Treffer: Regional-scale mapping for determining geochemical background values in soils of the Itacaiúnas River Basin, Brazil: The use of compositional data analysis (CoDA)

This study aims at providing high quality soil geochemical data at a regional scale (1 sample per 25 km2) to understand the source and distribution of potentially toxic elements (PTEs: Al, As, Ba, Cd, Cu, Co, Cr, Fe, Hg, Mo, Mn, Ni, Pb, Se, U, V, and Zn) and to define their geochemical background threshold values (GBTVs) in the Itacaiúnas River Basin (IRB), Brazilian Amazon. A total of 2958 soil samples were collected at two depths (surface: 0–10 cm; bottom: 30–50 cm) and the fine fractions (<0.117 mm) were analyzed by ICP-MS and ICP-AES after aqua-regia digestion. The compositional nature of geochemical data was evaluated using the log-ratio approach and compared with traditional methods. Results show that compared to raw/log-transformation, centred log-ratio (clr) transformation improves spatial mapping and also better separated variables in Principal Component Analysis (PCA). Correlation analysis based on the isometric log-ratio (ilr) transformation in heat-maps provides reliable and better structure of the results. The spatial maps (clr) indicate that most of the elements in surface and bottom soils are mainly governed by underlying bedrock geology (parent lithologies and mineralization), while anthropogenic factors are insignificant. The resulting clr-based PCA and cluster analyses associated with geological information indicate that geochemical patterns of Fe-Ti-V-Cr-Sc can be linked to mafic to intermediate metavolcanic rocks and banded-iron formations, which are dominant in the Carajás basin, while Ni and Cr distribution pattern is attributed to mafic and ultramafic lithologies, and Cu anomalous values are mainly related to hydrothermal mineralized copper belts. Among the statistical methods applied for estimation of GBTVs, TIF produced the highest BTVs, followed by 98th and mMAD, with few exceptions, while mMAD was considered the more suitable for defining GBTVs. The number of potential anomalies of PTEs identified by these methods follow the order of MAD > 98th > TIF or MAD > TIF > 98th, ...