The potential ecological risk assessment of soil heavy metals using self-organizing map

Xiang, Qing; Yu, Huan; Chu, Hongliang; Hu, Mengke; Xu, Tingting; Xu, Xiaoyu; He, Zhiyao

doi:10.1016/j.scitotenv.2022.156978

Cited by 31 publications

(11 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The detailed visualization of variables and observations derived by SOMs revealed the homology in Cd, Pb, and Zn distribution, thus confirming their common origin. The advantage of SOM over other multivariate methods in revealing the correlation and classification of different variables and observations, especially for high-dimensional and complex data sets, is proven in previous studies [ 36 ]. This method can provide more reliable results in complex and linear problems due to their robustness to noise data and extreme values in complex high-dimensional datasets.…”

Section: Discussionmentioning

confidence: 99%

“…During the iterative learning procedure, the SOMs were trained for all possible combinations from 2 to 20 neuron nodes for the X and Y axes. The quality of these alternative topologies was evaluated using the quantization error (QE), which evaluates the resolution of the map, and the topographic error (TE), which indicates the accuracy of the topology preservation of the map [ 35 , 36 ]. The learning rate (α) varied linearly from 0.05 to 0.01, and the neighborhood function was Gaussian.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Spatial distribution and source apportionment of DTPA-extractable metals in soils surrounding the largest Serbian steel production plant

Dragović

Smičiklas

Jović

et al. 2023

Heliyon

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Spatial distribution and source apportionment of DTPA-extractable metals in soils surrounding the largest Serbian steel production plant

Dragović

Smičiklas

Jović

et al. 2023

Heliyon

View full text Add to dashboard Cite

“…This method was later used in studies related to soil HM pollution [ 40 ]. This can comprehensively reflect the potential environmental impacts of HMs [ 41 ]. Some scholars have improved the Hakanson index method by introducing fractions.…”

Section: Methodsmentioning

confidence: 99%

Probabilistic Risk Assessment of Heavy Metals in Mining Soils Based on Fractions: A Case Study in Southern Shaanxi, China

Han,

Fan,

Chen

et al. 2023

Toxics

View full text Add to dashboard Cite

With rapid economic development, soil heavy metal (HM) pollution has emerged as a global environmental concern. Because the toxicity of HMs differs dramatically among various fractions, risk assessments based on these fractions are of great significance for environmental management. This study employed a modified Hakanson index approach to evaluate the possible ecological impacts of soil HMs in a gold mine tailings pond in Shaanxi Province, China. A modified Hakanson–Monte Carlo model was built to perform a probabilistic risk assessment. The results showed that: (1) the exceedance rates of chromium (Cr) and zinc (Zn) were 68.75% and 93.75%, respectively. Moreover, the overall concentrations of nickel (Ni), copper (Cu), arsenic (As), and lead (Pb) were higher than the background soil environmental values in China. (2) HMs with the lowest oxidizable fraction were mostly present in the residual fraction. The oxidizable portions of Cr, Cu, and Pb and the reducible and residual fractions of As were notably distinct. (3) The risk degrees of Cr, Ni, Cu, and Zn were low; those of As and Pb were very high and moderate; and the comprehensive ecological hazard index was very high. This study offers a solid scientific foundation for ecological risk notification and environmental management.

show abstract

“…The degree of neuron correction is an important basis for measuring whether or not SOM algorithm is convergent. When the convergence condition or the number of iterations is reached, the entire SOM learning will end (Xiang et al, 2022). SOM performs the following three processes (Giraudel and Lek, 2001;Ghaseminezhad and Karami, 2011): (1) competition: for each input vector, the neurons in the network calculate the value of their respective discriminant functions, and the neuron with the maximum value of discriminant functions becomes the winner of competition; (2) cooperation: the winning neuron determines the spatial position of input vector in topological neighborhood and activates the adjacent neurons; and (3) adjustment: with the iteration of algorithm, the best matching unit corresponding to the input vector is locally adjusted to enhance its response to similar input vectors.…”

Section: Self-organizing Map (Som)mentioning

confidence: 99%

Analysis of morphological characteristics of gravels based on digital image processing technology and self-organizing map

Qiu³

et al. 2023

J. Arid Land

Self Cite

View full text Add to dashboard Cite

A comprehensive understanding of spatial distribution and clustering patterns of gravels is of great significance for ecological restoration and monitoring. However, traditional methods for studying gravels are low-efficiency and have many errors. This study researched the spatial distribution and cluster characteristics of gravels based on digital image processing technology combined with a self-organizing map (SOM) and multivariate statistical methods in the grassland of northern Tibetan Plateau. Moreover, the correlation of morphological parameters of gravels between different cluster groups and the environmental factors affecting gravel distribution were analyzed. The results showed that the morphological characteristics of gravels in northern region (cluster C) and southern region (cluster B) of the Tibetan Plateau were similar, with a low gravel coverage, small gravel diameter, and elongated shape. These regions were mainly distributed in high mountainous areas with large topographic relief. The central region (cluster A) has high coverage of gravels with a larger diameter, mainly distributed in high-altitude plains with smaller undulation. Principal component analysis (PCA) results showed that the gravel distribution of cluster A may be mainly affected by vegetation, while those in clusters B and C could be mainly affected by topography, climate, and soil. The study confirmed that the combination of digital image processing technology and SOM could effectively analyzed the spatial distribution characteristics of gravels, providing a new mode for gravel research.

show abstract

The potential ecological risk assessment of soil heavy metals using self-organizing map

Cited by 31 publications

References 47 publications

Spatial distribution and source apportionment of DTPA-extractable metals in soils surrounding the largest Serbian steel production plant

Spatial distribution and source apportionment of DTPA-extractable metals in soils surrounding the largest Serbian steel production plant

Probabilistic Risk Assessment of Heavy Metals in Mining Soils Based on Fractions: A Case Study in Southern Shaanxi, China

Analysis of morphological characteristics of gravels based on digital image processing technology and self-organizing map

Contact Info

Product

Resources

About