Spatial distribution prediction of soil As in a large-scale arsenic slag contaminated site based on an integrated model and multi-source environmental data

Li, Geng; Zhou, Xin; Li, Qiang; Shi, Ying; Guo, Guanlin; Zhao, Long; Wang, Jie; Su, Yingqing; Zhang, Chao

doi:10.1016/j.envpol.2020.115631

Cited by 57 publications

(20 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The F1 fraction of Pb changed only slightly with depth at all three points, which could be due to its limited mobility (Yang et al, 2020). The proportion of various fractions of Ni, Cu and As changed little with depth at all three sampling point, meaning that the fractions of these three elements were less affected by human activities and more influenced by natural factors such as parent materials (Li et al, 2020).…”

Section: Fraction Distribution Of Heavy Metalsmentioning

confidence: 87%

“…The concentrations of heavy metals were influenced by many factors, including the distribution and release of pollution sources, the characteristic of heavy metals and soil, as well as environmental conditions (Liu et al, 2020). The descriptive statistical concentrations of five heavy metals in the topsoil at the Wenshan site are summarized in Table 1.…”

Section: Descriptive Statistics Of Heavy Metal Concentrations In the Topsoilmentioning

confidence: 99%

“…The spatial distribution of heavy metals in soil is the basis for the evaluation of pollution risk and decision-making, which was also essential for the understanding the environmental behavior of heavy metals (Liu et al, 2020;Niazi et al, 2011). The map of heavy metal distribution in the topsoil was generated in Surfer 11.0 using the Kriging interpolation method (Fig.…”

Section: Spatial Distribution Of Heavy Metalsmentioning

confidence: 99%

See 2 more Smart Citations

Distribution and risk assessment of heavy metals in soil in a commonly used mining area

Xu¹,

Dai²,

Skuza³

et al. 2021

Preprint

View full text Add to dashboard Cite

This study investigated the spatial, vertical and fraction distribution, multivariate statistical analysis, as well as assessed pollution levels and health risks posed by heavy metals at the Wenshan mining area. There were 6 sampling points at the site, from which a total of 32 samples were collected. The eastern and south-eastern parts of the site were heavily polluted, while the western and north-western parts were less contaminated. As pollution was particularly severe in the topsoil, with the mean value of 503.31 mg kg− 1 being more than 25-fold higher than the risk screening value. As content in all layers was greater than the standard risk screening value in the three typical profiles. The proportion of various Ni, Cu and As fractions changed slightly with depth at all three sampling points, and the residual fraction percentage accounted for more or nearly 80% of the total concentration. In addition, a significantly negative correlation (p < 0.05) was detected between Ni and As (-0.85), indicating a different source of these two elements. Principal component analysis demonstrated that two PCs, i.e. PC1, attributed to human activities, e.g. mining activities and transport, and PC2, defined as natural sources, were responsible for 80.632% of the total variance. As posed severe ecological and unacceptable health risks, i.e. non-carcinogenic and carcinogenic risks both for adults and children. Therefore, a comprehensive understanding of the characteristics of mining pollutants and improved emission management in the mining process are essential to protect the environment and health of local residents.

show abstract

Section: Fraction Distribution Of Heavy Metalsmentioning

confidence: 87%

Section: Descriptive Statistics Of Heavy Metal Concentrations In the Topsoilmentioning

confidence: 99%

Section: Spatial Distribution Of Heavy Metalsmentioning

confidence: 99%

See 1 more Smart Citation

Distribution and risk assessment of heavy metals in soil in a commonly used mining area

Xu¹,

Dai²,

Skuza³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The advancement of geographic information technology has also led to the application of remote sensing in many disciplines [18][19][20][21]. In the field of environmental science, many scholars have combined spectral data and machine learning methods for the estimation of heavy metal content in soil, such as support vector regression (SVR) [22,23], artificial neural network (ANN) [24][25][26][27], and random forest (RF) [28][29][30]. On the one hand, the high dimension and redundancy characteristics of spectral data for estimation of heavy metal pollution in soil seriously affect the accuracy and stability of the estimation model.…”

Section: Introductionmentioning

confidence: 99%

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

Shi

Hou

et al. 2022

Land

View full text Add to dashboard Cite

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.

show abstract

“…However, due to financial availability, the number of these samples is quite limited and they are usually located sparsely compared to the size of the contaminated site . Thus, it has been a great interest to compute the best estimates of the actual distribution based on those isolated measurements of contaminant concentrations. − …”

Section: Introductionmentioning

confidence: 99%

Application of the Deep Learning Algorithm to Identify the Spatial Distribution of Heavy Metals at Contaminated Sites

et al. 2021

View full text Add to dashboard Cite

Accurate estimation of the spatial distribution of pollutants, such as heavy metals, is indispensable in investigation of contaminated sites. In this paper, we develop a novel deep learning (DL) algorithm, in which the data value of the target point is predicted by a nearest-neighbor neural network. Using 20 hypothetical sites and a real-world one, the developed DL is compared with several commonly used kriging algorithms (e.g., ordinary kriging). By taking the results of ordinary kriging as the benchmark, the interpolation accuracy can be improved by an average of 38.2% and 11.2–36.6%, respectively. The comparisons also indicate that the new method performs much better in cases with significant spatial variability by alleviating the smoothing effect and the edge effect in the kriging. Upon further examination of the developed method, the prediction accuracy is found to first increase and then decrease with the number of neighbor points. Moreover, the influence of the sampling density is limited if the number exceeds a certain threshold (e.g., n = 64 in our case). As a preliminary attempt of applying the DL algorithm at individual contaminated sites, this work provides a general alternative method to identify the spatial distribution of heavy metals.

show abstract

Spatial distribution prediction of soil As in a large-scale arsenic slag contaminated site based on an integrated model and multi-source environmental data

Cited by 57 publications

References 38 publications

Distribution and risk assessment of heavy metals in soil in a commonly used mining area

Distribution and risk assessment of heavy metals in soil in a commonly used mining area

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

Application of the Deep Learning Algorithm to Identify the Spatial Distribution of Heavy Metals at Contaminated Sites

Contact Info

Product

Resources

About