Reconstruction and analysis of negatively buoyant jets with interpretable machine learning

In this paper, negatively inclined buoyant jets, which appear during the discharge of wastewater from processes such as desalination, are observed. A detailed numerical investigation is necessary to minimize harmful effects and assess environmental impact. Selecting appropriate geometry and working conditions for minimizing such effects often requires numerous experiments and numerical simulations. For this reason, the application of machine learning models is proposed. Several models including Support Vector Regression, Artificial Neural Networks, Random Forests, XGBoost, CatBoost and LightGBM were trained. The dataset was built with numerous OpenFOAM simulations, validated by experimental data from previous research. The average prediction of ML models has R² 0.94±0.05, RMSE 0.42±0.14 and RRSE 0.24 ± 0.09, whereas the best prediction was obtained by Artificial Neural Network with R² 0.98, RMSE 0.28 and RRSE 0.16. To understand the influence of input parameters on the geometrical characteristics of inclined buoyant jets, the SHAP feature interpretation method was used.

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

This paper presents an in-depth analysis of seawater quality measurements during the bathing seasons from year 2009 to 2020 in the city of Rijeka, Croatia. Due to rare occurrences of measurements with less than excellent water quality, considered dataset is deeply imbalanced. Additionally, it incorporates measurements under the influence of submerged groundwater discharges (SGD), which were observed in some bathing locations. These discharges were previously thought to dry up during the summer season and are now suspected to be one of the causes of increased Escherichia coli values. Consequently, and in view of the fact that the accuracy of prediction models can be significantly influenced by temporal and spatial variation of the input data, a novel cascade prediction modeling strategy was proposed. It consists of a sequence of prediction models which tend to identify general environmental conditions which confidently lead to excellent bathing water quality. The proposed model uses environmental features which can rather easily be estimated or obtained from the weather forecast. The model was trained on a highly biased dataset, consisting of data from locations with and without SGD influence, and for the time period spanning extremely dry and warm seasons, extremely wet seasons, as well as normal seasons. To simulate realistic application, the model was tested using temporal and spatial stratification of data. The cascade strategy was shown to be a good approach for reliably detecting environmental parameters which produce excellent water quality. Proposed model is designed as a filter method, where instances classified as less-than-excellent water quality require further analysis. The cascade model provides great flexibility as it can be customized to the particular needs of the investigated area and dataset specifics.

Impacts of Atmospheric and Anthropogenic Factors on Microbiological Pollution of the Recreational Coastal Beaches Neighboring Shipping Ports

A comparative study of the two northeastern ports of the Adriatic Sea indicated that the port of Rijeka is microbiologically more loaded than the port of Pula and posing a greater threat to other ports through a potential transfer of pathogens by ballast water. Fecal indicator bacteria, Escherichia coli and intestinal enterococci, were investigated seasonally in 2014–2015 in the ports and during the bathing season monitoring in the two bays where ports are located in 2009–2020. In addition, the indicators and pathogens related to human health were determined in the ports’ seawater and sediment. The determined factors contributing to microbiological pollution were higher number of tourists and locals, potential wastewater and ballast water discharge and enclosed port configuration, with high solar radiation and low precipitation reducing the negative effects. Our research points to the necessity of including Clostridium perfringens in monitoring beach sand during the bathing seasons and a wider list of pathogens in port monitoring due to a potential transfer by shipping ballast water.

Machine-Learning Classification of a Number of Contaminant Sources in an Urban Water Network

In the case of a contamination event in water distribution networks, several studies have considered different methods to determine contamination scenario information. It would be greatly beneficial to know the exact number of contaminant injection locations since some methods can only be applied in the case of a single injection location and others have greater efficiency. In this work, the Neural Network and Random Forest classifying algorithms are used to predict the number of contaminant injection locations. The prediction model is trained with data obtained from simulated contamination event scenarios with random injection starting time, duration, concentration value, and the number of injection locations which varies from 1 to 4. Classification is made to determine if single or multiple injection locations occurred, and to predict the exact number of injection locations. Data was obtained for two different benchmark networks, medium-sized network Net3 and large-sized Richmond network. Additionally, an investigation of sensor layouts, demand uncertainty, and fuzzy sensors on model accuracy is conducted. The proposed approach shows excellent accuracy in predicting if single or multiple contaminant injections in a water supply network occurred and good accuracy for the exact number of injection locations.

Temporal variations analyses and predictive modeling of microbiological seawater quality

Bathing water quality is a major public health issue, especially for tourism-oriented regions. Currently used methods within EU allow at least a 2.2 day period for obtaining the analytical results, making outdated the information forwarded to the public. Obtained results and beach assessment are influenced by the temporal and spatial characteristics of sample collection, and numerous environmental parameters, as well as by differences of official water standards. This paper examines the temporal variation of microbiological parameters during the day, as well as the influence of the sampling hour, on decision processes in the management of the beach. Apart from the fecal indicators stipulated by the EU Bathing Water Directive (E. coli and enterococci), additional fecal (C. perfringens) and non-fecal (S. aureus and P. aeriginosa) parameters were analyzed. Moreover, the effects of applying different evaluation criteria (national, EU and U.S. EPA) to beach ranking were studied, and the most common reasons for exceeding water-quality standards were investigated. In order to upgrade routine monitoring, a predictive statistical model was developed. The highest concentrations of fecal indicators were recorded early in the morning (6 AM) due to the lack of solar radiation during the night period. When compared to enterococci, E. coli criteria appears to be more stringent for the detection of fecal pollution. In comparison to EU and U.S. EPA criteria, Croatian national evaluation criteria provide stricter public health standards. Solar radiation and precipitation were the predominant environmental parameters affecting beach water quality, and these parameters were included in the predictive model setup. Predictive models revealed great potential for the monitoring of recreational water bodies, and with further development can become a useful tool for the improvement of public health protection.