Heavy metal concentrations in the soil near illegal landfills in the vicinity of agricultural areas—artificial neural network approach

Abstract

Purpose To anticipate the impact of illegal landfills, development of new models should become a part of environmental risk management strategies. One of such approaches includes applications of the artificial neural network (ANN). The main objective of this study was to elucidate the impact of illegal landfilling on the surrounding soil environment and human health, as well as to establish an artificial neural network (ANN) models for predicting the hazards of illegal landfilling as an effective tool in decision-making and environmental risk management. Methods The identification of heavy metals source in soil was performed by principal component analysis (PCA). To assess the sensitivity of the soil ecosystem to heavy metal concentrations, Soil Quality standards and quantitative indices were used. The possible health effects were valued using the average daily doses (ADDs), hazard quotient (HQ), hazard index (HI), and carcinogenic risk (CR). ANN modeling was used for the prediction of heavy metal concentrations in the soil based on landfill size, municipality size, the number of residents, plant species, soil, and landform types. Results The average values of the pollution indexes for Cd were in the moderately contaminated and very high contamination categories. The $$HQ$$ HQ values were lower than the safe level. Cr and Pb posed a significant $$CR$$ CR for adults and children, and Ni for children. The ANN models have exhibited good generalization power and accurately predicted the output parameters with a high value of the coefficient of determination. Conclusion Concerning heavy metal concentrations, illegal landfills near agricultural soil have a significant impact on the soil ecosystem and people’s health. The developed ANN models can be applied generally to anticipate the heavy metal concentrations in soil, according to the before mentioned input parameters, with high accuracy.

Enhancing Cookie Formulations with Combined Dehydrated Peach: A Machine Learning Approach for Technological Quality Assessment and Optimization

“…The output value, denoted as Y , is determined by transfer functions, with f 1 representing the transfer function for the hidden layer and f 2 for the output layer. The input layer matrix is denoted by X [ 32 , 33 ]: …”