Virtual water quality monitoring at inactive monitoring sites using Monte Carlo optimized artificial neural networks: A case study of Danube River (Serbia).

Rationalization of water quality monitoring stations nowadays is applied in many countries. In some cases, missing data from abandoned/inactive stations, spatial and temporal, could be very important, hence the use of artificial neural networks (ANNs) for virtual water quality monitoring at inactive monitoring sites was investigated. The aim was to develop single-output and simultaneous ANNs for the spatial interpolation of 18 water quality parameters at single- and multi-inactive monitoring sites on Danube River course through Serbia.

Evaluation of the origin of sulphate at the groundwater source Ključ, Serbia.

The dual-isotope method of measuring both the δ(34)S and δ(18)O values of dissolved sulphate to assess the origin and fate of groundwater sulphate at the Ključ groundwater source, Serbia is applied. A sampling campaign was conducted in September 2007 during low-flow conditions, obtaining river water and groundwater from observation wells completed in a shallow aquifer formed in alluvial sandy-gravelly sediments. In the shallow groundwater, sulphate concentrations ranged from 56.

Spatial and temporal variability of stable isotopes and biological parameters for the Danube River in Serbia.

This paper presents the results of hydrological, physicochemical, biological, and isotopic investigations of the Danube River along the stretch through Serbian territory conducted during four campaigns in September and November 2007, September 2008 and April 2009. The stable isotope values exhibited significant changes both in the Danube (-10.7 to-9.