Depletion of dissolved oxygen (DO) is a major cause of fish kills in urban streams. Although forecasting short‐term DO concentrations in streams prior to hypoxic events is necessary, such efforts have been rarely made. In this study, 24‐h forecasting models were developed for DO concentrations in three urban streams of South Korea. To forecast the DO concentrations at the outlet sites, which coincide with fish kill hot spot areas, water quality parameters at the lower reaches and hydrometeorological parameters were used as input variables. The monitoring data were measured hourly between 2017 and 2018 and divided into training and test sets at a ratio of 8:2. Tenfold cross validation was performed for hyperparameter optimization. Due to the dynamic characteristics of DO concentrations and the discontinuity in time‐series data, a long short‐term memory (LSTM) neural network modeling approach was selected. Overall, a high degree of accuracy was recorded for all study streams. Although hypoxic events were forecast with lower accuracy, the timing and magnitude of abrupt DO depletion were well captured. Water temperature and DO concentrations at the lower reaches and 24‐h cumulative precipitation were important variables for forecasting DO concentrations at all stream outlets. In particular, the importance of cumulative precipitation across all streams indicated that the effects of nonpoint sources were critical in depleting DO in urban streams. Monitoring of both lower reaches and outlets in conjunction with a variable importance analysis enhanced interpretability of the LSTM model outputs. This study improves our understanding of precursors of hypoxic events in urban streams.

Harmful algal blooms (HABs) pose a potential risk to human and ecosystem health. HAB occurrences are influenced by numerous environmental factors; thus, accurate predictions of HABs and explanations about the predictions are required to implement preventive water quality management. In this study, machine learning (ML) algorithms, i.e., random forest (RF) and extreme gradient boosting (XGB), were employed to predict HABs in eight water supply reservoirs in South Korea. The use of synthetic minority oversampling technique for addressing imbalanced HAB occurrences improved classification performance of the ML algorithms. Although RF and XGB resulted in marginal performance differences, XGB exhibited more stable performance in the presence of data imbalance. Furthermore, a post hoc explanation technique, Shapley additive explanation was employed to estimate relative feature importance. Among the input features, water temperature and concentrations of total nitrogen and total phosphorus appeared important in predicting HAB occurrences. The results suggest that the use of ML algorithms along with explanation methods increase the usefulness of predictive models as a decision-making tool for water quality management.

The effects of tree species on soil organic carbon (SOC) content have been evaluated in many studies, but only with a relatively small number of sample plots, resulting in ambiguous conclusions. Here we used a total of 595 forest plots in South Korea to investigate the role of four grouped tree species—pines, oaks, other conifers, and other deciduous trees—in the forest SOC content in both forest floors and mineral soils. Significant differences were observed in SOC content among the groups. Pines contained 7.12 Mg C ha^‐1 of organic carbon in forest floors, whereas oaks and other deciduous trees contained 5.39 and 5.41 Mg C ha^‐1, respectively. In contrast, oaks and other deciduous trees contained ~66 Mg C ha^‐1 of organic carbon each in mineral soils (0‐30 cm depth), whereas pines contained 49.50 Mg C ha^‐1. The total SOC content including both forest floors and mineral soils was the largest under oaks and the smallest under other coniferous trees, due to SOC being approximately an order of magnitude higher in mineral soils than in forest floors. The effects of tree species on SOC storage became apparent for the forest stands with >20‐year‐old trees, which suggests that the observed differences in the SOC content are likely due to the current stands rather than remnants of previous stands. The decomposition rates of organic materials could be a controlling factor affecting SOC storage, rather than inputs of photosynthesized products to soils.

The pressure on water infrastructure has increased due to an increase in the number of aging water pipes. Aging pipes are prone to failure, causing significant financial losses and service disruptions. The increasing number of aged pipes and limited budget for pipe rehabilitation or replacement necessitates water infrastructure asset management to ensure sustainable water supply services. In this study, contingent valuation was used to estimate the willingness to pay (WTP) and value improved water supply services through the implementation of asset management. To estimate the WTP at the individual and county levels, we performed a nationwide survey including eight provinces and 24 counties/cities with distinct water supply service performances. At the individual level, the median WTP estimated using the double-bounded dichotomous choice model was 249.50 KRW/month (0.22 USD/month). The results showed that high-level satisfaction of customers with water supply services and positive price perception of water bills resulted in a high WTP. At the county level, decreasing water supply service performances were associated with a low WTP, indicating that proper interventions by local utilities are required to achieve sustainable water supply services. Our results provide a quantitative basis for decision-making in implementation of water infrastructure asset management.