Assessment of spatial distribution of soil heavy metals using ANN-GA, MSLR and satellite imagery

Abstract

This study aims to assess and compare heavy metal distribution models developed using stepwise multiple linear regression (MSLR) and neural network-genetic algorithm model (ANN-GA) based on satellite imagery. The source identification of heavy metals was also explored using local Moran index. Soil samples (n = 300) were collected based on a grid and pH, organic matter, clay, iron oxide contents cadmium (Cd), lead (Pb) and zinc (Zn) concentrations were determined for each sample. Visible/near-infrared reflectance (VNIR) within the electromagnetic ranges of satellite imagery was applied to estimate heavy metal concentrations in the soil using MSLR and ANN-GA models. The models were evaluated and ANN-GA model demonstrated higher accuracy, and the autocorrelation results showed higher significant clusters of heavy metals around the industrial zone. The higher concentration of Cd, Pb and Zn was noted under industrial lands and irrigation farming in comparison to barren and dryland farming. Accumulation of industrial wastes in roads and streams was identified as main sources of pollution, and the concentration of soil heavy metals was reduced by increasing the distance from these sources. In comparison to MLSR, ANN-GA provided a more accurate indirect assessment of heavy metal concentrations in highly polluted soils. The clustering analysis provided reliable information about the spatial distribution of soil heavy metals and their sources.

Modification of nano-clays with ionic liquids for the removal of Cd (II) ion from aqueous phase

“…Cadmium is the seventh most toxic heavy metal as per the agency for toxic substances and disease registry (ATSDR) ranking and also low level permissible exposure to humans (Kabata-Pendias, 2010). It has various anthropogenic sources of exposure like industrial activities and transportation, and natural factors like wind, topography and streams that distribute Cd (II) into the environment (Nadari et al, 2017). In trace quantities, Cd (II) has many hazardous effects on plants by disordering their metabolisms cycles (Shi et al, 2010;Nazar et al, 2012) and cause of many human diseases like digestive system, respiratory system, acute intoxication, kidney damage, bone damage and carcinogenicity (Godt et al, 2006).…”

Comparison of Models for Spatial Distribution and Prediction of Cadmium in Subtropical Forest Soils, Guangdong, China

“…Among modeling approaches, ANN has been widely used to estimate some soil properties including Cd [31][32][33]. In a recent conference, Ghazi [31] presented an approach in which a neural network is used to estimate the concentrations of Cd with variables such as soil retention, release reactions of solutes, and the soil matrix.…”

“…Some studies, although few, have been conducted to address the most complicated but important task of estimating spatial and temporal concentrations of Cd. For example, an ANN-GA model (artificial neural network-genetic algorithm), which has been proven to have better performance than ANN alone, was developed by Nadri et al to estimate Cd removal and determine heavy metal contamination [32]. However, due to the black-box property of this method, many networks developed from this algorithm lack ecological, biological, geological, and topological principles.…”

Characterizing Khetri copper mine environment using geospatial tools

“…Correlation between the pixel values of satellites imaginary and analyzed parameters in soil and water is continuously being monitored for the development of suitable predication model. Nadari et al [43] reported that the assessment and predication of heavy metals around the contaminated sites using stepwise multiple linear regression and neural network-genetic algorithm model based on visible/near-infrared reflectance of electromagnetic range of satellite imagery provides reliable information. Thus, relation between satellite spectral response and elemental concentration in soil is needed to be study.…”