In this study, experiments were carried out to estimate sorptivity of a chitosan foamed structure and its selectivity towards Cu(+2), Zn(+2) and Cr(+6) ions. In the case of single ions it was found that in the whole range of concentrations, experimental data were well described by the Langmuir-Freundlich equation which is a relationship between the amount of adsorbed metal per adsorbent mass unit and equilibrium concentration of the solution. A mathematical description of sorption isotherms of the analyzed ions in the presence of one or two additional ions in the solution is complicated from the theoretical point of view. In this case the application of a neural MLP network was proposed. The network consisted of three inputs corresponding to equilibrium concentrations of particular components, a hidden layer and an output layer. On the basis of available experimental data in the so-called process of network training, the number of hidden neurons and weights of neurons combinations were given. Calculations with the use of MLP enabled description of sorption isotherms for one ion, for selected two and for three ions present at the same time in the solution. The network enabled also an analysis of sorption of the selected ion, taking into account the effect of its concentration on the sorption of other ions. This assessment would not be possible in an experimental way only.