The design of the Rovni Lake reservoir in the Kolubara District, western Serbia, is the basis for the regional water-supply system there. The design was promoted as an example of integrative and sustainable water management, with regard to the planned provision for long-term municipal water supply in the Kolubara region, as well as for the regulation of the downstream river flow. Hydrogeological analyses, however, have indicated three key issues that contest this sustainable water-management model: (1) the capability of the available groundwater sources to fully meet the drinking water demands in the region, (2) a pronounced risk of water loss from the reservoir, and (3) a pronounced risk of karst aquifer contamination. The Rovni project ignores the hydrogeological properties of a karst aquifer and thereby needlessly threatens the groundwater resource. Hence, modifications to the project are recommended in order to mitigate or eliminate the most significant construction and ecological risk factors and to improve sustainable exploitation and integrative water-resource management.

This study developed methodology for statistically assessing groundwater contamination mechanisms. It focused on microbial water pollution in low-income regions. Risk factors for faecal contamination of groundwater-fed drinking-water sources were evaluated in a case study in Juba, South Sudan. The study was based on counts of thermotolerant coliforms in water samples from 129 sources, collected by the humanitarian aid organisation Médecins Sans Frontières in 2010. The factors included hydrogeological settings, land use and socio-economic characteristics. The results showed that the residuals of a conventional probit regression model had a significant positive spatial autocorrelation (Moran’s I = 3.05, I-stat = 9.28); therefore, a spatial model was developed that had better goodness-of-fit to the observations. The most significant factor in this model (p-value 0.005) was the distance from a water source to the nearest Tukul area, an area with informal settlements that lack sanitation services. It is thus recommended that future remediation and monitoring efforts in the city be concentrated in such low-income regions. The spatial model differed from the conventional approach: in contrast with the latter case, lowland topography was not significant at the 5% level, as the p-value was 0.074 in the spatial model and 0.040 in the traditional model. This study showed that statistical risk-factor assessments of groundwater contamination need to consider spatial interactions when the water sources are located close to each other. Future studies might further investigate the cut-off distance that reflects spatial autocorrelation. Particularly, these results advise research on urban groundwater quality.