A New Model of Heavy Metal Transport in the Soil Using Nonlinear Artificial Neural Networks

The contamination of the soil by heavy metals is still of great interest to environmental scientists because of further metal mobilization and the possibility of groundwater and surface water pollution. One of the most efficient tools for risk assessment is a combination of an ex situ column leaching experiment with computer modeling. This paper presents the results of a chemometric treatment of data from such experiments and describes the development of a model based on an artificial neural networks topology. The column leaching experiments have been used to find dependencies between different physiochemical parameters of soil and heavy metals concentrations in leachate. Investigations of three different soil types has been found to be sufficient to create the local model of heavy metal transport within soil profile.