Self-organizing map for the detection of seasonal variations in Sidi Chahed Dam sediments (Northern Morocco)

Abstract

A database of 88 superficial sediment samples, distributed in space and time, was collected from the Sidi Chahed Dam (northeast of Meknes city, Morocco) and from four other reference stations (in the same region) located in supposedly uncontaminated environments. Analyses were focused on the physico-chemical characteristics and concentrations of heavy metals (Fe, Mn, As, Cu, Zn, Pb, Cr, Cd). The database was processed by advanced statistical analysis techniques. The method of classification by self-organizing maps (SOM) was used, permitting understanding and visualization of the spatial and temporal distribution of samples. Principal component analysis (PCA) and SOM hierarchical classification (SOM-HC) were used to validate the classification and detect seasonal variations in heavy metal concentrations. Dependencies between different metal tracers were considered and their spatio-temporal distribution is shown, together with the ranking of clusters, according to their pollution levels. Thus, autumn samples were the only ones with high concentrations of As, compared to the four reference stations. This is due to leaching of bare soil by the first stormy rains of autumn. In winter and spring samples, the concentrations of tracers Mn, Zn, Cu, Pb, Cd and Cr were relatively high compared to those of the reference stations. Summer sample concentrations were most comparable with the reference stations, probably due to the scarcity of rainfall and runoff in this season.