Predictive modeling of microbiological seawater quality classification in karst region using cascade model

TL;DR

This study introduces a cascade machine learning model to predict seawater quality in a karst region, addressing data imbalance and considering groundwater influences, with potential to serve as a standalone water quality assessment tool.

Contribution

The paper proposes a novel cascade model for seawater quality prediction that accounts for karst terrain effects and data imbalance, enhancing monitoring accuracy.

Findings

Cascade model improves prediction accuracy over traditional methods.

Groundwater sources significantly influence E. coli levels.

Model has potential to operate independently for water quality classification.

Abstract

In this paper, an in-depth analysis of Escherichia coli seawater measurements during the bathing season in the city of Rijeka, Croatia was conducted. Submerged sources of groundwater were observed at several measurement locations which could be the cause for increased E. coli values. This specificity of karst terrain is usually not considered during the monitoring process, thus a novel measurement methodology is proposed. A cascade machine learning model is used to predict coastal water quality based on meteorological data, which improves the level of accuracy due to data imbalance resulting from rare occurrences of measurements with reduced water quality. Currently, the cascade model is employed as a filter method, where measurements not classified as excellent quality need to be further analyzed. However, with improvements proposed in the paper, the cascade model could be ultimately used as a standalone method.