Analysis of the adsorption and retention models for Cd, Cr, Cu, Ni, Pb, and Zn through neural networks: selection of variables and competitive model

Abstract

In this study, the neural networks are used to predict and explain the behavior of different edaphological variables in the adsorption and retention of heavy metals, both isolated and competing. A comparison with the results obtained using multiple regression, stepwise analysis, and regression trees is performed. In the neural network technique, CEC amorphous and crystallized oxides and kaolinite in the clay fraction are the most selected variables for making the optimal models, while mica and, to a lesser extent, plagioclase, are the next variables selected. Additionally, a competitive model has been considered, using simultaneously different metals. In the competitive model, the model predicts a more intense competence between Pb and Ni for the adsorption process and between Cr and Ni for the retention process.