Methods to investigate the geochemistry of groundwaters with values for nitrogen compounds below the detection limit

Groundwaters, like other natural waters, are solutions of a variety of substances in the solvent water. Human impact upon groundwater systems has created many environmental problems so that hydrogeochemical studies related to pollution have become very important. In this context high abundance of nitrogen species, particularly nitrates, can cause adverse health effects, their main sources being fertilizer, animal or human waste, natural soil organic matter, nitrogen fixation and rain. Graphical representations of hydrogeochemical data (for example molar ratio diagrams, stochiometric diagrams, triangular diagrams, mixing diagrams) pose considerable problems if statistical evaluations have to be performed. In fact, since hydrochemical data are compositional (proportional data), their sample space is the simplex, a constrained space where the application of the standard geometrical approach may provide misleading information. In this paper classical binary diagrams used to investigate the whole chemistry of water as well as the behaviour of nitrogen species were substituted by new equivalent graphs coherent with the properties of compositional data, thus opening new perspectives in the evaluation of geochemical processes affecting water resources. Moreover, since nitrogen species are often affected by the presence of numerous data below the detection limit, their role was investigated by considering different imputation methods, and evaluating their performance in the sub-composition NH4+,NO2-, NO3-, NO3-. The first phase of the analysis did not consider the presence of data below the detection limit but subsequently, step by step, the possibility to recuperate this type of information was explored. The opportunity to recover information about data below the detection limit from the variance-covariance structure of the whole composition (Ca-2(+), Mg2+, K+, Na+, HCO3-, Cl- and SO42- and available nitrogen data) was also investigated by considering a multivariate framework. The approaches, coherent with compositional data analysis theory, pointed out interesting aspects of 1) the relationships in the sub-composition of NH4+, NO2-, and NO3-, giving us a different perception of the background level of these species as well as of their source; 2) the effects on the variance-covariance structure of the whole composition (main anions and cations and nitrogen species); and 3) the loss of information about the covariance between chemical variables (coherence of geochemical behaviour), which is able to affect the understanding of geochemical systemsThis research has been supported by the University of Florence (ex-60% 2011/2012 funds), Geobasi Project (Tuscany Region, Italy), Scottish Government's Rural and Environment Science and Analytical Services (RESAS) and "METRICS" (Ref. MTM2012-33236) project of the Spanish Ministry of Economy and Competitivenes