Heavy Metals In Topsoil Research Articles

Investigating the Spatial Patterns of Heavy Metals in Topsoil and Asthma in the Western Salt Lake Valley, Utah

Mining activities, particularly in large excavations like the Bingham Canyon Copper Mine in Utah, have been increasingly linked to respiratory conditions due to heavy-metal-enriched waste and dust. Operating continuously since 1906, the Bingham Canyon Copper Mine contributes 4.4% of the Salt Lake Valley PM2.5 pollution. However, the extent of its contributions to larger-sized particulate matter (PM10) dust, soil and water contamination, and human health impacts is largely unknown. Aerosol optical depth data from Sentinel-2 imagery revealed discernible dust clouds downwind of the mine and smelter on non-prevailing-wind days, suggesting potential heavy metal dispersion from this fugitive dust and subsequent deposition to nearby surface soils. Our analysis of topsoils from across the western Salt Lake Valley found mean arsenic, copper, lead, and zinc concentrations to be well above global background concentrations. Also, the minimum values for arsenic and maximum values for lead were well above the US EPA regional screening levels for residential soils. Thus, arsenic is the metal of greatest concern for impacts on human health. Elevated concentrations of all metals were most notable near the mine, smelter, and tailings pond. Our study linked these elevated heavy metal levels to regional asthma outcomes through cluster analysis and distance-related comparison tests. Significant clusters of high asthma rates were observed in regions with elevated topsoil heavy metal concentrations, impacting both low- and high-income neighborhoods. The findings of this preliminary study suggest that the mine, smelter, and recent construction activities, especially on lands reclaimed from former tailings ponds, could be contributing to atmospheric dust containing high levels of heavy metals and exacerbating asthma outcomes for residents. However, the methods used in the study with aggregated health outcome data cannot determine causal links between the heavy metal contents of soil and health outcomes; they can only point to potential links and a need for further investigation. Such further investigation should involve individual-level data and control for potential confounding factors, such as socioeconomic status, access to healthcare, and lifestyle factors, to isolate the effect of metal exposures on asthma outcomes. This study focused on atmospheric deposition as a source of heavy metal enrichment of topsoil. However, future research is also essential to assess levels of heavy metals in subsoil parent materials and local surface and groundwaters to be able to assess the links between the sources or methods of soil contamination and health outcomes.

Pollution of Heavy Metals in Topsoil of Remote Mountainous Areas in Western Yunnan-Guizhou Plateau

Heavy metals from anthropogenic emissions have had a negative impact on the ecological environment in remote regions. A total of 69 topsoil samples were collected from 13 remote mountainous areas in the western Yunnan-Guizhou Plateau at altitudes of 2 563-4 037 m, and the concentrations of ten heavy metals in the samples were determined. Enrichment characteristics and pollution sources of heavy metals in topsoil were discussed by referencing the enrichment factor （EF）, positive matrix factorization （PMF）, and Pb isotopes. The results showed that the average concentrations of Al, Fe, Cu, V, and Zn in the topsoil were lower than the soil background values in Yunnan Province； the average concentrations of Ni and Pb were similar to the background values； and the average concentrations of Cd, Cr, and Hg were 1.8-3.6 times higher than the background values. The average EF values of Pb, Cr, and Ni were 3.8, 3.4, and 2.3, respectively, showing moderate enrichment according to the EF classification criteria； the average EF values of Cd and Hg were 15.2 and 10.0, reflecting significant enrichment； and the average EF values of the other metals ranged from 1.1 to 1.9, displaying none-weak enrichment. Combining the comparisons of heavy metal concentrations and ratios in topsoil and bedrock and the EF and PMF results, Al, Fe, V, Cr, Cu, Ni, and Zn in topsoil were considered primarily from detrital sources, and the spatial concentration variations of the metals should have been mainly regulated by the parent material. Cadmium, Hg, and Pb were obviously polluted by anthropogenic emissions, and the main sources were non-ferrous metal smelting and coal combustion. The areas with relatively high Cd, Hg, and Pb pollution were mainly distributed in the Jiaozi snow mountain, Bitahai watershed, Luoji Mountain, and Laojun Mountain areas. Anthropogenic emissions contributed 23.8% of the accumulation of heavy metals in the topsoil.

Vertical distribution and migration of heavy metals in soil of green stormwater infrastructure receiving roof runoff

In order to achieve effective management of urban stormwater runoff, green stormwater infrastructure (GSI) has been widely used worldwide. However, the problem of heavy metal contamination in GSI soils has gradually become a limiting factor for their development. In this paper, concentrations of 6 heavy metals were detected in soils from 0 to 80 cm depth in the GSI receiving roof runoff. The total concentration of the 6 heavy metals in topsoil of the GSI was 395 mg·kg−1, which was significantly higher than that of the control site (p < 0.01). Vertically, heavy metal concentrations in GSI soils decreased with depth. The concentrations of As, Cr, Cu, Pb and Zn in the soils at different depths (0–80 cm) of GSI were higher than those in the soils at the corresponding depths at the control site. This suggests that heavy metals may have migrated below 80 cm. The decrease in Zn/Cu ratios with depth indicated that Zn has a higher initial concentration and more of Zn accumulated in upper layer soil than Cu. Finally, we simulated the vertical migration of dissolved heavy metals in GSI soils by the Hydrus-1D model. Heavy metal concentrations in runoff and soil particle size distributions were examined, while adsorption isotherm experiments were conducted to determine input parameters for the model. The simulation results showed that only dissolved Zn would accumulate in the top soil layer. A short time of infiltration (<60 min) may have little effect on the profile shape of dissolved heavy metal levels in the soil. Substantial increases in infiltration may result in the migration of dissolved heavy metals to deeper depths in the soil.

Effects of Organic Manure on Wheat Yield and Accumulation of Heavy Metals in a Soil—Wheat System

The application of organic manure is an effective way to develop sustainable agriculture. However, the application of organic manure may be associated with a potential risk of heavy metal pollution for soil and crops. In this study, the effects of organic cow manure (T1) (as base fertilizer), organic pig manure (T2) (as base fertilizer) and chemical fertilizer (T3) on winter wheat grain yields, grain quality, heavy metal concentrations and heavy metal bioconcentration factors (BCFs) in a soil–wheat system were studied from November 2021 to June 2023. The results showed that the winter wheat grain yields in the T1 and T2 treatments were lower than those in the T3 treatment by 2.57–38.0% and 10.5–25%, respectively. There were no significant differences in quality indexes of winter wheat grain among different fertilizer treatments. The concentrations of heavy metals in topsoil and winter wheat were 0.12–76.11 μg/g and 0.01–43.25 μg/g, respectively. The BCFs of heavy mental in the soil–wheat grain system was 0–2.92. In general, there were no significant differences in heavy metals’ concentrations in topsoil and wheat grain among different fertilizer treatments. In summary, compared with chemical fertilizer, the short-term application of organic manures had no significant effect on heavy metals concentrations in topsoil and wheat.

Pollution Characteristics and Source Apportionment of Heavy Metals in Topsoil of Counties Along the Shandong Section of the Yellow River

The 25 counties along the Shandong section of the Yellow River are the core areas for promoting the ecological protection and high-quality development of the Yellow River in Shandong Province. Moreover, it is of great significance to study the current situation, sources, and potential risks of heavy metal pollution in the topsoil in this region. In this study, 103 soil samples were collected from the 25 counties along the Shandong section of the Yellow River, and the contents of eight heavy metals （As, Cu, Pb, Cr, Zn, Ni, Cd, and Hg） were determined. The pollution characteristics of heavy metals were analyzed and evaluated using the geological accumulation index and potential ecological risk index. Correlation analysis and the positive matrix factorization （PMF） model were used to analyze the sources of heavy metals. The results showed that the average contents of Cu and Cr were lower than that of the background values of soils, whereas the average contents of As, Pb, Zn, Ni, Cd, and Hg were 1.16, 1.42, 1.05, 1.14, 2.29, and 1.85 times higher than that of the background values, respectively, and the average contents of all eight elements were lower than the screening value of soil pollution risk in agricultural land. In terms of different heavy metal variations, the coefficient of variation （CV） of Cu and Cd was higher than 0.500, indicating high variations, whereas As, Pb, Cr, Zn, Ni, and Hg showed moderate variation. Cd and Hg were slightly polluted, whereas the other six elements were not polluted. Cd and Hg had a moderate potential ecological risk level, whereas the other six elements were at a low level. Correlation analysis and PMF model showed that the sources of heavy metals in the study area were influenced by four factors, i.e., agricultural activities, natural sources, industrial emissions, and atmospheric dust from coal combustion and vehicle exhaust emissions, and the relative contribution rates were 32.4%, 34.9%, 16.5%, and 16.2%, respectively.

Accumulation Pattern and Potential Ecological Risk of Heavy Metals in Topsoil as Affected by Diverse Sources in Different Ecosystems in Western Dabie Mountain

Accumulation Pattern and Potential Ecological Risk of Heavy Metals in Topsoil as Affected by Diverse Sources in Different Ecosystems in Western Dabie Mountain

Human health and ecological risk assessment of heavy metals in topsoil of different peatland use types

Peatlands, known for their ability to retain and immobilize heavy metals due to unique waterlogged conditions and organic matter, face challenges when subjected to disturbances such as land use changes. These disruptions alter the organic matter, redox potential, and pH of the peatsoil, potentially influencing the migration, mobilization, and increased availability of stored heavy metals. Peatsoil samples from various peatland use types (improved and semi-natural grassland, forest, industrial cutaway bog) were collected to assess the human health and ecological risk associated with heavy metals (Cd, Cu, Hg, Pb, and Zn) in Co-Offaly, Ireland. Results reveal variations in heavy metal concentrations across peatland use types, with Cd, Hg, and Pb in improved and semi-natural grassland peatsoils exceeding the World Health Organization (WHO) permissible safety limits. Contamination factors (CF) were higher in improved grassland, especially for Cd and Pb, exceeding one. Hakanson potential ecological risk assessment indicates acceptable overall risk levels, though variations exist between improved grassland, unimproved grassland, forest, and industrial cutaway bog. Combined exposure routes (dermal, ingestion and inhalation routes) to all heavy metals do not exceed safe exposure levels (indicating low non-carcinogenic risks. However, the cancer risk (CR) exceeds acceptable thresholds across all use types, with higher CR in improved grassland, especially for children. Overall, the findings emphasize the need for careful consideration of heavy metal risks associated with land use changes in peatlands, particularly in the improved grassland areas.

The statistical analysis of training data representativeness for artificial neural networks: spatial distribution modelling of heavy metals in topsoil

The statistical analysis of training data representativeness for artificial neural networks: spatial distribution modelling of heavy metals in topsoil

Prevalence rates of neurodegenerative diseases versus human exposures to heavy metals across the United States

Novel means are needed to identify individuals and subpopulations susceptible to and afflicted by neurodegenerative diseases (NDDs). This study aimed to utilize geographic distribution of heavy metal sources and sinks to investigate a potential human health risk of developing NDDs. Known or hypothesized environmental factors driving disease prevalence of Alzheimer's Disease (AD), Parkinson's Disease (PD), and amyotrophic lateral sclerosis (ALS) are heavy metals, including arsenic (As), cadmium (Cd), manganese (Mn) and mercury (Hg). Lead (Pb) has been associated with AD and ALS. Analyzable mediums of human exposure to heavy metals (i.e., toxic metals and metalloids), or proxies thereof, include infant blood, topsoil, sewage sludge, and well water. U.S. concentrations of heavy metals in topsoil, sewage sludge, well water, and infant blood were mapped and compared to prevalence rates of major NDDs. Data from federal and state agencies (i.e., CDC, EPA, and the US Geological Survey) on heavy metal concentrations, age distribution, and NDD prevalence rates were geographically represented and statistically analyzed to quantify possible correlations. Aside from an expected significant association between NDD prevalence and age (p < 0.0001), we found significant associations between the prevalence of the sum of three major NDDs with: Pb in topsoil (p = 0.0433); Cd (p < 0.0001) and Pb (p < 0.0001) in sewage sludge; Pb in infant blood (p < 0.0001). Concentrations in sewage sludge of Cd and Pb were significantly correlated with NDD prevalence rates with an odds ratio of 2.91 (2.04, 4.225 95%CI) and 4.084 (3.14, 5.312 95%CI), respectively. The presence of toxic metals in the U.S. environment in multiple matrices, including sewage sludge, was found to be significantly associated with NDD prevalence. This is the first use of sewage sludge as an environmental proxy matrix to infer risk of developing NDDs.

Comprehensive Risk Assessment of Heavy Metals in Topsoil and Their Risks to Human Health and Ecosystem in Zanjan Mineral Province, Western Iran

Comprehensive Risk Assessment of Heavy Metals in Topsoil and Their Risks to Human Health and Ecosystem in Zanjan Mineral Province, Western Iran

Potential Source Identification and Ecological Risk Assessment of Heavy Metals in Surface Soil of Heze Oil Peony Planting Area Based on PMF-PCA/APCS and PERI

To study the sources and potential risks of heavy metals in soils of characteristic agricultural product producing areas is of great significance for the scientific management and safe utilization of soil and crop resources. The contents of heavy metals As, Cd, Cr, Cu, Hg, Ni, Pb, and Zn in the 254 surface soil samples collected from the Heze oil peony planting area were determined. The content characteristics and correlation of heavy metals were analyzed using multivariate statistical methods. The sources of heavy metals in topsoil were analyzed using Igeo, PMF, and PCA/APCS. The ecological risks of the eight heavy metals were assessed through the potential ecological risk index (PERI). The results showed that the average contents of seven heavy metals in the soil were basically consistent with the background values of soil elements in Heze City, except that the average value of Cd was 1.44 times higher than the background value in Heze City. Correlation analysis and cluster analysis revealed that Pb, Hg, and Cd elements in the soil were greatly affected by human activities in the later period. The sources of eight heavy metals in the study area were natural sources, agricultural fertilizer sources, industrial coal sources, and domestic transportation sources, with the contribution rates of 81.31%, 15.45%, 2.74%, and 0.50%, respectively; 84.25% of the sites in the study area were at slight ecological risk, whereas the moderate risk and strong risk sites accounted for 14.96% and 0.79%, respectively. Among them, Cd and Hg were the dominant elements of ecological risk in the study area.

Spatial distribution, sources and health risk assessment of heavy metals in topsoil around oil and natural gas drilling sites, Andhra Pradesh, India

Soils are usually the interface between human activity and environmental components that must be conserved and protected. As a result of rising industrialization and urbanization, activities such as exploration and extraction operations lead to the release of heavy metals into the environment. This study presents distribution of six heavy metals (As, Cr, Cu, Ni, Pb and Zn) in 139 top soil samples collected in and around oil and natural gas drilling sites at a sampling density of 1 site/12 km2. The results indicated the concentration ranged from 0.1 to 16 mg/kg for As, 3–707 mg/kg for Cr, 7–2324 mg/kg for Cu, 14–234 mg/kg for Ni, 9–1664 mg/kg for Pb, and 60–962 mg/kg for Zn. The contamination of soil was estimated on the basis of Index of geo accumulation (Igeo), enrichment factor (Ef), and contamination factor (Cf). Further, spatial distribution pattern maps indicated that the pollution levels for Cu, Cr, Zn, and Ni were higher around drilling sites of the study area relative to other regions. Using exposure factors for the local population and references from the USEPA’s integrated database, potential ecological risk indices (PERI) and health risk assessments were made. The hazard index (HI) values of Pb (in adults) and Cr, Pb (in children) exceeded the recommended limit of HI = 1, indicating the non-carcinogenic risks. Total carcinogenic risk (TCR) calculations revealed Cr (in adults) and As, Cr (in children) levels in soils exceeded the threshold value of 1.0E − 04, indicating significant carcinogenic risk due to high metal concentrations in the study area. These results may assist in determining the soil’s present state and its effect due to extraction strategies used during drilling process and initiate few remedial techniques, particularly for proper management strategies in farming activities to decrease point and non-point source of contamination.

Heavy Metal Concentration, Source, and Pollution Assessment in Topsoil of Chuzhou City

In order to understand the pollution level and ecological risk of heavy metals in topsoil of Chuzhou City, a total of 4360 soil samples in Chuzhou City were collected, and the concentrations of eight heavy metals including Cr, Zn, Pb, Cu, Ni, Cd, As, and Hg were measured. Correlation analysis, cluster analysis, and principal component analysis were used to analyze the sources of the heavy metals, and the enrichment factor index, single-factor pollution index, pollution load index, geo-accumulation index method, and potential ecological risk index were selected to assess the environmental risk of the eight heavy metals in the topsoil. The results showed that the average values of Cr, Zn, Pb, Cu, Ni, Cd, As, and Hg contents in the surface soil of Chuzhou City were higher than the background value of that in the soil of Yangtze-Huaihe River Basin of Anhui, and Cd, Ni, As, and Hg were significantly different in space and influenced by external disturbance. The eight types of heavy metals could be divided into four categories based on correlation analysis, cluster analysis, and principal component analysis. Cr, Zn, Cu, and Ni were from natural background sources; As and Hg mainly came from sources of industrial and agricultural pollution; Pb mainly came from the sources of transportation pollution and industrial and agricultural pollution; and Cd came from the sources of transportation pollution, natural background, and industrial and agricultural pollution. The overall pollution degree of Chuzhou City was low, and the ecological risk level was at a slight level based on the pollution load index and the potential ecological risk index; however, the ecological risk of Cd and Hg was generally serious, and these two heavy metals should be taken as the objects of priority control. The results provided a scientific basis for soil safety utilization and classification control in Chuzhou City.

Enrichment characteristics of potential risk elements in the black soil region of Northeast China

Heavy metals in topsoil mainly originate from the natural geological background and human activities, and once the soil is contaminated with heavy metals, it is difficult to restore it to its original natural state. Therefore, it is important to assess the level of influence of heavy metals in soil to provide information for agricultural production. To clarify the intensity of anthropogenic impact on the soil environment in the black soils region (BSR), we used the geochemical data of 0–20cm topsoil (anthropogenic impact depth) and 150–180cm subsoil(natural background) to analyze the topsoil heavy metal enrichment coefficient for cadmium, mercury, lead, arsenic, zinc, nickel, copper, chromium, and their spatial distribution characteristics in BSR . The analysis showed that the heavy metal enrichment coefficients of lead, arsenic, zinc, nickel, copper and chromium are basically less than 2.0 in BSR, and there are only localized points with enrichment coefficients of greater than 2.0. Cadmium and mercury are more obviously enriched in the black soils area, and the enrichment areas are mainly distributed south of Harbin. The mercury enrichment area is distributed in a north–eastward strip along Shenyang, Changchun, and Harbin, and the cadmium enrichment areas are mainly distributed south of Changchun, with a continuous distribution to Tieling City. the enrichment of heavy metals in the topsoil is closely related to the population density by comparing spatial distribution patterns of the geological background, topography and land use, and the obvious enrichment areas for heavy metals are located in and around cities, especially in industrial cities and their surrounding areas. The enrichment depth of 40 cm is further evidence that the heavy metals in topsoil mainly originate from human activities.

Geochemical Baseline of Heavy Metals in Topsoil on Local Scale and Its Application

Geochemical Baseline of Heavy Metals in Topsoil on Local Scale and Its Application

Analysis of the status and ecological risks of heavy metals contamination in artisanal and small-scale gold mine-spoils at the Atewa Forest Landscape, Ghana

The study analysed the contamination status and potential ecological risk of heavy metals (Fe, Cu, Mn, Zn, Pb, Cd, As and Hg) in soils from un-reclaimed illegal artisanal and small-scale gold mine (‘galamsey’) sites at the Atewa forest landscape. Composite soil samples (48) were collected from topsoil (0–20 cm) and subsoil (20–50 cm) across eight communities in four districts. Samples were analyzed using FAAS in the laboratory, and the results were evaluated using the geoaccumulation index (Igeo) and potential ecological risk index (PERI). The results based on the I geo values showed that the contamination status from the heavy metals in the topsoil and subsoil were: Hg>Cd>As>Pb>Mn>Cu>Zn>Fe and Hg>Cd>As>Pb>Cu>Mn>Zn>Fe respectively. These suggest strong Hg pollution in both topsoil (4.01) and subsoil (4.45), moderate Cd contamination in topsoil (1.04) and subsoil (1.48) and moderate As (0.54) contamination in subsoil only. The PERI from the heavy metals in both topsoil and subsoil were: Hg>Cd>As>Pb>Cu>Mn>Zn>Fe. Overall, Hg (PERI > 964) posed very severe ecological risk, with the greatest contribution to potential ecological toxicity; followed by Cd (PERI > 92) and As (PERI > 16) in the soils. Multivariate statistical analysis revealed that the elements Fe, Cu, Mn were consistently naturally occurring in the soil minerals while As, Pb and Hg were of anthropogenic origin, notably galamsey’ activities with Cd and Zn originating from both sources. This outcome highlights the need for prompt action towards the restoration of soil quality in the study area to protect human and ecological health and enhance post-mine forest restoration.

Spatial Distribution and Source Apportionment of Heavy Metals in the Topsoil of Weifang City, East China

The distribution of heavy metals in topsoil can have a significant impact on human health. A total of 1, 556 samples were collected from the topsoil of Weifang, China. Various indices, including the pollution index (PI), the Nemerow integrated pollution index (PN), and the potential ecological risk index (RI), were used to analyze the heavy metal pollution levels. The sources of heavy metals were analyzed using the positive matrix factorization (PMF) model. The results are as follows: (1) the ecological risk level of Cu, Pb, Zn, Ni, Cr, and As in the study area is relatively safe, but the ecological risk level of Cd and Hg is relatively high, leading to an increase in the ecological risk level of heavy metals in the study area and (2) the PMF results show that there are six main sources of the eight heavy metals. Cr and Ni come from soil parent material and nonferrous metal industrial activities; As is closely related to fossil fuel (coal)-related industrial activities; Cu originated from diesel fuel-related transportation and agricultural machinery activities; Pb is derived from gasoline transportation activities; Hg is closely related to the application of pesticides in agricultural production; Cd and Zn originated from organic fertilizers used in agricultural activities.

Ecological and Probabilistic Health Risk Assessment of Heavy Metals in Topsoils, Southeast of Iran.

This study aimed to assess ecological and health risk of heavy metals (HMs) in the 35 topsoils in southeastern Iran. Ecological and health risks were assessed based on the EPA method. The order of the HMs followed as: Zn > Cr>Cu>Pb>As>Cd. All samples, except As and Cu, had the moderate enrichment and low to moderate pollution, respectively. The As in both regions and Cu in the city was classified in the lack to minimal enrichment and no pollution category. The studied HMs in both regions were shown a low ecological risk. There was minimal possibility of adverse non-carcinogenic effects. The Cr and As had an acceptable or tolerable carcinogenic risk from ingestion route (ELCRing) in both regions. According to the important role of As, Cd and Cr from the aspect of ecological and health risk, control of their sources must be considered to attenuate ecological and human adverse effets in the studied areas.

Meta-analysis of the Effects of Metal Mining on Soil Heavy Metal Concentrations in Southwest China

Metal mining is one of the main contributors of soil heavy metals. Previous studies examining the impact of metal mining on surrounding soil have mainly focused on one or a few metal mining areas. However, such studies cannot effectively inform the management of heavy metal pollution in soil at an inter-provincial scale. As part of this study, literature was collected on soil heavy metals (i.e., As, Cd, Cr, Cu, Hg, Ni, Pb, and Zn) affected by metal mining in regions of Southwest China (i.e., Yunnan Province, Sichuan Province, Guizhou Province, Chongqing Municipality, and Tibet Autonomous Region); Next, the impact of metal mining on the soil concentrations of these metals was quantified through meta-analysis, and the relationships between the selected factors (i.e., different sub-regions, metal minerals, and land-use types) and soil heavy metal concentrations were explored. Finally, the literature data was tested for publication bias. The results showed that metal mining in Southwest China has significantly increased the concentrations of heavy metals in topsoil. The different metals were ranked according to their weight effect sizes (ES+) in the following order Cd > Pb > Hg > Zn > As > Cu > Ni > Cr. Metal mining in both Sichuan and Yunnan led to higher effect sizes of soil Cd (ES+Sichuan=4.16, ES+Yunnan=3.20) and Pb (ES+Sichuan=3.47, ES+Yunnan=2.54) than those of the other heavy metals, while metal mining in Guizhou led to a higher effect size of soil Hg (ES+=2.80). The effect size of metal mining on soil heavy metals was higher in cultivated soil (ES+=1.42) than in forested soil (ES+=0.50). The mining of lead-zinc and tin significantly increased the concentrations of soil Cd, Pb, and Zn, and the mining of copper significantly increased the concentrations of soil Cu, Cd, and Pb. Of the investigated soil heavy metals in Southwest China, Pb and Zn showed slight potential publication biases (P<0.05). The above results can provide more effective information for the environmental protection of soil in metal mining areas of Southwest China.

The extraction of the training subset for the spatial distribution modelling of the heavy metals in topsoil

The choice of the method of raw data dividing into train and test subsets in the models based on the artificial neural networks (ANN) is one of the underexplored problems of continuous Spatio-temporal field interpolation. Selecting the best training subset for modelling the spatial distribution of elements in the topsoil is not a trivial task since the sampling points are not equivalent. Errors and outliers, which are present in the distribution, can be misleading. Most of the points, which contain utility information, should be involved in modelling. The raw data were Chromium (Cr) and Manganese (Mn) contents in the topsoil on the residential areas in Noyabrsk and Novy Urengoy (South Part) cities (Russian subarctic zone). A three-step algorithm for extraction of the raw data dividing into training and test subsets for modelling the spatial distribution of the feature presented. The spatial distributions of the element contents in the topsoil, which constructed by the multilayer perceptron (MLP), consider spatial heterogeneity and training rules. The MLP structure was chosen by the minimization of the root mean squared error (RMSE). For each territory, according to the number of hits in the training subset, the points divided into three classes: the «elite», «middle», and «useless». Considering this information at the stage of dividing the raw sample makes it possible to increase the accuracy of the predictive model.