No abstract

No abstract

Predictive models of bathing water quality are a useful support to traditional monitoring and provide timely and adequate information for the protection of public health. When developing models, it is critical to select an appropriate model type and appropriate metrics to reduce errors so that the predicted outcome is reliable. It is usually necessary to conduct intensive sampling to collect a sufficient amount of data. This paper presents the process of developing a predictive model in Kaštela Bay (Adriatic Sea) using only data from regular (official) bathing water quality monitoring collected during five bathing seasons. The predictive modelling process, which included data preprocessing, model training, and model tuning, showed no silver bullet model and selected two model types that met the specified requirements: a neural network (ANN) for Escherichia coli and a random forest (RF) for intestinal enterococci. The different model types are probably the result of the different persistence of two indicator bacteria to the effects of marine environmental factors and consequently the different die-off rates. By combining these two models, the bathing water samples were classified with acceptable performances, an informedness of 71.7%, an F-score of 47.1%, and an overall accuracy of 80.6%.

We analyzed and discussed bathing water quality at 11 official bathing sites in Kaštela (Croatia) in the period 2009-2022. The results showed spatial and temporal variations in quality. The worst bathing water quality was in the eastern part of the area, at beaches Torac, Kamp and Gojača. Levels of indicator microorganisms at identified sources of fecal pollution near these beaches indicate a significant load of fecal material to these areas. The observed decrease in annual fecal indicator bacteria exceedances, while not statistically significant, indicates a trend toward improvement in water quality. The number of sites with worse annual and final assessment showed a decreasing trend only since 2017 and 2020, respectively, which is not a ‘sufficient’ time period to draw a clear conclusion about the trend. The improvements are probably the result of intensive work in recent years to improve the sewage system in the area. In the annual and final assessment, bathing sites from Kaštela with ‘poor’ water quality accounted on average for more than 27% of all waters with ‘poor’ quality in Croatia. This implies that additional efforts are needed to eliminate the sources of fecal pollution in the area.