk of MPs-HMs combined pollution, exhibiting an exceedance rate of 56 % with a mean of 445.07. The risk level of the combined pollution was graded as 6, indicating high risk. The microplastic risk evaluation model and the comprehensive evaluation method of combined pollution established in this study provide a reference for the future risk evaluation of multi-pollutant combined pollution.

Digital exploration of selected heavy metals using Random Forest and a set of environmental covariates at the watershed scale

The current study was established for predicting some selected heavy metals (HMs) including Zn, Mn, Fe, Co, Cr, Ni, and Cu, by applying random forest (RF) and a set of environmental covariates at watershed scale. The objectives were to find out the most effective combination of variables and controlling factors on the variability of HMs in a semiarid watershed in central Iran. One hundred locations were selected in the given watershed in the hypercube manner and soil samples from a surface 0-20 cm depth and concentration of HMs and some soil properties were measured in the laboratory. Three scenarios of input variables were defined for HMs prediction. The results revealed that the first scenario (remote sensing + topographic attributes) explained about 27-34% of the variability in HMs. Inclusion of a thematic map to the scenario I, improved the prediction accuracy for all HMs. Scenario III (remote sensing data+ topographic attributes + soil properties) was the most efficient scenario for prediction of HMs with R² values ranging from 0.32 for Cu to 0.42 for Fe. Similarly, the lowest nRMSE was found for all HMs in scenario III, ranging from 0.271 for Fe to 0.351 for Cu. Among the soil properties, clay content and magnetic susceptibility were the most important variables, and also some remote sensing data (Carbonate index, Soil adjusted vegetation index, Band2, and Band7) and topographic attributes (mainly control soil redistribution along the landscape) were the most efficient variables for estimating HMs. We concluded that the RF model with a combination of remote sensing data, topographic attributes, and assisting of thematic maps such as land use in the studied watershed could reliably predict HMs content.

Uncertainty assessment of spatiotemporal distribution and variation in regional soil heavy metals based on spatiotemporal sequential Gaussian simulation

Revealing the spatiotemporal (ST) distribution and changes in regional soil heavy metals is significant to soil pollution control and management. However, most of the ST analysis models in the existing studies ignore the uncertainty of ST changes in soil heavy metals, making their results unreliable. In this study, using soil Pb collected from 2016 to 2019 in a mining city in China as case data, an ST sequential Gaussian simulation (STSGS) is proposed to reveal the ST distribution and variation in heavy metals in regional soils and their uncertainties. Firstly, the ST variogram was analysed and fitted using a theoretical variogram model integrating the experimental variations at the ST scale. Secondly, 500 simulation realisations with random access path were generated by the ST Kriging method. Considering the obtained 500 simulation realisations, a series of ST analysis methods was proposed and employed to reveal the ST distribution and changes with uncertainty assessment of regional soil heavy metals. The main results are as follows. (1) For the whole study region, soil Pb content initially increased and then decreased from 2016 to 2019. The average probability of soil Pb exceeding 90 mg/kg was 0.121, 0.214, 0.312 and 0.291 in 2016, 2017, 2018 and 2019, respectively, whereas the average probability of always exceeding 90 mg/kg in the 4 years was only 0.032. (2) From 2016 to 2019, the area proportions of the increase and decrease of soil Pb content in the study area were 87.2% and 12.8%, respectively. However, according to the standardised statistic, only 0.161% and 8.72% of the total areas were determined to have a significant decrease and increase in soil Pb content from 2016 to 2019. (3) From 2016 to 2019, the areas with a greater than 0.6 probability of soil Pb concentration decreasing by more than 5 mg/kg and increasing by more than 20, 40 and 80 mg/kg accounted for 4.96%, 32.2%, 11.5% and only 1.91% of the total study region, respectively. The incremental high-probability areas were primarily those where Pb pollution was already serious. Finally, the advantages of the proposed STSGS method were summarised.

Assessment of macronutrients status using digital soil mapping techniques: a case study in Maru'ak area in Lorestan Province, Iran

The present study was conducted to compare generalized linear model (GLM), random forest (RF), and Cubist to produce available phosphorus (AP) and potassium (AK) maps and to identify the covariates that control mineral distribution in Lorestan Province, Iran. To this end, the locations for collecting 173 soil samples were determined through the conditioned Latin hypercube sampling (cLHS) method, at four different land-uses (orchards, paddy fields, agricultural, and abandoned fields). The performance of the models was assessed by coefficient of determination (R²), root-mean-square error (RMSE), and mean absolute error (MAE) indices. The results showed that the RF model fitted better than GLM and Cubist models and could explain 40 and 57% of AP and AK distribution, respectively. The R², RMSE, and MAE of the RF model were 0.4, 2.81, and 2.43 for predicting AP and equal to 0.57, 143.77, and 116.61 for predicting AK, respectively. The most important predictors selected by the RF model were valley depth and soil-adjusted vegetation index (SAVI) for AP and AK, respectively. The maps showed higher AP and AK content in apricot orchards compared to other land-uses. No difference was observed between AP and AK content on paddy fields, agricultural, and abandoned areas. The higher AP and AK contents were related to orchard management practices, such as failure to dispose of plant residuals and fertilizer consumption. It can be concluded that the orchards (by increasing soil quality) was the best land-use in line with sustainable management for the study area. However, generalizing the results needs more detailed research.

Spatiotemporal patterns of soil heavy metal pollution risk and driving forces of increment in a typical industrialized region in central China

Excessive enrichment of soil heavy metals seriously damages human health and soil environment. Exploring the spatiotemporal patterns and detecting the influencing factors are conducive to developing targeted risk management and control. Based on the soil samples of Co, Cr, Cu, Mn, Ni, Pb, Zn, and Cd collected in one typical industrialized region in China from 2016 to 2019, this study analyzed the spatiotemporal pattern of geo-accumulation risk and potential ecological risk based on the spatiotemporal ordinary kriging (STOK) prediction, and probed the driving forces of heavy metal increments with the random forest (RF) regression model. The risk assessment revealed that soils were seriously contaminated by Pb, Cd, and Cu, moderately contaminated by Zn and Mn, and uncontaminated by Co, Cr, and Ni; more than 30% of areas had moderate to high potential ecological risks. From 2016 to 2019, soil heavy metal contents increased in more than 50% of regions and the growth rates of accumulations were ranked as Co (65%) > Ni (56%) > Mn (43%) > Pb (40%) > Cr (36%) > Zn (31%) > Cu (23%) > Cd (3%). High contents and increases of heavy metals in soils near industrial lands are higher. Smelter (24%), mine (20%), and factory (12%) were the major contributing factors for these heavy metal increments, followed by transportation (6%) and population (5%). The results indicated that the management of industrial discharge and contaminated soils should be strengthened to prevent the worsening soil heavy metal pollution in the study area.

Pollution Risk Prediction for Cadmium in Soil from an Abandoned Mine Based on Random Forest Model

It is highly uncertain as to the potential risk of toxic metal(loid)s in abandoned mine soil. In this study, random forest was used to predict the risk of cadmium pollution in the soils of an abandoned lead/zinc mine. The results showed that the random forest model is stable and precise for the pollution risk prediction of toxic metal(loid)s. The mean of Cd, Cu, Tl, Zn, and Pb was 6.02, 1.30, 1.18, 2.03, and 2.08 times higher than the soil background values of China, respectively, and their coefficients of variation were above 30%. As a case study, cadmium in the mine soil had "slope" hazard characteristics while the ore sorting area was the major source area of cadmium. The theoretical values of the random forest model are similar to the practical values for the ore sorting area, metallogenic belt, riparian zone, smelting area, hazardous waste landfill, and mining area. The potential risk of soil Cd in the ore sorting area, metallogenic belt, and riparian zone are extremely high. The tendency of pollution risk migrates significantly both from the ore sorting area to the smelting area and the mining area, and to the hazardous waste landfill. The correlation of soil pollution risk is significant between the mining area, the smelting area, and the riparian zone. The results suggested that the random forest model can effectively evaluate and predict the potential risk of the spatial heterogeneity of toxic metal(loid)s in abandoned mine soils.

Investigation of health and ecological risk attributed to the soil heavy metals in Iran: Systematic review and meta-analysis

The presence of heavy metals (HMs) in the soil can pose risks to human health via ingestion and dermal absorption. This systematic review and meta-analysis study focused on both of health and ecological risks attributed to the six HMs (As, Cd, Cr, Cu, Pb, Zn) in the soil of different Provinces of Iran. Articles were selected in the Web of Science and Scopus from 2000 to August 2021. The study was carried out according to Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guideline. Based on the inclusion and exclusion criteria, finally 32 studies were reviewed which the ranking of mean concentrations of the studied metals followed as: As > Zn > Cr > Pb > Cu > Cd. Mean concentration of Cd and As calculated via meta-analysis in the studied Provinces was found to be more than Iran's environment protection agency (EPA) guideline values. Other HMs met guideline values. A significant non-carcinogenic risk attributed to the As found in Kurdistan Province (hazard index, HI > 1). Furthermore, a significant carcinogenic health risk was found in Kurdistan and West Azerbaijan associated to As and in Fars, Khozestan and Khorasan-e-Razavi Provinces associated to Cd (ELCR >10^-4). Concerning the impact on the ecosystem, Cd, As and Pb caused ecological risks in some areas of Iran (ecological risk, ER > 40 and potential ecological risk, PER >150). Hence, we can conclude that Cd and As are important heavy metals from the health aspect. Moreover, Cd, As and Pb must be considered from an ecological point of view. Therefore, control of the Cd, As and Pb release in the environment and remediation of polluted sites through novel approaches is recommended.

Tracking the origin of trace metals in a watershed by identifying fingerprints of soils, landscape and river sediments

The identification of the spatial distribution of soil trace-elements and the contribution of different sources to the sediment yield is necessary for a better watershed and river water quality management. Until now, less attention has been paid to comprehensive assessments of sediment sources and soil trace-elements with respect to the suspended sediment production. The present study aimed at modelling the spatial distribution of soil trace-elements, quantifying the sediment sources apportionment and relating the landforms to polluted soils. Different techniques and approaches such as the Nemerow pollution index, machine learning algorithms (Random Forest (RF), generalised boosting methods (GBM), generalised linear models (GLM) and sediment fingerprinting were applied to the Kan watershed. A total of 79 soil samples having different Nemerow index values were considered for spatial modelling. Using statistical methods (Range test, Kruskal-Wallis and discrimination function analysis), an optimal set of tracers was selected. An unmixing model was applied to calculate the relative contribution of landforms for eight rainfall events. The results of the soil trace-element mapping showed that RF had the best performance with an accuracy of 83%. The evaluation of polluted soil areas showed that the landforms 'steep hills' and 'valley' contributed the most with 51% and 27% in the riparian zone, respectively. In addition, these landforms give a high contribution to sediment production in late-winter-spring events (29%) with a GOF (goodness of fit) of 0.65. The landform 'plain' had the highest contribution (28%) in sediment yield with a GOF of 0.72 in early-winter events. This means that the valley and steep hill landforms accelerate the transport of trace-elements across the watershed. Interestingly, the contribution of landforms varies during the year. Overall, the new proposed approach enables to better trace the origin of suspended sediments and trace-elements discharge into the river environment.

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.

Characteristics and Risk of Forest Soil Heavy Metal Pollution in Western Guangdong Province, China

West Guangdong is an important ecological barrier in Guangdong province, so understanding the spatial patterns and sources of heavy metal pollution of forest soil in this region is of great significance for ecological protection. In this study, the concentrations of heavy metals (Cd, Pb, Cu, Zn, and Ni) in forest soil were determined. Geostatistics, single-factor pollution index (PI), potential ecological risk index (RI), principal component analysis (PCA), and Pearson’s correlation analysis were used to evaluate and analyze the characteristics of heavy metal pollution of forest soil. The results showed that the average concentration did not exceed the critical value. Cd, Pb, and Cu were enriched in southwest Xinxing County, while Zn and Ni were enriched in most areas of the Yunan and Yuncheng districts. Two groups of heavy metals from different sources were identified by PCA and a correlation analysis. Cd, Pb, and Cu in their respective enrichment areas were mainly from marble and cement production, whereas Zn and Ni were primarily from transportation and chemical fertilizer. Most of the study area was safe or slightly polluted while the heavy metal-enriched areas were moderately to severely polluted. The potential ecological risk was at a lower level in the study area but moderate in southwest Xinxing County. In summary, human factors impact the spatial patterns and ecological risks of heavy metals in forest soil. This study provides a scientific basis for forest soil pollution control and ecological protection.