In this study, an ensemble machine learning model was developed to predict the recovery rate of water quality in a water treatment plant after a disturbance. XGBoost, one of the most popular ensemble machine learning models, was used as the main framework of the model. Water quality and operational data observed in a pilot plant were used to train and test the model. Disturbance was determined when the observed turbidity was higher than the given turbidity criteria. Therefore, the recovery rate of water quality at a time t was defined during the falling limb of the turbidity recovery period. It was considered as a relative ratio of the differences between the peak and observed turbidities at time t to the difference between the peak turbidity and turbidity criteria. The root mean square error–observation standard deviation ratio of the XGBoost model improved from 0.730 to 0.373 by pretreatment, removing the observation for the rising limb of the disturbance from the training data. Moreover, Shapley value analysis, a novel explainable artificial intelligence method, was used to provide a reasonable interpretation of the model’s performance.

The quantitative analysis of the disaster effect on water supply systems can provide useful information for water supply system management. In this study, a total disaster index (TDI) was developed using open-source public data in 419 water treatment plants in Korea with 23 input variables. The TDI quantifies the possible effects or damage caused by three major disasters (typhoons, heavy rain, and earthquakes) on water supply systems. The four components (regional factor, risk factor, urgency factor, and response and recovery factor) were calculated using input variables to determine the disaster index (DI) of each disaster. The weight of the input variables was determined using principal component analysis (PCA), and the weights of the DI of three natural disasters and four components used to calculate the TDI were determined by the analytical hierarchy process (AHP). Specifically, two ensemble machine learning models, random forest (RF) and XGBoost (XGB), were used to develop models to predict the TDI. Both models predicted the TDI with the coefficient of determination and root-mean-square error-observations standard deviation ratio of 0.8435 and 0.3957 for the RF model and 0.8629 and 0.3703 for the XGB model, respectively. The relative importance analysis suggests that the number of input variables can be minimized, which improves the models’ practical applicability.

Domestic wastewater treatment facilities(WTF) in Korea consume a lot of energy and generate greenhouse gases in the process of treating contaminated sewage. In response to climate change and the government's carbon neutrality, measures for energy reduction in WTF is an important issue along with water quality management, and simultaneously, diversification of renewable energy based on treatment facilities is essential. The energy independence and renewable energy utilization by facility capacity were analyzed based on sewage statistics (2019) and operation data of the National Sewage Information System. The amount of energy consumed by WTF was analyzed to be 83.6 million TOE, and the renewable energy produced was 10.8 million TOE. In consequence of analysis, the energy independence of domestic WTF in Korea was 12.9%. Among renewable energy, the contribution of biogas was the highest at 83.6%, but the current status of energy independence is somewhat insufficient to energy independence plan of WTF, requiring support for alternatives and policies to produce and secure additional renewable energy. In order to increase and diversify the use of renewable energy, the integrated digestion biogas of organic waste resources, the use of cooling and heating energy based on sewage heat, and the development of salinity gradient power generation were reviewed. Based on this, it was intended to contribute to the preparation of measures to achieve carbon neutrality in sewage treatment facilities.

Making and securing safe drinking water is considered as the most important element and human right for sustainable human life. However, many countries in Africa still have low access to safe water, and in particular, fluorosis symptoms are severe from the people of Africa where there is a lot of groundwater and surface water contaminated with fluoride due to the geological natures. Fluoride is a colorless, tasteless, and odorless element with very strong reactivity and is emitted from the cleaning process of semiconductors and the fertilizer manufacturing industries. Various technologies such as chemical coagulation/precipitation, electrochemical method, ion exchange, separation membrane technology, nanotechnology, and adsorption may be proposed as a technology for removing fluoride for securing safe drinking water. The strengths and weaknesses of each element technology and recent research cases were investigated and analyzed, and an appropriate technology application plan for the sustainable development of emerging and developing countries in Africa was presented. Efficiency of fluoride removal may be important to secure drinking water for developing countries in Africa, but it is necessary to consider the local economic situation and cultural background first for sustainability of the applied technology. Therefore, animal bone-based adsorption process is advantageous in terms of sustainability and can be proposed as a fluoride removal technology suitable for the developing countries in Africa.