Next Article in Journal
Modelling of Water Drop Movement and Distribution in No Wind and Windy Conditions for Different Nozzle Sizes
Next Article in Special Issue
Swimming Pool-Related Outbreak of a Rare gp60 Subtype of Cryptosporidium hominis, England, October 2016
Previous Article in Journal
Silver-Modified β-Cyclodextrin Polymer for Water Treatment: A Balanced Adsorption and Antibacterial Performance
Previous Article in Special Issue
Inland and Coastal Bathing Water Quality in the Last Decade (2011–2020): Croatia vs. Region vs. EU
 
 
Article

Modelling Bathing Water Quality Using Official Monitoring Data

1
Faculty of Science, Ruđera Boškovića 33, 21000 Split, Croatia
2
Ericsson Nikola Tesla, Poljička Cesta 39, 21000 Split, Croatia
3
Institute of Oceanography and Fisheries, Šetalište I. Meštrovića 63, 21000 Split, Croatia
4
Teaching Institute of Public Health of Split-Dalmatia County, Vukovarska 46, 21000 Split, Croatia
*
Author to whom correspondence should be addressed.
Academic Editor: Athena Mavridou
Water 2021, 13(21), 3005; https://doi.org/10.3390/w13213005
Received: 27 August 2021 / Revised: 20 October 2021 / Accepted: 22 October 2021 / Published: 26 October 2021
(This article belongs to the Special Issue Healthy Recreational Waters: Sanitation and Safety Issues)
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%. View Full-Text
Keywords: faecal indicator bacteria; E. coli; intestinal enterococci; bathing water quality prediction; predictive models; neural network; random forest faecal indicator bacteria; E. coli; intestinal enterococci; bathing water quality prediction; predictive models; neural network; random forest
Show Figures

Figure 1

MDPI and ACS Style

Džal, D.; Kosović, I.N.; Mastelić, T.; Ivanković, D.; Puljak, T.; Jozić, S. Modelling Bathing Water Quality Using Official Monitoring Data. Water 2021, 13, 3005. https://doi.org/10.3390/w13213005

AMA Style

Džal D, Kosović IN, Mastelić T, Ivanković D, Puljak T, Jozić S. Modelling Bathing Water Quality Using Official Monitoring Data. Water. 2021; 13(21):3005. https://doi.org/10.3390/w13213005

Chicago/Turabian Style

Džal, Daniela, Ivana Nižetić Kosović, Toni Mastelić, Damir Ivanković, Tatjana Puljak, and Slaven Jozić. 2021. "Modelling Bathing Water Quality Using Official Monitoring Data" Water 13, no. 21: 3005. https://doi.org/10.3390/w13213005

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop